#2 by GitHub stars
obra/superpowers
An agentic skills framework & software development methodology that works.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/brainstorming/SKILL.md
Week of Nov 2, 2026 · +60 / −38 lines
Before Network or broad shell → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
+ 34 If nothing is open when you write your first message and there's one
+ 35 sensible way, steps 1 to 3 happen in that message (see Your First
+ 36 Message).
+ 37
- 45 project or their context already answers.
+ 49 project or their context already answers, or reopen what they've
+ 50 already decided.
- 61 corrections, then one question about what they want: the thing their
- 62 request leaves open whose answer would most change what gets built.
+ 66 corrections. Then, if they haven't told you why they want it, even if
+ 67 you can guess, ask about that: one open question in their own terms,
+ 68 with nothing to pick from. If they have told you, and their request
+ 69 and the project leave open something whose answer would change what
+ 70 gets built, ask about the one that would change it most; when its
+ 71 choices can be named, sketch each concretely, with what it trades off
+ 72 and which you'd pick. If nothing like that is open, there's one
+ 73 sensible way: end with the short design itself (the approach, a line on
+ 74 why the others don't fit, and the design in a few lines) and ask them
+ 75 to approve it. Their approval covers the approach and the design: write
+ 76 the short design doc as approved and go on to the plan.
- 75 design discussion): end with your question. They want this
- 76 conversation.
- 77 - **They didn't:** they may not want a conversation at all. After your
- 78 question, add a light, one-line offer to just get going instead, like
+ 89 design discussion): end there. They want this conversation.
+ 90 - **They didn't:** they may not want a conversation at all. End with a
+ 91 light, one-line offer to just get going instead, like
- 88 Each message ends with one question: a single sentence with no list of
- 89 example answers hanging off it. Use plain language, pitched just a little
- 90 above where your human partner is. Match their vocabulary; never use
- 91 process jargon. You never need to quote this skill to your human
- 92 partner.
+ 101 Ask a question only when the answer would change what gets built and
+ 102 neither the request nor the project answers it. Otherwise, state your
+ 103 call and your reason as a proposal they can correct, and move the work
+ 104 forward. Process steps are always your calls: writing things up, where
+ 105 files go, looking further, how to show something. Do them and say so.
+ 106 Ask one at a time. Use plain language, pitched just a little above where
+ 107 your human partner is. Match their vocabulary; never use process jargon.
+ 108 You never need to quote this skill to your human partner.
- 98 **Get them describing.** Open questions come first. Their own words carry
- 99 intent that your options can't. Offer a short menu only when they're
- 100 stuck. When they say "just guess" or "what do you think?", propose
- 101 something concrete.
+ 114 **Get them describing.** Until you know why they want it, ask open
+ 115 questions, with no example answers attached. Their own words carry
+ 116 intent that your options can't. Once you know why, when a decision has
+ 117 choices you can name, sketch each concretely, with what it trades off
+ 118 and which you'd pick. When they say "just guess" or "what do you think?",
+ 119 propose something concrete.
- 105 libraries for an app; the medium for a piece of art. Find out early which
- 106 of those choices they want to make, which they're handing to you, and what
- 107 they already have to work with. Someone with strong views or skills will
- 108 want to talk it through. Someone counting on you needs sensible defaults,
- 109 said in plain words. When there's existing work, build on what it already
+ 123 libraries for an app; the medium for a piece of art. Read from how they
+ 124 talk which of those choices they want to make. Someone who raises the how
+ 125 or asks about trade-offs wants the options with your pick. Someone who
+ 126 talks about outcomes is handing you the how: make those calls and state
+ 127 each in a line. When there's existing work, build on what it already
- 134 **Offer recon.** Once you have a bit of grounding and looking further
- 135 would help, offer to go look: deeper into their codebase or project,
- 136 their own files and data, or the web. Say what you'd look for. They
- 137 decide whether you go.
+ 152 **Do recon.** Once you have a bit of grounding and looking further
+ 153 would help, go look: deeper into their codebase or project, their own
+ 154 files and data, or the web. Say what you looked for and what you found.
- 143 existing work rules out. Present the two or three that remain, grounding
- 144 each in what the project actually does and saying what it trades off.
