Claude Design vs Rive

Agent ops

1. ai-native userAn agent can create or modify designs programmatically — through a write-capable API, plugin surface, or MCP tools — not just read them

   weight 2 · round to Rive
   Claude Design~partialprobed4/10

   There's no documented first-party write API or MCP server for Claude Design itself (OpenAPI probe returned 404s), but Claude Code slash-commands (/design, /design-sync) and handoff bundles let an agent programmatically create/modify designs, and one community report describes a working MCP flow pushing Claude Design output into PenPot with reusable components. Missing for 10: official documented MCP server/API surface for Claude Design, broader independent corroboration of agent-driven write access beyond a single anecdote.

   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Rive✓fullprobed8/10

   Rive documents an MCP integration letting AI tools create/modify complex View Models, State Machines, Layouts, and Shapes directly in the Editor, plus RML (a text-based file format) explicitly designed so coding agents can build/modify Rive files programmatically, and a CLI for agent-driven generation. This goes beyond read-only access into genuine write-capable agent tooling. Missing for 10: independent/hands-on verification of the MCP tools working in practice and more detail on the write-scope limits of the MCP server.

   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [claimed-docs] “RML uses XML to describe the objects and relationships in a Rive file... build Rive files with coding agents and other text-based workflows …”
   • [claimed-docs] “It lets you create and modify Rive content as code, making it possible to build Rive files with coding agents and other text-based workflows…”
   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”

   proof ↗⚑ flag

2. ai-native userAn agent can render and export designs — screenshots, images, or production formats — through a documented programmatic surface

   weight 2 · round to Claude Design
   Claude Design~partialprobed5/10

   Docs confirm export to PPTX/PDF/HTML and a Claude Code handoff bundle triggered via /design-sync, and community reports an MCP-based flow (into PenPot) suggesting some programmatic surface exists, but there is no documented API/SDK for rendering or exporting designs and the openapi probe returned 404s, indicating no formal machine-callable spec. missing for 10: documented API/SDK for export, evidence of screenshot/image export via a callable interface, corroborated OpenAPI or MCP server documentation.

   • [claimed-docs] “Export to PPTX, PDF, or HTML, share an org-scoped link, hand off to Claude Code, or send to the apps you already use daily.”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Rive!disputedcontradicted4/10

   Rive's runtimes expose a documented programmatic Renderer interface (rive-gh-1/2/3) and RML lets code/agents construct .riv content (rive-docs-13/20/25), and export docs describe exporting to 'websites, mobile apps, games, videos' (rive-docs-7/8) — suggesting a programmatic render/export surface. However, hands-on community feedback directly contradicts image/video export capability: users report 'no way to export movie files' and ask 'can I export video assets with this!?' with no answer (rive-comm-3, rive-comm-10), indicating the actual exportable surface is limited to the .riv runtime format rather than screenshots/images/production video as the story requires. Missing for 10: documented API/CLI for agent-triggered screenshot or image/video export, and confirmation this gap has been resolved.

   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”
   • [github] “The built-in GPU renderer (RiveRenderer) has RenderContextImpl backends for Metal, Vulkan, D3D11, D3D12, and OpenGL/WebGL.”
   • [claimed-docs] “Export once and use your interactive graphics across websites, mobile apps, games, videos, and more.”
   • [claimed-docs] “You can use the same exported file across supported runtimes, including web, mobile, game engines, and other platforms.”
   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”
   • [community] “It's so insane they don't offer any way to export movie files. The animation IDE is decent. Nowhere near as good as Flash was. But at least …”
   • [community] “But can I export video assets with this!? That's my question - I've had to resort to WebGL for a lot of this so far.”

   proof ↗⚑ flag

3. ai-native userMy coding agent can pull real design context — frames, variables, screenshots, component mappings — through an MCP server or API to implement the design

   weight 3 · round drawn
   Claude Design~partialcommunity5/10

   Claude Design ships explicit hand-off paths for coding agents — /design-sync to pull the design system into Claude Code, packaged handoff bundles, and import from GitHub/codebase/component libraries — which functionally lets an agent implement designs with real context. However, the mechanism is documented as slash-command/bundle integration rather than an explicit MCP server or general API exposing frames, variables, screenshots, and component mappings; the one community mention of MCP (comm-7) describes Claude Design consuming an external tool's MCP (PenPot), not exposing its own for coding agents to pull context. missing for 10: first-party documentation of an MCP server or API surface for frames/variables/screenshots/component mappings, and independent verification that agents (not just Claude Code) can pull that structured context.

   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction…”
   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”

   proof ↗⚑ flag

   Rive~partialprobed5/10

   Rive documents an official MCP server connecting the Editor to AI tools, letting agents create/modify View Models (variable-like data), State Machines, Layouts, and Components (rive-docs-19, rive-docs-27, rive-docs-10, rive-docs-11). This covers some 'design context' elements (component mappings, variables via view models) but is framed as agents building/editing Rive content rather than pulling existing frames or screenshots for implementation elsewhere. Missing for 10: explicit screenshot/frame extraction capability, evidence of pulling existing design context (vs. generating new), and independent/hands-on confirmation of the MCP workflow.

   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “Create a component once, then use customized instances of it throughout your Rive file. Changes made to the source component are reflected a…”
   • [claimed-docs] “Data binding — autoBind, view models, bindViewModelInstance”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”

   proof ↗⚑ flag

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round drawn
   Claude Design✓fullprobed7/10

   Probes confirm llms.txt is live (HTTP 200) at the Claude support domain and that Claude Design's own docs page is available in agent-friendly markdown form (docs-md probe), meaning an agent could be pointed at these resources to learn the product. Missing for 10: explicit vendor documentation describing llms.txt as an intended agent-consumption channel, and community/hands-on confirmation that an agent actually used llms.txt to complete a task with Claude Design.

   • [probe] “PROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English #…”
   • [probe] “PROBE docs-md: HTTP 200 at https://support.claude.com/en/articles/14604416-get-started-with-claude-design.md # Get started with Claude Desig…”

   proof ↗⚑ flag

   Rive✓fullprobed7/10

   Rive's docs are served in agent-friendly markdown (docs/*.md return 200) and explicitly point agents to a documentation index at https://rive.app/docs/llms.txt for full-site context, satisfying the 'point an agent at llms.txt or agent-oriented docs' story even though the conventional root-level /llms.txt path 404s. Missing for 10: direct confirmation that /docs/llms.txt itself loads and contains a complete index, and no independent (non-vendor) corroboration of an agent successfully using it.

