Rank #2 of 5 in Agent Skills & Extensions
Access
vs Anthropic Skills
vs Skills for Real Engineers
vs skills.sh
vs Codex PluginsShowcase
Try itExperimental
See what an agent can do with Superpowers before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$npx -y skills add obra/superpowers --skill test-driven-development -a claude-code -y --copy # in a scratch dir, then print installed SKILL.md frontmatterrecorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agent workflows — stories about agent workflows in this arenaAgent workflowsevidence →
Stories about agent workflows in this arena
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Cross agent portability — stories about cross agent portability in this arenaCross agent portabilityevidence →
Stories about cross agent portability in this arena
Discovery distribution — stories about discovery distribution in this arenaDiscovery distributionevidence →
Stories about discovery distribution in this arena
Docs onboarding — stories about docs onboarding in this arenaDocs onboardingevidence →
Stories about docs onboarding in this arena
Install experience — stories about install experience in this arenaInstall experienceevidence →
Stories about install experience in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Safety review — stories about safety review in this arenaSafety reviewevidence →
Stories about safety review in this arena
Skill authoring — stories about skill authoring in this arenaSkill authoringevidence →
Stories about skill authoring in this arena
Testing quality — stories about testing quality in this arenaTesting qualityevidence →
Stories about testing quality in this arena
Versioning updates — stories about versioning updates in this arenaVersioning updatesevidence →
Stories about versioning updates in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Superpowers stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agent workflows — stories about agent workflows in this arenaAgent workflows
Stories about agent workflows in this arena
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
—–
Subscribe to events via webhooks
n/an/a
Build against official SDKs
~3/10
Issue scoped/least-privilege API credentials for an agent
n/an/a
Connect an agent via an official MCP server
—–
Download a machine-readable API spec (OpenAPI or equivalent)
n/an/a
Rely on versioned APIs with a documented deprecation policy
n/an/a
Test against a sandbox environment without touching production data
~4/10
unlocks → Headless / CI
Explore an interactive API reference with runnable examples
n/an/a
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~6/10
unlocks → AI insights
Operate the product with natural-language commands
✓8/10
Plug MCP servers into this product so it can use their tools
n/an/a
Get AI-generated insights and suggestions from my data inside the product
—–
Set up automations that run autonomously in the background
~5/10
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Cross agent portability — stories about cross agent portability in this arenaCross agent portability
Stories about cross agent portability in this arena
Discovery distribution — stories about discovery distribution in this arenaDiscovery distribution
Stories about discovery distribution in this arena
Browse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anything
~6/10
Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project
✓8/10
Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment
✓7/10
Docs onboarding — stories about docs onboarding in this arenaDocs onboarding
Stories about docs onboarding in this arena
Install experience — stories about install experience in this arenaInstall experience
Stories about install experience in this arena
Install
List what is installed and remove skills cleanly, without orphaned files or lingering instructions
—0/10
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Safety review — stories about safety review in this arenaSafety review
Stories about safety review in this arena
Skill authoring — stories about skill authoring in this arenaSkill authoring
Stories about skill authoring in this arena
Testing quality — stories about testing quality in this arenaTesting quality
Stories about testing quality in this arena
Versioning updates — stories about versioning updates in this arenaVersioning updates
Stories about versioning updates in this arena
Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 6/10 | Xcommunity | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | 0/10 | ||
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Xcommunity | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 3/10 | Cclaimed | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | partial | 4/10 | Cclaimed | |
Install a skill collection with one documented command — a package-manager one-liner, CLI, or in-agent marketplace command — and it is active in my next session C Install | developer | Install experience — stories about install experience in this arenaInstall experience | 3 | full | 8/10 | Xcommunity | |
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructions C Portability | developer | Cross agent portability — stories about cross agent portability in this arenaCross agent portability | 3 | full | 8/10 | Xcommunity | |
Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment C Triggering | developer | Discovery distribution — stories about discovery distribution in this arenaDiscovery distribution | 3 | full | 7/10 | Xcommunity | |
A quickstart takes me from nothing to a working installed skill in under five minutes C Onboarding | developer | Docs onboarding — stories about docs onboarding in this arenaDocs onboarding | 3 | partial | 6/10 | Xcommunity | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partial | 6/10 | Cclaimed | |