- 145 Recommend one and say why, then ask which way they want to go. When
- 146 there's genuinely one sensible way, say so and explain why the others
- 147 don't fit. This is for how it gets built; for what they want, get them
+ 160 existing work rules out. Sketch the two or three that remain concretely
+ 161 enough to picture, grounded in what the project actually does, with what
+ 162 each trades off. Recommend one and say why, then ask which way they want
+ 163 to go; if they've handed you the how, say you'll go with your pick
+ 164 instead. When there's genuinely one sensible way, say so in that
+ 165 message and explain why the others don't fit; the design comes in the
+ 166 next one. This is for how it gets built; for what they want, get them
- 150 **Show, don't tell.** Offer the visual companion (below) whenever seeing
- 151 would help more than reading:
+ 169 **Show, don't tell.** Whenever seeing would help more than reading,
+ 170 sketch it in text: a few lines of what they'd see. Offer the visual
+ 171 companion (below) when the look itself is theirs to decide:
- 183 look at, like a page, a screen, a schedule, or a printout? If so, and
- 184 they haven't seen the visual companion offer yet, send the offer instead
- 185 (its own message, below) and hold the chunk for the next message. Once
- 186 they've accepted, put a mockup next to the description.
+ 203 look at, like a page, a screen, a schedule, or a printout? If so, put a
+ 204 text sketch next to the description. If the look itself is theirs to
+ 205 decide and they haven't seen the visual companion offer yet, send the
+ 206 offer instead (its own message, below) and hold the chunk for the next
+ 207 message. Once they've accepted, put a mockup next to the description.
- 226 Otherwise, ask. Your human partner's preferences override both.
+ 247 Otherwise, pick a sensible place and say where. Your human partner's
+ 248 preferences override both.
- 269 | "I've answered their questions, so I'll write the doc" | Lay out the approaches first, in a message of their own. |
+ 291 | "I've answered their questions, so I'll write the doc" | Lay out the approaches first, in a message of their own (or, when nothing was open from the start, in your first message's short design). |
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/diagnosing-superpowers/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/dispatching-parallel-agents/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/executing-plans/SKILL.md
Week of Nov 2, 2026 · +6 / −4 lines
Before Local scripts → After Local scripts
2ce8aa15d05b → 22f0b463e7a5
- 126 `../subagent-driven-development/scripts/sdd-workspace PLAN_FILE` — it
+ 126 `../subagent-driven-development/scripts/sdd-workspace PLAN_FILE` by its
+ 127 absolute path, from the working tree you're executing in — it
- 172 - Run this skill's `scripts/task-start PLAN_FILE N`. It prints the brief
+ 173 - Run this skill's `scripts/task-start PLAN_FILE N` by its absolute path,
+ 174 from the working tree you're executing in. It prints the brief
- 225 with the test command the brief names for the whole task. It runs the
+ 227 by its absolute path, from the working tree you're executing in, with the test command the brief names for the whole task. It runs the
- 237 (MERGE_BASE = the commit the branch started from, e.g.
+ 239 by its absolute path, from the working tree you're executing in (MERGE_BASE = the commit the branch started from, e.g.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/finishing-a-development-branch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/receiving-code-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/requesting-code-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/subagent-driven-development/SKILL.md
Week of Nov 2, 2026 · +7 / −4 lines
Before Network or broad shell → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
- 114 `bash scripts/sdd-workspace PLAN_FILE` — it prints the plan's git-ignored
+ 114 `bash scripts/sdd-workspace PLAN_FILE` by its absolute path, from the
+ 115 working tree you're executing in — it prints the plan's git-ignored
- 203 `bash scripts/task-brief PLAN_FILE N` — it extracts the task's full text to a
+ 204 `bash scripts/task-brief PLAN_FILE N` by its absolute path, from the
+ 205 working tree you're executing in — it extracts the task's full text to a
- 241 **DONE:** Generate the review package (`bash scripts/review-package PLAN_FILE BASE HEAD`, from this skill's directory — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never `HEAD~1`, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.
+ 243 **DONE:** Generate the review package (`bash scripts/review-package PLAN_FILE BASE HEAD` by its absolute path, from the working tree you're executing in — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never `HEAD~1`, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.