   • [probe] “PROBE llms.txt: HTTP 404 at https://rive.app/llms.txt”
   • [probe] “PROBE docs-md: HTTP 200 at https://rive.app/docs/getting-started/introduction.md > ## Documentation Index > Fetch the complete documentation…”
   • [claimed-docs] “Create vector graphics, responsive layouts, and reusable components, or import images, audio, fonts, and other assets from your favorite des…”

   proof ↗⚑ flag

2. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Rive
   Claude Design~partialcommunity3/10

   Only a single ambiguous community mention notes 'Claude Design into PenPot via its MCP,' suggesting some MCP-based integration exists, and docs reference pulling data from tools like Salesforce/QuickBooks/HubSpot without specifying MCP as the mechanism. There is no official documentation confirming users can plug arbitrary MCP servers into Claude Design to expose their tools. Missing for 10: first-party docs on MCP server support, clarity on directionality (client vs server), and broader independent confirmation beyond one ambiguous forum comment.

   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [claimed-docs] “Turn this proposal into a one-pager a prospect will want to open. Pull their details from Salesforce and export it as a PDF.”
   • [claimed-docs] “Dig into your numbers in Intuit QuickBooks, plan a promotion to get sales up, generate branded assets in Canva, and get your next campaign s…”

   proof ↗⚑ flag

   Rive✓fullprobed7/10

   Rive documents a first-party MCP integration letting users connect the Rive Editor to AI tools via MCP so AI can perform tasks like creating View Models, State Machines, Layouts, and Shapes, confirmed by both docs and a dedicated probe. Missing for 10: independent/hands-on verification of the MCP integration working in practice and details on which MCP clients/servers are supported beyond the editor's own tools.

   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”

   proof ↗⚑ flag

3. ai-native userUse an official CLI

   weight 2 · round to Rive
   Claude Design—none0/10

   Evidence shows Claude Design integrates with Claude Code via slash commands (/design-sync, /design) and handoff bundles, but this is Claude Code's CLI, not an official CLI shipped by Claude Design itself; no standalone CLI for Claude Design is documented.

   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction…”

   proof ↗⚑ flag

   Rive~partialclaimed3/10

   The Rive homepage claims users can 'let an agent generate them with the CLI' (rive-docs-26), indicating an official CLI exists for AI-agent workflows, but no other evidence pack item documents CLI installation, commands, or usage — most AI-agent tooling evidence instead centers on the MCP server and in-editor AI agent, not a standalone CLI. Missing for 10: dedicated CLI docs/reference, install instructions, command examples, and independent/hands-on corroboration of the CLI working.

   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”
   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”

   proof ↗⚑ flag

4. ai-native userDrive the product through a documented public API

   weight 3 · round to Rive
   Claude Design—none0/10

   Evidence pack shows only end-user product docs (import/export, design generation, handoff to Claude Code) and no documented public API; a direct probe for OpenAPI/swagger specs at claude.com/support returned 404s, and no REST/SDK API for Claude Design is mentioned anywhere.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Rive✓fullprobed8/10

   Rive documents open-source runtime APIs (web, mobile, game engines) for loading and controlling animations programmatically (rive-docs-21, rive-gh-1, rive-docs-14/15), plus a text-based file format (RML) explicitly designed for coding agents and automated workflows (rive-docs-13, 20, 25, 30), and an official MCP server/AI agent integration for driving the Editor via AI tools (rive-docs-19, 27, rive-probe-4, rive-docs-9/18). Together these give an AI-native user multiple documented, agent-friendly ways to control the product beyond the GUI. Missing for 10: a formal REST/OpenAPI-style public API (probe shows 404s for openapi/swagger endpoints) and independent third-party corroboration of programmatic API usage.

   • [claimed-docs] “The Rive runtimes are open-source libraries that allow you to load and control your animations in apps, games, and websites.”
   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”
   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”
   • [claimed-docs] “RML uses XML to describe the objects and relationships in a Rive file... build Rive files with coding agents and other text-based workflows …”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”
   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “Caching a Rive file: Load the .riv into memory once, use it multiple times.”
   • [claimed-docs] “Data binding — autoBind, view models, bindViewModelInstance”

   proof ↗⚑ flag

5. ai-native userBuild against official SDKs

   weight 2 · round to Rive
   Claude Design—none0/10

   Claude Design's evidence pack shows only end-user product docs (mockups, prototypes, handoff, exports) and community discussion of MCP integration with third-party tools like PenPot, but no mention of an official SDK for building against Claude Design itself. A direct probe for API/OpenAPI specs returned 404s, indicating no public developer SDK is documented.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

   Rive✓fullclaimed8/10

   Rive documents open-source official runtimes (SDKs) for web, mobile, game engines, and other platforms, with a public GitHub repo (rive-runtime) implementing the loading/rendering API, plus explicit guidance on caching and using the same exported .riv file across supported runtimes. This directly satisfies 'build against official SDKs' for developers, including AI-native workflows via RML/MCP integration for programmatic file creation. Missing for 10: independent third-party corroboration of SDK quality/completeness across all listed platforms and more granular per-language SDK documentation (e.g., npm/Swift/Kotlin package specifics).

   • [claimed-docs] “You can use the same exported file across supported runtimes, including web, mobile, game engines, and other platforms.”
   • [claimed-docs] “The Rive runtimes are open-source libraries that allow you to load and control your animations in apps, games, and websites.”
   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”
   • [claimed-docs] “Caching a Rive file: Load the .riv into memory once, use it multiple times.”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”

   proof ↗⚑ flag

Agentic features

1. ai-native userSet up automations that run autonomously in the background

   weight 2 · round drawn
   Claude Design—none0/10

   Claude Design is a conversational/interactive design tool for generating mockups, prototypes, and handoffs; nothing in the evidence describes scheduled tasks, triggers, or autonomous background runs — all workflows are synchronous and user-initiated via chat or explicit commands.

   ⚑ flag

   Rive—none0/10

   Rive's docs describe an AI agent, MCP integration, and CLI that generate animations/code when invoked by a user, but there is no evidence of scheduled, unattended, or continuously running background automations — all AI features described are user-triggered, session-based interactions within the Editor.

   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”

   proof ↗⚑ flag

2. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round drawn
   Claude Design✓fullcommunity8/10

   Claude Design is built around delegating design tasks directly to Claude within the product—describing a visual, refining through conversation/sliders, generating variations, and packaging handoffs are all done by the embedded Claude assistant, and this is corroborated by hands-on community reports of building shippable pages and using the handoff skill successfully. missing for 10: independent quality benchmarking of how much genuine agentic reasoning vs templated generation occurs, and some community reports note underwhelming or 'boring' outputs suggesting delegation quality varies.