There is a documented update path — marketplace auto-updates or an explicit update command — so I get fixes without reinstalling from scratch C Updates | developer | Versioning updates — stories about versioning updates in this arenaVersioning updates | 3 | partial | 6/10 | Cclaimed | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | partial | 5/10 | Cclaimed | |
Review exactly what instructions and scripts a skill will add — list contents before installing and read every file afterward C Review | engineering-lead | Safety review — stories about safety review in this arenaSafety review | 3 | partial | 5/10 | Xcommunity | |
Author a new skill from a documented template — a SKILL.md with name and description frontmatter — without reverse-engineering existing skills C Authoring | developer | Skill authoring — stories about skill authoring in this arenaSkill authoring | 3 | partial | 4/10 | Cclaimed | |
My coding agent can install a skill by itself — a non-interactive, promptless install path an agent can run headlessly end to end C Agent ops | ai-native user | Agent workflows — stories about agent workflows in this arenaAgent workflows | 3 | none | 0/10 | ||
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | n/a | untested | none yet | |
Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project C Distribution | engineering-lead | Discovery distribution — stories about discovery distribution in this arenaDiscovery distribution | 2 | full | 8/10 | Xcommunity | |
My agent can author and package a new skill end to end by following the project's own spec, template, or meta-skill C Agent ops | ai-native user | Agent workflows — stories about agent workflows in this arenaAgent workflows | 2 | full | 8/10 | Xcommunity | |
Skills are plain markdown files and folders I can read, copy, and carry to another harness — not a proprietary binary format C Portability | developer | Cross agent portability — stories about cross agent portability in this arenaCross agent portability | 2 | full | 8/10 | Cclaimed | |
Skills follow the open Agent Skills specification so the same skill folder is valid beyond this one vendor's tooling C Spec | developer | Skill authoring — stories about skill authoring in this arenaSkill authoring | 2 | full | 8/10 | Cclaimed | |
The collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibes C Testing | developer | Testing quality — stories about testing quality in this arenaTesting quality | 2 | full | 8/10 | Cclaimed | |
Every skill documents what it does and when it activates, so I can predict my agent's new behavior before it surprises me C Onboarding | developer | Docs onboarding — stories about docs onboarding in this arenaDocs onboarding | 2 | partial | 7/10 | Xcommunity | |
The collection ships a meta-skill or tool that guides my agent through writing, improving, and packaging new skills C Authoring | developer | Skill authoring — stories about skill authoring in this arenaSkill authoring | 2 | full | 7/10 | Cclaimed | |
Browse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anything C Discovery | developer | Discovery distribution — stories about discovery distribution in this arenaDiscovery distribution | 2 | partial | 6/10 | Cclaimed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 5/10 | Cclaimed | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed | |
The collection is actively maintained — recent releases, triaged issues, and accepted community contributions C Maintenance | developer | Testing quality — stories about testing quality in this arenaTesting quality | 2 | partial | 5/10 | Xcommunity | |
Choose install scope — project-local files committed with my repo, or user-global across all projects C Install | developer | Install experience — stories about install experience in this arenaInstall experience | 2 | none | 0/10 | ||
Install only the specific skills I want from a collection instead of taking the whole bundle C Install | developer | Install experience — stories about install experience in this arenaInstall experience | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | n/a | untested | none yet | |
The project documents its security posture — what skills can execute, the trust model for third-party skills, and any telemetry or data collection C Trust | engineering-lead | Safety review — stories about safety review in this arenaSafety review | 2 | none | untested | none yet | |
Releases ship with notes or a changelog so I can see what changed in the skills before I take an update C Updates | developer | Versioning updates — stories about versioning updates in this arenaVersioning updates | 1 | full | 7/10 | Cclaimed | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 5/10 | Cclaimed | |
List what is installed and remove skills cleanly, without orphaned files or lingering instructions C Lifecycle | developer | Install experience — stories about install experience in this arenaInstall experience | 1 | none | 0/10 | ||
Control when skill changes reach my team — pinned versions or a lockfile rather than silent behind-the-back updates C Pinning | engineering-lead | Versioning updates — stories about versioning updates in this arenaVersioning updates | 1 | none | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 29 stories with headroom
What would move Superpowers’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server
nonemoves agent-readyimpact 45
Superpowers is a skills/plugin framework installed into various agent harnesses (Claude Code, Devin, Codex, Gemini CLI, etc.), not an agent itself, so an official MCP server is a plausible axis for this kind of product—but no evidence anywhere in the pack mentions Superpowers exposing an MCP server for agents to connect to; installation is via harness-specific plugin mechanisms, not MCP.