- 260 `bash scripts/review-package PLAN_FILE BASE HEAD` and pass the reviewer the file path
+ 262 `bash scripts/review-package PLAN_FILE BASE HEAD` by its absolute path, from
+ 263 the working tree you're executing in, and pass the reviewer the file path
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/systematic-debugging/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/test-driven-development/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/using-git-worktrees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/using-superpowers/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/verification-before-completion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/writing-plans/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
skills/writing-skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
2ce8aa15d05b → 22f0b463e7a5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2ce8aa15d05b
No earlier version was observed for comparison.
Verified commit 22f0b463e7a5e579904dd6211a520321035526f7
git clone --filter=blob:none --no-checkout https://github.com/obra/superpowers.git .hotskills/obra-superpowers && git -C .hotskills/obra-superpowers checkout --detach 22f0b463e7a5e579904dd6211a520321035526f7
# Copy each selected skill directory from .hotskills/obra-superpowers into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/obra/superpowers.git .hotskills/obra-superpowers && git -C .hotskills/obra-superpowers checkout --detach 22f0b463e7a5e579904dd6211a520321035526f7
# Copy each selected skill directory from .hotskills/obra-superpowers into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/obra/superpowers.git .hotskills/obra-superpowers && git -C .hotskills/obra-superpowers checkout --detach 22f0b463e7a5e579904dd6211a520321035526f7
# Copy each selected skill directory from .hotskills/obra-superpowers into .gemini/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/obra/superpowers.git .hotskills/obra-superpowers && git -C .hotskills/obra-superpowers checkout --detach 22f0b463e7a5e579904dd6211a520321035526f7
# Copy each selected skill directory from .hotskills/obra-superpowers into .opencode/skills/<skill-name>/Heat
6.9- Star growth, last 7 daysAhead of 87% of tracked repositories
- Star growth, last 24 hoursAhead of 85% of tracked repositories
- Rank movement, last 7 daysAhead of 67% of tracked repositories
- Commits, last 30 daysAhead of 67% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- brainstorming
skills/brainstorming - diagnosing-superpowers
skills/diagnosing-superpowers - dispatching-parallel-agents
skills/dispatching-parallel-agents - executing-plans
skills/executing-plans - finishing-a-development-branch
skills/finishing-a-development-branch - receiving-code-review
skills/receiving-code-review - requesting-code-review
skills/requesting-code-review - subagent-driven-development
skills/subagent-driven-development - systematic-debugging
skills/systematic-debugging - test-driven-development
skills/test-driven-development - using-git-worktrees
skills/using-git-worktrees - using-superpowers
skills/using-superpowers - verification-before-completion
skills/verification-before-completion - writing-plans
skills/writing-plans - writing-skills
skills/writing-skills
How it works
brainstorming
When your agent uses it
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
3,494 tokensWhen the skill is activated
Reference documents
3,373 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First: What Do You Actually Know?
- Look Before You Ask
- Your First Message
- The Conversation
- Play It Back
- Size the Work
- The Written Design
- Red Flags
- Visual Companion
Scripts executed separately
scripts/helper.jsscripts/server.cjsscripts/start-server.shscripts/stop-server.sh
Files
../../.claude-plugin/marketplace.jsonasset514 bytes../../.claude-plugin/plugin.jsonasset497 bytes../../hooks/hooks.jsonasset424 bytesSKILL.mdcore15,190 bytesbuilder-check-prompt.mddoc881 bytesscripts/frame-template.htmlasset8,094 bytesscripts/helper.jsruns5,615 bytesscripts/server.cjsruns25,699 bytesscripts/start-server.shruns7,315 bytesscripts/stop-server.shruns3,263 bytesvisual-companion.mddoc13,413 bytes
Read SKILL.md
# Brainstorming
You are very good at building. You build what you believe your human
partner wants, and that belief is usually thinner than it feels. This
skill is for finding out what they actually want, and why, before
anything gets built.
People often haven't finished working out what they want. Good questions
help them think it through. When you understand the why, you make the
hundred decisions they never mention the way they would have made them.