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “Refine, share, or hand off to the tools you use. You're the designer, start to finish.”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

   proof ↗⚑ flag

   Rive✓fullclaimed8/10

   Rive documents a built-in AI agent inside the Editor that writes code, generates layouts, data models, view models, state machines, and animation, letting users delegate repetitive/complex tasks to it directly within the product. This is first-party documented with specific task examples, though there's no independent/hands-on corroboration of its real-world effectiveness. Missing for 10: independent verification of the AI agent's actual capability/reliability, more detail on scope/limits of delegation.

   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”

   proof ↗⚑ flag

3. ai-native userOperate the product with natural-language commands

   weight 2 · round to Claude Design
   Claude Design✓fullcommunity8/10

   Claude Design's entire interaction model is natural-language: users 'describe a visual and Claude builds a first version,' refine 'through conversation, inline comments,' and use conversational handoffs like /design and /design-sync — with real-world use (landing pages, PenPot flows) confirming this works in practice, though output quality and robustness vary across users. Missing for 10: consistent quality/benchmarks across users and no independent rigor testing beyond anecdotal HN reports.

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
   • [claimed-docs] “Now you can use Claude Design from inside any conversation with Claude.”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [community] “Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

   proof ↗⚑ flag

   Rive~partialprobed6/10

   Rive documents a built-in AI agent and MCP integration that let users describe tasks in natural language to generate ViewModels, state machines, layouts, and animation code, plus a CLI for agent-driven generation (rive-docs-9,10,18,19,26,27). However, this is entirely first-party documentation with no independent or hands-on confirmation that natural-language commands reliably drive the full editor experience, and community feedback focuses on pricing/licensing rather than the AI agent's real-world behavior. Missing for 10: independent/hands-on verification of the AI agent's natural-language command success, broader coverage beyond docs-based claims, and detail on command scope/limits.

   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”

   proof ↗⚑ flag

Api quality

1. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Claude Design—none0/10

   Claude Design is a design/prototyping product with no evidence of a public API, and the direct probe for OpenAPI/swagger endpoints returned 404 on all candidate paths, with no other documentation mentioning a machine-readable API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Rive—none0/10

   A direct probe for OpenAPI/swagger spec endpoints (openapi.json, swagger.json, etc.) returned 404 for all candidates, and no docs mention a machine-readable API spec being downloadable.

   • [probe] “PROBE openapi: all candidate paths 404 (https://rive.app/openapi.json, https://rive.app/swagger.json, https://rive.app/api/openapi.json, htt…”

   proof ↗⚑ flag

Ai

1. designerBuilt-in AI handles asset chores — image generation, background removal, content-aware fills, copy suggestions — inside the editor

   weight 1 · round to Claude Design
   Claude Design~partialclaimed3/10

   Claude Design can generate full visual designs from a text prompt and offers layout/color adjustment sliders (claude-design-docs-13, claude-design-docs-9), which loosely maps to 'image generation' and some asset tuning, but there is no evidence of dedicated background-removal, content-aware fill, or copy-suggestion tools built into the editor. missing for 10: background removal tool, content-aware fill/inpainting, in-editor copy/headline suggestion feature.

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”

   proof ↗⚑ flag

   Rive—none0/10

   Rive's AI agent/MCP tooling is focused on generating code, view models, state machines, layouts, and animation logic — not on image generation, background removal, content-aware fill, or copy suggestions for asset creation. No evidence names any of these specific asset-chore AI features; missing for 10: image generation, background removal, content-aware fill, copy/text suggestions.

   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”

   proof ↗⚑ flag

2. designerGenerate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually produces

   weight 2 · round drawn
   Claude Design~partialcommunity6/10

   First-party docs and community reports confirm Claude Design generates first drafts, multiple directions, layouts, and mockups from natural-language prompts with editing/refinement controls (docs-13,20,9,21; comm-6,7,16), and users describe shippable landing pages and solid handoff. However hands-on community feedback also reports underwhelming, 'boring', or 'useless' results for some prompts and generic upload errors (comm-3,9,10,8), showing real quality variance rather than a uniformly reliable draft-to-mockup pipeline. Missing for 10: consistent independent benchmarking of output quality across prompt types, and resolution of reported failure cases (large file uploads, simple prompts underwhelming).

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “Designers can quickly create a wide range of directions to explor”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
   • [community] “Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
   • [community] “After having high expectations from watching the intro, the actual result of a simple prompt 'Bear on a bicycle' is very underwhelming.”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”
   • [community] “I've tried it. It's useless.”

   proof ↗⚑ flag

   Rive~partialprobed6/10

   Rive documents an AI agent/MCP integration that generates View Models, State Machines, Layouts, Shapes and animation from prompts or via coding-agent workflows, and even an 'agent generate them with the CLI' claim on the homepage — this matches the story's spirit of prompt-driven first drafts. However, all evidence is first-party docs describing 'the first set of tools' as handling repetitive tasks rather than full end-to-end mockup generation, and there's no independent/hands-on corroboration of output quality. Missing for 10: independent or hands-on validation of AI-generated designs, clearer evidence of full mockup/layout generation (not just repetitive sub-tasks) from a single prompt.

   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Rive
   Claude Design~partialclaimed4/10

   Claude Design supports generating multiple design directions at once (claude-design-docs-2) and applying a design system consistently 'to every project automatically' (claude-design-docs-3), which suggests some batch-like automation, but there's no evidence of true bulk operations across many items (e.g., batch editing dozens of files/assets, bulk export/import at scale, or programmatic multi-item processing). missing for 10: evidence of bulk/batch processing across many discrete items (not just generating variants), bulk edit/export APIs, scale limits, and independent confirmation of multi-item automation workflows.

   • [claimed-docs] “Generate a dozen directions in minutes, then narrow down in your primary tool.”
   • [claimed-docs] “Claude can also apply your team's design system to every project automatically, so the output is consistent with the rest of your company's …”

   proof ↗⚑ flag

   Rive~partialclaimed6/10

   Rive documents an AI agent/MCP integration explicitly designed to let AI 'handle repetitive tasks, like creating complex View Models, State Machines with hundreds of states/layers, Layouts, Shapes, and more,' and RML provides a text-based file format enabling coding agents to script bulk edits outside the Editor. Components/instances also let one source change propagate across many instances. However, there's no independent/hands-on evidence of actual bulk-operation performance at scale, no documented API for batch scripting beyond RML/MCP, and no benchmarks or examples of large-scale bulk edits succeeding. Missing for 10: independent verification of bulk-task performance, concrete examples/benchmarks of large-scale batch operations, and a documented API/CLI for scripted bulk edits beyond the AI agent's stated purpose.