Agenticness — how well agents can access and operate the productDrive the product through a documented public API
nonemoves agent-readyimpact 45
Superpowers ships as skills/plugins consumed via harness-specific install commands and Claude Code slash commands (/brainstorm, /execute-plan) rather than a documented public API (REST, SDK, etc.) that an external AI agent could call to drive the product programmatically; no such API is described anywhere in the evidence.
Agent workflows — stories about agent workflows in this arenaMy coding agent can install a skill by itself — a non-interactive, promptless install path an agent can run headlessly end to end
nonemoves PA Scoreimpact 30
All installation evidence describes human-run commands (`/plugin marketplace add`, `devin plugins install`, git clone steps) that differ per harness and are documented as manual steps a user performs, not a single headless, promptless path the agent runs itself end-to-end.
Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the product
nonemoves Built-in AIimpact 30
The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".
Agenticness — how well agents can access and operate the productRun the product headlessly / in CI for automation
nonemoves agent-readyimpact 30
Superpowers is described as a Claude-Code-style plugin/skills system that repeatedly pauses for human approval (brainstorming step asks the user what they're trying to do, 'every path still stops for your approval before implementation', worktree conflicts ask rather than force) — this is an interactive workflow, and no evidence pack item mentions a headless mode, CI flag, non-interactive invocation, or automation pipeline usage.
Agenticness — how well agents can access and operate the productBuild against official SDKs
partialq3/10moves agent-readyimpact 21
Missing: no formally branded 'SDK', no language-specific client libraries, no versioned API reference, and no independent developer accounts of building against it as an SDK.
Openness — open source, data portability, and self-hosting storiesDo everything through the API that I can do in the UI
nonemoves PA Scoreimpact 20
The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".
Privacy posture — data-handling and privacy storiesControl data retention and deletion
nonemoves PA Scoreimpact 20
The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".
Showing the top 8 of 29 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map4 surfaces · 28 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
GitHub README28 stories
- My agent can author and package a new skill end to end by following the project's own spec, template, or meta-skill
- Point an agent at llms.txt or agent-oriented docs
- Build against official SDKs
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Test against a sandbox environment without touching production data
- Perform bulk operations across many items at once
- Define rules that trigger actions automatically on events
- Version, review, and roll back my automations
- Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructions
- Skills are plain markdown files and folders I can read, copy, and carry to another harness — not a proprietary binary format
- Browse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anything
- Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project
- Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment
- A quickstart takes me from nothing to a working installed skill in under five minutes
- Every skill documents what it does and when it activates, so I can predict my agent's new behavior before it surprises me
- Install a skill collection with one documented command — a package-manager one-liner, CLI, or in-agent marketplace command — and it is active in my next session
- Read the product's source under an open license
- Self-host the core product
- Review exactly what instructions and scripts a skill will add — list contents before installing and read every file afterward
- Author a new skill from a documented template — a SKILL.md with name and description frontmatter — without reverse-engineering existing skills
- The collection ships a meta-skill or tool that guides my agent through writing, improving, and packaging new skills
- Skills follow the open Agent Skills specification so the same skill folder is valid beyond this one vendor's tooling
- The collection is actively maintained — recent releases, triaged issues, and accepted community contributions
- The collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibes
- There is a documented update path — marketplace auto-updates or an explicit update command — so I get fixes without reinstalling from scratch
- Releases ship with notes or a changelog so I can see what changed in the skills before I take an update
Hacker News11 stories
- My agent can author and package a new skill end to end by following the project's own spec, template, or meta-skill
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructions
- Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project
- Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right moment
- A quickstart takes me from nothing to a working installed skill in under five minutes