## First: What Do You Actually Know?
Before you reply, ask yourself: what do I know about what they want, andView the complete source on GitHubdiagnosing-superpowers
When your agent uses it
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,642 tokensWhen the skill is activated
Reference documents
7,995 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Quick reference
- Hard rules
- Red Flags
Files
SKILL.mdcore6,941 bytesprompts/analyst-common.mddoc1,582 bytesprompts/cost-and-time.mddoc1,640 bytesprompts/plan-adherence.mddoc1,637 bytesprompts/quality-evidence.mddoc1,476 bytesprompts/repeated-work.mddoc1,469 bytesprompts/request-conflicts.mddoc1,011 bytesprompts/scrub-audit.mddoc1,363 bytesprompts/scrub.mddoc1,471 bytesprompts/similar-session.mddoc1,711 bytesprompts/skill-timeline.mddoc1,646 bytesprompts/stumbles.mddoc1,330 bytesreferences/context-safety.mddoc990 bytesreferences/github-issues.mddoc1,636 bytesreferences/redaction-policy.mddoc2,243 bytesreferences/session-discovery.mddoc1,859 bytestemplates/bundle-README.mddoc3,672 bytestemplates/case.mddoc2,983 bytestemplates/issue.mddoc2,680 bytestemplates/report.mddoc2,359 bytes
Read SKILL.md
# Diagnosing Superpowers
## Overview
Pin down with your human partner what went wrong in a session, read the
transcripts on disk, and report what happened with evidence. You report;
you do not diagnose superpowers. Whoever triages the bundle or the issue
decides whether superpowers changes.
**Core principle:** Every finding cites `path:line`. No citation, no
finding. Every number comes from the transcript or from a command you ran,
never from memory.
## WorkflowView the complete source on GitHubdispatching-parallel-agents
When your agent uses it
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
1,363 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Pattern
- Agent Prompt Structure
- Common Mistakes
- When NOT to Use
- Real Example from Session
- Verification
Files
SKILL.mdcore6,078 bytes
Read SKILL.md
# Dispatching Parallel Agents
## Overview
You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.
**Core principle:** Dispatch one agent per independent problem domain. Let them work concurrently.
## When to Use
```dot
digraph when_to_use {View the complete source on GitHubexecuting-plans
When your agent uses it
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
4,322 tokensWhen the skill is activated
Reference documents
1,445 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- The Process
- Setup
- The Task Loop
- Final Review
- Finish
- Common Rationalizations
Scripts executed separately
scripts/task-donescripts/task-start../subagent-driven-development/scripts/review-package../subagent-driven-development/scripts/sdd-workspace
Files
SKILL.mdcore18,364 bytesscripts/task-doneruns1,900 bytesscripts/task-startruns1,185 bytes../requesting-code-review/code-reviewer.mddoc6,449 bytes../subagent-driven-development/scripts/review-packageruns2,444 bytes../subagent-driven-development/scripts/sdd-workspaceruns4,823 bytes
Read SKILL.md
# Executing Plans
Execute the plan yourself, task by task, in this session: no implementer
subagent per task, no reviewer per task. One fresh-context review of the
whole branch at the end.
**Why inline:** Subagent-driven development pays for a fresh implementer
and a fresh reviewer on every task, each re-reading the codebase from zero.
Inline execution pays for one context (yours) plus one reviewer at the end.
What it gives up is a fresh context per task and a second pair of eyes per
task. This skill keeps what those two things bought, by other means: the
brief is the spec, the ledger is your memory, TDD is the per-task gate, and
the final reviewer is the second pair of eyes.
View the complete source on GitHubfinishing-a-development-branch
When your agent uses it
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
1,926 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Step 1: Verify Tests
- Step 2: Detect Environment
- Step 3: Determine Base Branch
- Step 4: Present Options
- Step 5: Execute Choice
- Step 6: Cleanup Workspace
- Quick Reference
- Common Rationalizations
Files
SKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytesSKILL.mdcore7,781 bytes
Read SKILL.md
# Finishing a Development Branch
## Overview
**Core principle:** Verify tests → Detect environment → Present options → Execute choice → Clean up.
**Announce at start:** "I'm using the finishing-a-development-branch skill to complete this work."
## Step 1: Verify Tests
Run the project's full test suite (`npm test` / `cargo test` / `pytest` / `go test ./...`).