   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”
   • [claimed-docs] “Create a component once, then use customized instances of it throughout your Rive file. Changes made to the source component are reflected a…”
   • [claimed-docs] “Components are reusable artboards. Create a component once, then use customized instances of it throughout your Rive file. Changes made to t…”

   proof ↗⚑ flag

2. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Rive
   Claude Design—none0/10

   The evidence pack describes Claude Design's prototyping, design-system sync, and handoff features, but contains no mention of version history, review workflows, or rollback capability for any automations or design iterations it produces. Community comments even note lock-out of prior work after unsubscribing, with no rollback/versioning remedy mentioned.

   ⚑ flag

   Rive~partialclaimed4/10

   Rive's Revision History provides automatic tracking of changes, previewing of past revisions, and non-destructive rollback to prior versions of a file (rive-docs-12, rive-docs-17, rive-docs-29), which covers version/rollback for the design file itself. However, the story targets 'automations' (AI-agent/MCP-driven workflows), and there is no evidence of versioning, diffing, or review specifically for AI-generated scripts, MCP actions, or automation pipelines — only generic file revision history. Missing for 10: dedicated versioning/review/rollback for AI-agent or MCP-generated automations, audit trail of agent actions, diff/compare tooling, and any independent confirmation of this workflow in practice.

   • [claimed-docs] “Rive saves your files automatically as you work. Even if multiple people are working on the same file at the same time, Rive tracks all chan…”
   • [claimed-docs] “This guarantees that even restoring revisions is non-destructive, and you can always go back to the previous version of the file.”
   • [claimed-docs] “Select a revision to preview it and press the Edit Current Revision button. This copies the selected revision and creates a new entry at the…”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”

   proof ↗⚑ flag

Collaboration

1. product managerComment directly on designs, mention teammates, and resolve threads so review happens in the file, not in email

   weight 2 · round to Claude Design
   Claude Design~partialclaimed3/10

   Evidence shows collaborative editing (grant edit access, group conversation) and 'inline comments' as a refinement mechanism, but there's no documented @mention-teammates feature or thread-resolution workflow that would replace email-based review. Missing for 10: explicit @mention of teammates, comment thread resolution/status tracking, and any hands-on confirmation that commenting works as a review tool rather than just a chat refinement input.

   • [claimed-docs] “grant edit access so colleagues can modify the design and chat with Claude together in a group conversation”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”

   proof ↗⚑ flag

   Rive—none0/10

   Evidence covers animation, data binding, revision history, AI/MCP tooling, and export, but there is no mention of commenting, @mentions, or thread resolution features in Rive's editor. Revision history tracks changes but is not a comment/review workflow.

   • [claimed-docs] “Rive saves your files automatically as you work. Even if multiple people are working on the same file at the same time, Rive tracks all chan…”
   • [claimed-docs] “This guarantees that even restoring revisions is non-destructive, and you can always go back to the previous version of the file.”
   • [claimed-docs] “Select a revision to preview it and press the Edit Current Revision button. This copies the selected revision and creates a new entry at the…”

   proof ↗⚑ flag

2. designerMy whole team can edit the same file simultaneously with live cursors and instant sync

   weight 3 · round drawn
   Claude Design~partialclaimed4/10

   Docs mention granting edit access so colleagues can modify a design and chat with Claude in a group conversation, implying some shared editing, but there is no evidence of live cursors, simultaneous multi-user editing, or instant real-time sync mechanics typical of multiplayer design tools. Missing for 10: explicit live-cursor/presence indicators, real-time simultaneous editing demonstration, and independent confirmation of true multiplayer sync.

   • [claimed-docs] “grant edit access so colleagues can modify the design and chat with Claude together in a group conversation”

   proof ↗⚑ flag

   Rive~partialclaimed4/10

   Docs confirm multiple people can work on the same file simultaneously with all changes tracked in Revision History, implying some multiplayer support, but there is no mention of live cursors, presence indicators, or real-time instant sync mechanics that the story specifically asks for. Missing for 10: explicit live cursor/presence UI, real-time sync latency claims, independent hands-on confirmation of simultaneous editing experience.

   • [claimed-docs] “Rive saves your files automatically as you work. Even if multiple people are working on the same file at the same time, Rive tracks all chan…”
   • [claimed-docs] “This guarantees that even restoring revisions is non-destructive, and you can always go back to the previous version of the file.”
   • [claimed-docs] “Select a revision to preview it and press the Edit Current Revision button. This copies the selected revision and creates a new entry at the…”

   proof ↗⚑ flag

Design systems

1. designerManage design tokens or variables — colors, spacing, typography — with modes or themes applied across designs

   weight 2 · round to Claude Design
   Claude Design~partialcommunity3/10

   Claude Design can 'apply your team's design system to every project automatically' and offers sliders to tune spacing/color, and one community report describes it building 'reusable PenPot components and design system tokens' via an MCP export flow — but there's no first-party evidence of native token/variable definitions with mode/theme switching (light/dark, brand variants) inside Claude Design itself. missing for 10: explicit token/variable editor, multi-mode/theme support, first-party documentation of applying themes across multiple designs.

   • [claimed-docs] “Claude can also apply your team's design system to every project automatically, so the output is consistent with the rest of your company's …”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

   Rive—none0/10

   Rive is an animation/interactive-graphics tool with components, data binding, and view models, but there is no evidence of a design-tokens/variables system (colors, spacing, typography) with modes/themes applied across designs — the closest concepts (components, data binding) address reusability and runtime data, not token/theme management. Missing for 10: token or variable definitions, theme/mode switching, cross-design application of shared style values.

   • [claimed-docs] “Create a component once, then use customized instances of it throughout your Rive file. Changes made to the source component are reflected a…”
   • [claimed-docs] “Data binding — autoBind, view models, bindViewModelInstance”
   • [claimed-docs] “When data changes, your scene updates automatically. Likewise, changes made in your scene can be written back to your data.”
   • [claimed-docs] “Components are reusable artboards. Create a component once, then use customized instances of it throughout your Rive file. Changes made to t…”

   proof ↗⚑ flag

2. designerBuild reusable components with variants and per-instance overrides that stay linked to their source

   weight 3 · round to Rive
   Claude Design—none0/10

   Claude Design is described as a prompt-driven design/prototyping tool that can 'apply your team's design system' and import components, but there is no evidence of a structured component system with defined variants and per-instance overrides that stay linked to a master source, as in tools like Figma. The one related community mention (comm-7) is about exporting to PenPot's component system, not a native capability of Claude Design itself.

   • [claimed-docs] “Claude can also apply your team's design system to every project automatically, so the output is consistent with the rest of your company's …”
   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

   Rive✓fullclaimed8/10

   Rive's docs directly describe Components as reusable artboards where instances can be customized while changes to the source component propagate to all instances, matching the story's core requirement of variants/overrides linked to source. Missing for 10: no independent/hands-on corroboration of override behavior at scale, and no detail on variant-specific overrides beyond basic customization examples.