- Every skill documents what it does and when it activates, so I can predict my agent's new behavior before it surprises me
- Install a skill collection with one documented command — a package-manager one-liner, CLI, or in-agent marketplace command — and it is active in my next session
- Review exactly what instructions and scripts a skill will add — list contents before installing and read every file afterward
- The collection is actively maintained — recent releases, triaged issues, and accepted community contributions
2025 docs9 stories
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Test against a sandbox environment without touching production data
- Version, review, and roll back my automations
- Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the project
- A quickstart takes me from nothing to a working installed skill in under five minutes
- Install a skill collection with one documented command — a package-manager one-liner, CLI, or in-agent marketplace command — and it is active in my next session
- There is a documented update path — marketplace auto-updates or an explicit update command — so I get fixes without reinstalling from scratch
Plugins docs6 stories
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Define rules that trigger actions automatically on events
- Version, review, and roll back my automations
- Author a new skill from a documented template — a SKILL.md with name and description frontmatter — without reverse-engineering existing skills
- The collection ships a meta-skill or tool that guides my agent through writing, improving, and packaging new skills
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$npx -y skills add obra/superpowers --skill test-driven-development -a claude-code -y --copy # in a scratch dir, then print installed SKILL.md frontmatterreproduced$ npx -y skills add obra/superpowers --skill test-driven-development -a claude-code -y --copy # in a scratch dir, then print installed SKILL.md frontmatter \ ███████╗██╗ ██╗██╗██╗ ██╗ ███████╗ ██╔════╝██║ ██╔╝██║██║ ██║ ██╔════╝ ███████╗█████╔╝ ██║██║ ██║ ███████╗ ╚════██║██╔═██╗ ██║██║ ██║ ╚════██║ ███████║██║ ██╗██║███████╗███████╗███████║ ╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝╚══════╝ ┌ skills │ ◇ Source: https://github.com/obra/superpowers.git │ [ 3 5 m ◒ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◐ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◓ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◑ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◒ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◐ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◓ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◑ [ 3 9m C l o n i n g r e p o s i t o r y … [ 3 5 m ◒ [ 3 9m C l o n i n g r e p o s i t o r y … .◇ Repository cloned │ ◇ Found 14 skills │ ● Selected 1 skill: test-driven-development │ ◇ Installation Summary ─╮ │ │ │ │ │ │ │ [ │ │ 3 │ │ 6 │ │ m │ │ . │ │ / │ │ . │ │ a │ │ g │ │ e │ │ n │ │ t │ │ s │ │ / │ │ s │ │ k │ │ i │ │ l │ │ l │ │ s │ │ / │ │ t │ │ e │ │ s │ │ t │ │ - │ │ d │ │ r │ │ i │ │ v │ │ e │ │ n │ │ - │ │ d │ │ e │ │ v │ │ e │ │ l │ │ o │ │ p │ │ m │ │ e │ │ n │ │ t │ │ │ │ [ │ │ 3 │ │ 9m │ │ │ │ │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ c │ │ o │ │ p │ │ y │ │ │ │ → │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ C │ │ l │ │ a │ │ u │ │ d │ │ e │ │ │ │ C │ │ o │ │ d │ │ e │ │ │ ├────────────────────────╯ │ ◇ Security Risk Assessments ─╮ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ G │ │ e │ │ n │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ S │ │ o │ │ c │ │ k │ │ e │ │ t │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ S │ │ n │ │ y │ │ k │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ │ │ [ │ │ 3 │ │ 6 │ │ m │ │ t │ │ e │ │ s │ │ t │ │ - │ │ d │ │ r │ │ i │ │ v │ │ e │ │ n │ │ - │ │ d │ │ e │ │ v │ │ e │ │ l │ │ o │ │ p │ │ m │ │ e │ │ n │ │ t │ │ │ │ [ │ │ 3 │ │ 9m │ │ │ │ │ │ │ │ [ │ │ 3 │ │ 2 │ │ m │ │ S │ │ a │ │ f │ │ e │ │ │ │ [ │ │ 3 │ │ 9m │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ [ │ │ 3 │ │ 2 │ │ m │ │ 0 │ │ │ │ a │ │ l │ │ e │ │ r │ │ t │ │ s │ │ │ │ [ │ │ 3 │ │ 9m │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ [ │ │ 3 │ │ 2 │ │ m │ │ L │ │ o │ │ w │ │ │ │ R │ │ i │ │ s │ │ k │ │ │ │ [ │ │ 3 │ │ 9m │ │ │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ D │ │ e │ │ t │ │ a │ │ i │ │ l │ │ s │ │ : │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ h │ │ t │ │ t │ │ p │ │ s │ │ : │ │ / │ │ / │ │ s │ │ k │ │ i │ │ l │ │ l │ │ s │ │ . │ │ s │ │ h │ │ / │ │ o │ │ b │ │ r │ │ a │ │ / │ │ s │ │ u │ │ p │ │ e │ │ r │ │ p │ │ o │ │ w │ │ e │ │ r │ │ s │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ ├─────────────────────────────╯ │ ◇ Installation complete │ ◇ Installed 1 skill ─╮ │ │ │ │ │ │ │ [ │ │ 3 │ │ 2 │ │ m │ │ ✓ │ │ │ │ [ │ │ 3 │ │ 9m │ │ │ │ t │ │ e │ │ s │ │ t │ │ - │ │ d │ │ r │ │ i │ │ v │ │ e │ │ n │ │ - │ │ d │ │ e │ │ v │ │ e │ │ l │ │ o │ │ p │ │ m │ │ e │ │ n │ │ t │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ ( │ │ c │ │ o │ │ p │ │ i │ │ e │ │ d │ │ ) │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ │ │ │ │ │ │ [ │ │ 2 │ │ m │ │ → │ │ │ │ [ │ │ 2 │ │ 2m │ │ │ │ . │ │ / │ │ . │ │ c │ │ l │ │ a │ │ u │ │ d │ │ e │ │ / │ │ s │ │ k │ │ i │ │ l │ │ l │ │ s │ │ / │ │ t │ │ e │ │ s │ │ t │ │ - │ │ d │ │ r │ │ i │ │ v │ │ e │ │ n │ │ - │ │ d │ │ e │ │ v │ │ e │ │ l │ │ o │ │ p │ │ m │ │ e │ │ n │ │ t │ │ │ ├─────────────────────╯ │ └ Done! Review skills before use; they run with full agent permissions. \--- installed SKILL.md frontmatter --- --- name: test-driven-development description: Use when implementing any feature or bugfix, before writing implementation code ---