   • [claimed-docs] “Create a component once, then use customized instances of it throughout your Rive file. Changes made to the source component are reflected a…”
   • [claimed-docs] “Components are reusable artboards. Create a component once, then use customized instances of it throughout your Rive file. Changes made to t…”

   proof ↗⚑ flag

3. designerShared libraries publish components and styles across files and projects, with controlled updates when the source changes

   weight 2 · round to Claude Design
   Claude Design~partialclaimed3/10

   Claude Design can apply a team's design system automatically across projects and sync design-system context via '/design-sync' from Claude Code, suggesting some cross-project consistency, but there is no evidence of a true shared-library mechanism (publishing reusable components/styles with versioned, controlled updates propagating when a source library changes) as in dedicated design tools. Missing for 10: library publishing workflow, update/versioning notifications when source components change, and independent confirmation of cross-project sync behavior.

   • [claimed-docs] “Claude can also apply your team's design system to every project automatically, so the output is consistent with the rest of your company's …”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”

   proof ↗⚑ flag

   Rive—none0/10

   Rive's docs describe components/instances reused within a single Rive file where changes to a source component propagate to instances (rive-docs-11, rive-docs-28), but there is no evidence of a shared-library system that publishes components/styles across separate files or projects with controlled update propagation, which is the core of this story. Missing for 10: cross-file/cross-project library publishing, subscribing to a library, and controlled update notifications when a source library changes.

   • [claimed-docs] “Create a component once, then use customized instances of it throughout your Rive file. Changes made to the source component are reflected a…”
   • [claimed-docs] “Components are reusable artboards. Create a component once, then use customized instances of it throughout your Rive file. Changes made to t…”

   proof ↗⚑ flag

Handoff

1. developerDesigns map to production code — component-to-code mappings or direct design-to-code output I can actually ship

   weight 2 · round to Rive
   Claude Design~partialcommunity7/10

   Docs describe concrete design-to-code handoff: importing real components from GitHub/codebase, syncing design systems via /design-sync, and packaging a 'handoff bundle' passed to Claude Code with one instruction (claude-design-docs-5,6,7,8). Community corroborates this works well ('handoff skill in Claude Design is pretty solid', 'Got something shippable in a few hours') but also flags that the generated code is often unmaintainable ('write-once, read-never' code) and animation/export sanitization bugs, showing real shippability caveats. Missing for 10: independent verification of true component-to-code mapping fidelity (not just handoff bundling) and resolution of maintainability/code-quality concerns raised by users.

   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”
   • [community] “Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80…”

   proof ↗⚑ flag

   Rive✓fullclaimed8/10

   Rive's core value prop is explicitly design-to-shippable-runtime: 'No mockups, no prototypes, no handoff... What you build in the editor is what ships in your app, game, or website' (rive-docs-23), backed by real runtime libraries that load .riv files directly into apps/games/web (rive-gh-1, rive-docs-21), reusable components/instances (rive-docs-11, rive-docs-28), and RML text representation enabling coding-agent-driven file construction (rive-docs-13, rive-docs-25, rive-docs-30). This is a genuine direct design-to-production path rather than a code-generation handoff, and MCP/AI agent tooling further bridges design and code workflows (rive-docs-9, rive-docs-19, rive-docs-27). Missing for 10: independent developer case studies confirming the 'no handoff' claim holds up in large production codebases, and clearer detail on how designers' Rive files integrate with existing component libraries/design systems in code.

   • [claimed-docs] “Design, animate, and code in one place. What you build in the editor is what ships in your app, game, or website. No mockups, no prototypes,…”
   • [claimed-docs] “Create a component once, then use customized instances of it throughout your Rive file. Changes made to the source component are reflected a…”
   • [claimed-docs] “Components are reusable artboards. Create a component once, then use customized instances of it throughout your Rive file. Changes made to t…”
   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “RML uses XML to describe the objects and relationships in a Rive file... build Rive files with coding agents and other text-based workflows …”
   • [claimed-docs] “It lets you create and modify Rive content as code, making it possible to build Rive files with coding agents and other text-based workflows…”
   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”
   • [claimed-docs] “The Rive runtimes are open-source libraries that allow you to load and control your animations in apps, games, and websites.”
   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Rive
   Claude Design—none0/10

   No evidence of a Claude Design API; the only API-related probe found openapi.json/swagger.json endpoints all returning 404, and no docs mention programmatic access to Design's prototyping, handoff, or editing features. All capabilities (prototyping, handoff, design-system sync) are described only as UI/Claude Code slash-command workflows.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “Now you can use Claude Design from inside any conversation with Claude.”

   proof ↗⚑ flag

   Rive~partialprobed5/10

   Rive offers RML (text-based file format) and an MCP server that let AI/coding agents create View Models, State Machines, Layouts, and Shapes programmatically, plus open-source runtimes for playback/control — but the evidence pack does not confirm full parity with the Editor UI (e.g., no OpenAPI/REST API, no confirmation that timeline keyframing, revision history management, or component/instance authoring can be done entirely via API/CLI). missing for 10: a documented public REST/OpenAPI API surface, confirmation that all editor features (keyframe timelines, revision history, component instancing) are scriptable/API-accessible, and independent hands-on verification that AI/API workflows match UI capability.

   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol).”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”
   • [claimed-docs] “RML uses XML to describe the objects and relationships in a Rive file... build Rive files with coding agents and other text-based workflows …”
   • [claimed-docs] “You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repet…”
   • [claimed-docs] “It lets you create and modify Rive content as code, making it possible to build Rive files with coding agents and other text-based workflows…”
   • [probe] “official MCP server documented at https://rive.app/docs/editor/ai/mcp”
   • [probe] “PROBE openapi: all candidate paths 404 (https://rive.app/openapi.json, https://rive.app/swagger.json, https://rive.app/api/openapi.json, htt…”
   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   Claude Design!disputedcontradicted4/10

   Docs confirm export to open-ish formats (PPTX, PDF, HTML) and that designs are HTML/CSS/JS editable by any tool, suggesting an open-format export path. However, community reports document a concrete failure: users lost access to their entire design history/projects after unsubscribing, effectively blocking 'leaving' with their data, which Anthropic staff acknowledged as a bug needing a fix rather than confirming it works as intended. Missing for 10: a documented, reliable full-data export mechanism (all chats, assets, code) confirmed to work post-cancellation, and independent verification that the promised fix was shipped.

   • [claimed-docs] “Export to PPTX, PDF, or HTML, share an org-scoped link, hand off to Claude Code, or send to the apps you already use daily.”
   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “If you export your data, all your Claude Design chats are in a design_chats directory along with the code, even if your account currently ha…”
   • [community] “Hi there, Thariq from the Claude team here. Sorry this is happening, we'll fix it ASAP. Claude's designs are HTML/CSS/JS that any editor can…”

   proof ↗⚑ flag

   Rive!disputedcontradicted4/10

   Rive documents an open, text-based file representation (RML/XML) and open-source runtimes, suggesting some data portability (rive-docs-13, rive-docs-20, rive-docs-25, rive-docs-21, rive-gh-1). However, community feedback directly contradicts a full 'export and leave' story: users report no way to export movie/video assets (rive-comm-3, rive-comm-10) and note the open-source license only covers a narrow rendering subset while the actual content-creation editor remains proprietary and subscription-locked (rive-comm-5, rive-comm-1, rive-comm-2), undermining claims of full open-format data portability. missing for 10: documented full-fidelity export to universal open formats (e.g. video/SVG/JSON), open-source editor or file-format spec, and independent confirmation that RML round-trips 100% of file data without proprietary lock-in.

   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”
   • [claimed-docs] “The Rive runtimes are open-source libraries that allow you to load and control your animations in apps, games, and websites.”
   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”
   • [community] “It's so insane they don't offer any way to export movie files. The animation IDE is decent. Nowhere near as good as Flash was. But at least …”
   • [community] “So I love Rive—the product and the company. And I love open source. But this is an MIT license for Rive's rendering abstraction layer, a sub…”
   • [community] “But can I export video assets with this!? That's my question - I've had to resort to WebGL for a lot of this so far.”
   • [community] “Didn't we already do this experiment with Flash? ... it seems that Rive wants to open source the player and then charge for the editor... He…”

   proof ↗⚑ flag

Plugins

1. designerExtend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and more

   weight 2 · round drawn
   Claude Design—none0/10

   No evidence of a plugin marketplace or extensibility ecosystem for Claude Design (icons, data fillers, accessibility checkers, etc.); the only related mention is a single user connecting Claude Design to PenPot via MCP, which is a one-off integration, not a documented plugin/marketplace system.

   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

   Rive—none0/10

   No evidence of a plugin marketplace, third-party extension ecosystem, or add-ons like icon packs, data fillers, or accessibility checkers. The evidence only covers Rive's own built-in features (components, data binding, MCP/AI agent, RML) — none of which describe an external plugin/marketplace ecosystem. Missing for 10: any mention of a plugin API, extension marketplace, or third-party-built add-ons.

   ⚑ flag

Pricing

1. product managerPublished plan pricing makes seat types, tiers, and AI-feature gating clear before procurement

   weight 1 · round drawn
   Claude Design—none0/10

   The evidence pack shows product features, an enterprise admin toggle, and usage-bar mentions, but contains no documentation of seat types, pricing tiers, or explicit AI-feature gating tables for procurement decisions.

   ⚑ flag

   Rive—none0/10

   The evidence pack contains only product/docs content about Rive's features (animation, data binding, AI agent, MCP) and community discussion referencing informal price points ($25-$39/month) but no published pricing page, seat-type breakdown, tier comparison, or explicit AI-feature gating documentation.

   • [community] “So does this mean someone can create a free editor I can use for basic animation that I don't have to pay $25 for the rest of my life to use…”

   proof ↗⚑ flag

2. designerThe free tier supports real design work — usable editor and collaboration without a paid seat

   weight 2 · round drawn
   Claude Design—none0/10

   The evidence pack contains no information about a free tier for Claude Design, its editor capabilities without payment, or collaboration limits for non-paying users. In fact, community reports indicate access is tied to an active subscription and is revoked upon cancellation (comm-11, comm-12, comm-13), which cuts against the idea of a functional free tier, but there's no direct claim or denial of a free tier's design capabilities to judge against.

   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “If you export your data, all your Claude Design chats are in a design_chats directory along with the code, even if your account currently ha…”

   proof ↗⚑ flag

   Rive—none0/10

   No evidence describes what the free tier includes for editor/collaboration access; the only relevant community signal explicitly states that basic solo-dev animation work requires a paid subscription ($25-39/month), suggesting the free tier is not sufficient for real design work.

   • [community] “Didn't we already do this experiment with Flash? ... it seems that Rive wants to open source the player and then charge for the editor... He…”
   • [community] “So does this mean someone can create a free editor I can use for basic animation that I don't have to pay $25 for the rest of my life to use…”

   proof ↗⚑ flag

1. designerPrototypes can carry advanced behavior — animation between states, conditions or variables, scroll effects — to feel like the real product

   weight 1 · round to Rive
   Claude Design~partialcommunity4/10

   Docs claim Claude Design produces 'interactive prototypes' that can be user-tested and 'look like the real product' via web capture, and community evidence confirms animated SVGs can be built, but with real friction (animations stripped by default sanitization, requiring workarounds). There is no evidence addressing prototype conditions/variables or scroll-based effects specifically. missing for 10: explicit support for state-based/conditional logic in prototypes, scroll-triggered effects, and clean first-party documentation of animation between screens/states without the SVG export bug.

   • [claimed-docs] “Turn a static mockup into a shareable, interactive prototype you can test with real people. No PRs, no code review.”
   • [claimed-docs] “Designers can turn static mockups into easily-shareable interactive prototypes to gather feedback and user-test, without code review or PRs.”
   • [claimed-docs] “You can also use the web capture tool to grab elements directly from your website so prototypes look like the real product.”
   • [community] “I've been using Claude Design to make animated SVGs. You have to ask it to first come up with a robust way to define the geometry and then a…”
   • [community] “Whatever tool prepares the SVG for export in Claude Design will strip animations as part of a sanitizing process; you have to export as a di…”

   proof ↗⚑ flag

   Rive✓fullcommunity8/10

   Rive's docs explicitly describe building interactive experiences responding to user input, screen size, scrolling, and application state (rive-docs-4), state machines/timelines/keyframes (rive-docs-3), and real-time data binding so animations update live (rive-docs-5, rive-docs-15, rive-docs-22, rive-docs-24) — directly matching the story's states/conditions/variables/scroll-effect prototyping needs. Community evidence corroborates real-world adoption for production-grade interactive UI/UX work (rive-comm-4, rive-comm-7), and Rive's own positioning ('no mockups, no prototypes... the real thing', rive-docs-16/23) reflects this design intent. Missing for 10: independent hands-on verification specifically of scroll-triggered effects and variable/condition-driven prototypes beyond vendor docs.