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
4 of 14 testable claims verified · 3 contradicted → integrity 0/100
36 distinct capability claims found in Superpowers’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
4
Verified
7
Unverified
3
Contradicted
17
Undersold
Verified (11)
“Devin CLI users can install via 'devin plugins install obra/superpowers', with skills auto-triggering at session start”
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructionsfullproof ↗
“Hermes Agent support: install from a git clone, skills register with Hermes' native loader, bootstrap loads on first turn”
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructionsfullproof ↗
“Relevant skills must be invoked before any response or action, including clarifying questions or codebase exploration”
Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right momentfullproof ↗
“Ships 20+ pre-built skills plus a skills-search tool for discovery and SessionStart context injection”
Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right momentfullproof ↗
“Codex, Copilot CLI, and Gemini CLI all recognize ~/.agents/skills/ as a shared cross-runtime install location”
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructionsfullproof ↗
“Installation differs by harness; must be installed separately for each harness in use”
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructionsfullproof ↗
“Antigravity harness runs the plugin's session-start hook so Superpowers is active from the first message; reinstall the same command to update”
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructionsfullproof ↗
“Claude Code users can install via '/plugin marketplace add obra/superpowers-marketplace' then '/plugin install superpowers@superpowers-marketplace'”
Install a skill collection with one documented command — a package-manager one-liner, CLI, or in-agent marketplace command — and it is active in my next sessionfullproof ↗
“Porting to a new harness only adds a tool-mapping reference and bootstrap injector — it never edits the skill markdown files themselves”
Install the same collection into multiple different coding agents — Claude Code, Codex, Cursor, and others — with per-harness instructionsfullproof ↗
“Requires the harness to inject bootstrap text into the model's context at the start of every session with no per-session opt-in”
Installed skills trigger automatically from task context, with descriptions engineered so the agent activates the right skill at the right momentfullproof ↗
“TDD reference doc rebuilt as a positive catalog of six rules leading with good examples, replacing the old anti-patterns doc”
Every skill documents what it does and when it activates, so I can predict my agent's new behavior before it surprises mepartialproof ↗
Unverified (10)
“Small same-shape tasks are batched into a single subagent dispatch to cut cost, with batch review verifying every file made it into the diff”
Perform bulk operations across many items at oncepartialproof ↗
“Skills live in a single skills/ directory as the harness-agnostic source of truth, shared verbatim across every harness”
Skills are plain markdown files and folders I can read, copy, and carry to another harness — not a proprietary binary formatfullproof ↗
“An eval harness drives real tmux sessions of Claude Code, Codex, and Gemini CLI with an LLM actor and verifier judging skill compliance”
The collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibesfullproof ↗
“New skills are authored TDD-style: write pressure-test scenarios, watch them fail, write the skill doc, watch tests pass, then refactor to close loopholes”
The collection ships a meta-skill or tool that guides my agent through writing, improving, and packaging new skillsfullproof ↗
“New skills are authored TDD-style: write pressure-test scenarios, watch them fail, write the skill doc, watch tests pass, then refactor to close loopholes”
The collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibesfullproof ↗
“Ships 20+ pre-built skills plus a skills-search tool for discovery and SessionStart context injection”
Browse or search a catalog of available skills — a registry, leaderboard, or marketplace listing — before installing anythingpartialproof ↗
“Agent can work autonomously for a couple of hours at a time without deviating from the agreed plan”
Set up automations that run autonomously in the backgroundpartialproof ↗
“Antigravity harness runs the plugin's session-start hook so Superpowers is active from the first message; reinstall the same command to update”
There is a documented update path — marketplace auto-updates or an explicit update command — so I get fixes without reinstalling from scratchpartialproof ↗