   • [claimed-docs] “Bring your designs to life with timelines, keyframes, and smooth interpolation.”
   • [claimed-docs] “Build interactive experiences that respond to user input, screen size, scrolling, and application state.”
   • [claimed-docs] “Connect animations, text, colors, layouts, and other properties to real-time data.”
   • [claimed-docs] “Data binding — autoBind, view models, bindViewModelInstance”
   • [claimed-docs] “Bind an enemy's X and Y position so it can be controlled at runtime.”
   • [claimed-docs] “When data changes, your scene updates automatically. Likewise, changes made in your scene can be written back to your data.”
   • [claimed-docs] “No mockups, no prototypes, no handoff. The real thing.”
   • [claimed-docs] “Design, animate, and code in one place. What you build in the editor is what ships in your app, game, or website. No mockups, no prototypes,…”
   • [community] “I've been pushing over the past six months or so for multiple clients... to adopt Rive over Lottie and other past solutions, as I think it's…”
   • [community] “Truthfully the program they have looks fantastic at empowering UI/UX designers to do more with games... the workflow of this tool is definit…”

   proof ↗⚑ flag

2. designerWire screens into clickable prototypes with triggers, transitions, and overlays — no code required

   weight 2 · round to Rive
   Claude Design~partialcommunity4/10

   Docs confirm Claude Design turns static mockups into shareable, testable interactive prototypes without code (claude-design-docs-1, claude-design-docs-18), which covers the no-code prototyping goal, but there is no evidence of specific multi-screen wiring primitives like triggers, transitions, or overlays that a designer would use in traditional prototyping tools. Community feedback (claude-design-comm-6, claude-design-comm-9) discusses general design output quality but not this specific screen-linking mechanic. Missing for 10: explicit support for defining triggers/transitions/overlays between distinct screens, and any hands-on confirmation that multi-screen flows can be wired together.

   • [claimed-docs] “Turn a static mockup into a shareable, interactive prototype you can test with real people. No PRs, no code review.”
   • [claimed-docs] “Designers can turn static mockups into easily-shareable interactive prototypes to gather feedback and user-test, without code review or PRs.”
   • [community] “Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80…”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

   proof ↗⚑ flag

   Rive~partialclaimed5/10

   Rive's State Machines and interaction docs (rive-docs-4, rive-docs-22, rive-docs-24) support building input-driven, trigger/transition-based interactivity without code, and rive-docs-16/23 frame the tool as skipping separate 'prototype' handoff entirely. However there is no evidence of a Figma-style multi-screen/overlay prototyping paradigm (linking distinct screens, overlay layers, click-through flows across artboards) — Rive's interactivity is scoped to state machines within/across components rather than an explicit screen-flow prototyping mode. Missing for 10: evidence of multi-screen linking, overlay/modal wiring, and click-through flow prototyping across separate artboards/screens.

   • [claimed-docs] “Build interactive experiences that respond to user input, screen size, scrolling, and application state.”
   • [claimed-docs] “No mockups, no prototypes, no handoff. The real thing.”
   • [claimed-docs] “Bind an enemy's X and Y position so it can be controlled at runtime.”
   • [claimed-docs] “Design, animate, and code in one place. What you build in the editor is what ships in your app, game, or website. No mockups, no prototypes,…”
   • [claimed-docs] “When data changes, your scene updates automatically. Likewise, changes made in your scene can be written back to your data.”

   proof ↗⚑ flag

Canvas

1. designerFrames can behave responsively — auto layout, constraints, and grids resize designs the way real UIs flex

   weight 2 · round to Rive
   Claude Design—none0/10

   The evidence pack describes Claude Design as a prompt-driven generator that outputs HTML/CSS/JS mockups and prototypes, with only generic 'rich layout controls' to drag/resize/align elements (claude-design-docs-9) — there is no mention of Figma-style frames, auto layout, constraints, or grid systems that adapt responsively. Community feedback even notes the generated code is not maintainable/structured (claude-design-comm-15), suggesting it isn't built on a constraint-based vector layout engine. Missing for 10: any documentation of frames, auto-layout, constraint-based resizing, or grid systems enabling responsive behavior.

   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”

   proof ↗⚑ flag

   Rive~partialclaimed5/10

   Rive's docs repeatedly reference "responsive layouts" and building interfaces that respond to screen size (rive-docs-1, rive-docs-4, rive-docs-9, rive-docs-18, rive-docs-26), and the AI tooling explicitly generates "Layouts" as an artboard-level construct (rive-docs-10). However, no evidence details the specific mechanics of auto layout, constraints, or grid systems the way Figma-style tools describe them. Missing for 10: explicit documentation of constraint-based resizing rules, grid systems, or auto-layout algorithms, and independent/hands-on confirmation that layouts flex like real UI frameworks.

   • [claimed-docs] “Create vector graphics, responsive layouts, and reusable components, or import images, audio, fonts, and other assets from your favorite des…”
   • [claimed-docs] “Build interactive experiences that respond to user input, screen size, scrolling, and application state.”
   • [claimed-docs] “Rive's AI agent helps you write code, design, and animate. Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of st…”
   • [claimed-docs] “Generate scripts, responsive layouts, data models, and even animation.”
   • [claimed-docs] “Build interactive UI, motion, and game experiences in the Editor, or let an agent generate them with the CLI.”

   proof ↗⚑ flag

2. designerI get professional vector tools — pen and path editing, boolean operations, precise alignment — for real interface design work

   weight 3 · round to Rive
   Claude Design—none0/10

   Claude Design is a prompt-driven design/prototyping generator with only basic layout controls (drag, resize, align, sliders for spacing/color) — there is no evidence of pen/path vector editing, boolean path operations, or precision alignment tooling akin to professional vector editors. Community feedback even notes the underlying output is HTML/CSS/JS, not vector paths, and code is not maintainable, reinforcing it's not a vector design tool.

   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”
   • [community] “I've been using Claude Design to make animated SVGs. You have to ask it to first come up with a robust way to define the geometry and then a…”
   • [community] “Whatever tool prepares the SVG for export in Claude Design will strip animations as part of a sanitizing process; you have to export as a di…”

   proof ↗⚑ flag

   Rive!disputedcontradicted3/10

   Rive's docs market it as a full design-to-ship tool ('design, animate, and code in one place... no mockups, no prototypes, no handoff') and mention vector graphics and components, but there is no documentation of boolean operations, precise alignment/snapping tools, or advanced path editing. A hands-on community comment directly contradicts the 'professional vector tools' claim, calling the drawing toolset just 'a pen and a couple of basic shapes' and comparing inefficient pen-only workflows unfavorably to real illustration tools. missing for 10: boolean operations, alignment/snap tooling, path-editing depth, and any rebuttal to the community criticism of basic drawing tools.

   • [claimed-docs] “Create vector graphics, responsive layouts, and reusable components, or import images, audio, fonts, and other assets from your favorite des…”
   • [claimed-docs] “No mockups, no prototypes, no handoff. The real thing.”
   • [claimed-docs] “Design, animate, and code in one place. What you build in the editor is what ships in your app, game, or website. No mockups, no prototypes,…”
   • [community] “Looks kinda interesting but I am not gonna touch anything that thinks an acceptable set of drawing tools is 'pen and a couple of basic shape…”

   proof ↗⚑ flag

Files

1. designerExport production assets — PNG, SVG, PDF, and more — with per-layer presets, scales, and slices

   weight 2 · round to Claude Design
   Claude Design~partialcommunity3/10

   Claude Design documents export to PPTX, PDF, and HTML, and community evidence confirms SVG export is possible (though it strips animations unless renamed), showing some baseline export capability exists. However, there is no evidence anywhere in the pack of PNG export, per-layer export presets, scale multipliers, or slice/asset regions — the core professional export controls the story asks about are entirely unevidenced. missing for 10: PNG export, per-layer export presets, scale export options, slice/asset export regions, any evidence of production-asset export workflows beyond whole-document PDF/PPTX/HTML.

   • [claimed-docs] “Export to PPTX, PDF, or HTML, share an org-scoped link, hand off to Claude Code, or send to the apps you already use daily.”
   • [community] “I've been using Claude Design to make animated SVGs. You have to ask it to first come up with a robust way to define the geometry and then a…”
   • [community] “Whatever tool prepares the SVG for export in Claude Design will strip animations as part of a sanitizing process; you have to export as a di…”

   proof ↗⚑ flag

   Rive—none0/10

   Rive's documentation focuses on exporting .riv files for runtime playback across platforms (web, mobile, games) rather than static production assets like PNG/SVG/PDF with per-layer presets, scales, or slices; no such export presets are described anywhere in the evidence. Community feedback explicitly confirms this gap — one user complains 'it's so insane they don't offer any way to export movie files' and another asks 'can I export video assets with this!?' — indicating the tool lacks traditional multi-format asset export entirely.

   • [claimed-docs] “Export once and use your interactive graphics across websites, mobile apps, games, videos, and more.”
   • [claimed-docs] “You can use the same exported file across supported runtimes, including web, mobile, game engines, and other platforms.”
   • [community] “It's so insane they don't offer any way to export movie files. The animation IDE is decent. Nowhere near as good as Flash was. But at least …”
   • [community] “But can I export video assets with this!? That's my question - I've had to resort to WebGL for a lot of this so far.”

   proof ↗⚑ flag

2. developerThe file format is open or documented, so my designs stay portable and toolable outside the vendor's editor

   weight 1 · round to Claude Design
   Claude Design~partialcommunity6/10

   Claude Design outputs are HTML/CSS/JS and can be exported to PPTX, PDF, or HTML (claude-design-docs-8), and an Anthropic team member explicitly confirmed 'Claude's designs are HTML/CSS/JS that any editor can handle' (claude-design-comm-14), supporting portability outside the vendor's editor. However, there was a real-world incident where users temporarily lost access to their design history/code after unsubscribing (claude-design-comm-11, claude-design-comm-12) before the fix, and community members note the generated code is hard for humans to maintain (claude-design-comm-15), undercutting practical toolability. missing for 10: a stable, always-available raw export/download path independent of subscription status, and clearer documentation of the underlying file format/spec beyond ad-hoc HTML/CSS/JS.

   • [claimed-docs] “Export to PPTX, PDF, or HTML, share an org-scoped link, hand off to Claude Code, or send to the apps you already use daily.”
   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “If you export your data, all your Claude Design chats are in a design_chats directory along with the code, even if your account currently ha…”
   • [community] “Hi there, Thariq from the Claude team here. Sorry this is happening, we'll fix it ASAP. Claude's designs are HTML/CSS/JS that any editor can…”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”

   proof ↗⚑ flag

   Rive!disputedcontradicted4/10

   Rive documents RML (a text-based/XML representation of Rive files) and open-source runtimes that can load/parse .riv files (rive-docs-13/20/25/30, rive-gh-1/3), suggesting some portability outside the editor. However, community evidence directly disputes this: the open-source runtime is described as only a rendering/playback layer, and actually authoring or building Rive content still requires the proprietary, paid Rive Editor (rive-comm-5), undercutting claims of full format openness/portability. Missing for 10: a public, versioned .riv binary spec independent of RML, third-party tools that can author/edit .riv files without the vendor's editor, and confirmation that RML round-trips losslessly with the binary format.

   • [claimed-docs] “Rive Markup Language (RML) is a text-based representation of a Rive file. It lets you create and modify Rive content as code”
   • [claimed-docs] “making it possible to build Rive files with coding agents and other text-based workflows instead of working exclusively in the Editor”
   • [claimed-docs] “RML uses XML to describe the objects and relationships in a Rive file... build Rive files with coding agents and other text-based workflows …”
   • [claimed-docs] “It lets you create and modify Rive content as code, making it possible to build Rive files with coding agents and other text-based workflows…”
   • [github] “Loads .riv files, advances state machines and animations, and draws via the abstract Renderer interface.”
   • [community] “So I love Rive—the product and the company. And I love open source. But this is an MIT license for Rive's rendering abstraction layer, a sub…”

   proof ↗⚑ flag

3. designerFull version history lets me name milestones, compare, and restore any earlier state of a file

   weight 2 · round to Rive
   Claude Design—none0/10

   No evidence describes named milestones, version comparison, or restore-to-earlier-state functionality in Claude Design; community discussion only mentions losing access to 'history' after unsubscribing, not a versioning/milestone/compare/restore feature.

   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “If you export your data, all your Claude Design chats are in a design_chats directory along with the code, even if your account currently ha…”

   proof ↗⚑ flag

   Rive~partialclaimed6/10

   Rive's docs confirm automatic revision tracking, non-destructive restore, and the ability to select and edit a prior revision (rive-docs-12, rive-docs-17, rive-docs-29), which covers 'restore any earlier state.' However there is no evidence of naming/labeling milestones or a compare/diff view between versions. Missing for 10: named milestone/labeling capability, side-by-side or diff comparison between revisions, independent corroboration of the restore workflow.

   • [claimed-docs] “Rive saves your files automatically as you work. Even if multiple people are working on the same file at the same time, Rive tracks all chan…”
   • [claimed-docs] “This guarantees that even restoring revisions is non-destructive, and you can always go back to the previous version of the file.”
   • [claimed-docs] “Select a revision to preview it and press the Edit Current Revision button. This copies the selected revision and creates a new entry at the…”

   proof ↗⚑ flag