“Maintains non-LLM integration tests (bash/node/python) for brainstorm-server, OpenCode plugin loading, codex-plugin sync, and analysis utilities”
The collection maintains tests or evals for its skills so changes are verified against regressions rather than shipped on vibesfullproof ↗
“Porting to a new harness only adds a tool-mapping reference and bootstrap injector — it never edits the skill markdown files themselves”
Skills are plain markdown files and folders I can read, copy, and carry to another harness — not a proprietary binary formatfullproof ↗
Contradicted (3)
“Non-catastrophic conflicts or ambiguities get a recorded ruling and work continues automatically; only destructive/irreversible actions stop for a human”
Run the product headlessly / in CI for automationnoneproof ↗
“Devin CLI users can install via 'devin plugins install obra/superpowers', with skills auto-triggering at session start”
My coding agent can install a skill by itself — a non-interactive, promptless install path an agent can run headlessly end to endnoneproof ↗
“Everything ships through the harness's own install mechanism and never edits the user's files directly”
The project documents its security posture — what skills can execute, the trust model for third-party skills, and any telemetry or data collectionnone
Undersold (17)
My agent can author and package a new skill end to end by following the project's own spec, template, or meta-skillfullproof ↗
Point an agent at llms.txt or agent-oriented docspartialproof ↗
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
Operate the product with natural-language commandsfullproof ↗
Test against a sandbox environment without touching production datapartialproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Distribute a standard skill set to my whole team — via a marketplace, a shared repo, or files committed to the projectfullproof ↗
A quickstart takes me from nothing to a working installed skill in under five minutespartialproof ↗
Read the product's source under an open licensepartialproof ↗
Review exactly what instructions and scripts a skill will add — list contents before installing and read every file afterwardpartialproof ↗
Author a new skill from a documented template — a SKILL.md with name and description frontmatter — without reverse-engineering existing skillspartialproof ↗
Skills follow the open Agent Skills specification so the same skill folder is valid beyond this one vendor's toolingfullproof ↗
The collection is actively maintained — recent releases, triaged issues, and accepted community contributionspartialproof ↗
Releases ship with notes or a changelog so I can see what changed in the skills before I take an updatefullproof ↗
Claims outside our story set (17)
Real capability claims found in Superpowers’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Before writing code, the agent asks clarifying questions about what you actually want”
source ↗“Agent drafts a detailed implementation plan clear enough for a junior engineer to follow”
source ↗“Agent runs a subagent-driven-development process, dispatching engineering tasks to subagents and reviewing each one before continuing”
source ↗“Plans emphasize strict red/green TDD, YAGNI, and DRY principles”
source ↗“Requests are classified as spike, bounded, or architectural; small tasks skip the full planning ritual but still require human approval before implementation”
source ↗“Worktree removal refuses to force-delete uncommitted work; instead it names the files and asks the user”
source ↗“Workspace directories are now scoped per-plan so a follow-up plan can't misread a previous plan's progress ledger”
source ↗“Review-fix loop resumes the same implementer subagent, with a five-round circuit breaker that escalates to controller adjudication”
source ↗“When starting a new task, Claude defaults to talking through a plan with you before implementation”
source ↗“After brainstorming, it automatically creates and switches to a git worktree, enabling parallel tasks without clobbering each other”
source ↗“At the end of implementation, offers to open a GitHub PR, merge the worktree locally, or just stop”
source ↗“Enforces no production code without a failing test written first”
source ↗“Slash commands like /brainstorming and /execute-plan let you explore design or run batched implementation plans with review checkpoints”
source ↗“A four-phase debugging methodology requires root-cause investigation, with architectural review triggered after three failed fix attempts”
source ↗“User instructions in CLAUDE.md/AGENTS.md/GEMINI.md or direct requests take precedence over skills, which in turn override default behavior”
source ↗“Bootstrap teaches Claude that it has skills — 'Superpowers' — at session start”
source ↗“Offers a choice between acting as a human PM in a second session or letting the agent dispatch and review subagent tasks itself”
source ↗
Business model
MIT open-source skill framework and development methodology, free on every supported harness; commercial support, tooling, and managed spending offered to enterprises by Prime Radiant.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
Agent surface uptime llms.txt 100% (30d, checked every 6h since Sep 8 '26)