**If tests fail**, report the failures and stop — the menu comes after a green suite:
View the complete source on GitHubreceiving-code-review
When your agent uses it
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
1,459 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- The Response Pattern
- Forbidden Responses
- Handling Unclear Feedback
- Source-Specific Handling
- YAGNI Check for "Professional" Features
- Implementation Order
- When To Push Back
- Acknowledging Correct Feedback
- Gracefully Correcting Your Pushback
- Common Mistakes
- Real Examples
- GitHub Thread Replies
Files
SKILL.mdcore6,203 bytes
Read SKILL.md
# Code Review Reception
## Overview
Code review requires technical evaluation, not emotional performance.
**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.
## The Response Pattern
```
WHEN receiving code review feedback:
1. READ: Complete feedback without reactingView the complete source on GitHubrequesting-code-review
When your agent uses it
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
688 tokensWhen the skill is activated
Reference documents
1,445 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Request Review
- How to Request
- Example
- Common Rationalizations
- Red Flags
Files
SKILL.mdcore2,974 bytesSKILL.mdcore2,974 bytescode-reviewer.mddoc6,449 bytes
Read SKILL.md
# Requesting Code Review
Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history.
**Core principle:** Review early, review often.
## When to Request Review
**Mandatory:**
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
**Optional but valuable:**View the complete source on GitHubsubagent-driven-development
When your agent uses it
Use when executing implementation plans with independent tasks in the current session
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
4,478 tokensWhen the skill is activated
Reference documents
7,079 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- The Process
- Setup
- Model Selection
- The Task Loop
- Final Review
- Common Rationalizations
Scripts executed separately
scripts/review-packagescripts/sdd-reposcripts/sdd-workspacescripts/task-brief
Files
SKILL.mdcore19,740 bytesSKILL.mdcore19,740 bytesimplementer-prompt.mddoc6,335 bytesre-review-prompt.mddoc4,833 bytesreferences/batching.mddoc583 bytesreferences/cannot-verify.mddoc513 bytesreferences/final-review.mddoc2,576 bytesreferences/fix-loop.mddoc4,314 bytesreferences/handling-reports.mddoc1,062 bytesreferences/preflight.mddoc1,353 bytesreferences/resuming.mddoc614 bytesscripts/review-packageruns2,444 bytesscripts/sdd-reporuns2,356 bytesscripts/sdd-workspaceruns4,823 bytesscripts/task-briefruns4,769 bytestask-reviewer-prompt.mddoc9,175 bytes
Read SKILL.md
# Subagent-Driven Development
Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.
**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
**Core principle:** Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration
**Narration:** between tool calls, narrate at most one short line — the
ledger and the tool results carry the record.
**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
**Rulings, not stalls.** A running plan does not wait on a human. Conflicts,View the complete source on GitHubsystematic-debugging
When your agent uses it
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
2,203 tokensWhen the skill is activated
Reference documents
2,999 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- The Iron Law
- When to Use
- The Four Phases
- Red Flags - STOP and Follow Process
- your human partner's Signals You're Doing It Wrong
- Common Rationalizations
- Quick Reference
- When Process Reveals "No Root Cause"
- Supporting Techniques
Scripts executed separately
condition-based-waiting-example.tsfind-polluter.sh
Files
SKILL.mdcore9,530 bytesSKILL.mdcore9,530 bytescondition-based-waiting-example.tsruns5,054 bytescondition-based-waiting.mddoc3,516 bytesdefense-in-depth.mddoc3,650 bytesfind-polluter.shruns1,986 bytesroot-cause-tracing.mddoc5,321 bytes
Read SKILL.md
# Systematic Debugging
## Overview
**Core principle:** ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
**Violating the letter of this process is violating the spirit of debugging.**
## The Iron Law
```
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
```
View the complete source on GitHubtest-driven-development
When your agent uses it
Use when implementing any feature or bugfix, before writing implementation code
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
2,340 tokensWhen the skill is activated
Reference documents
1,779 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Iron Law
- Red-Green-Refactor
- Good Tests
- Common Rationalizations
- Red Flags - STOP and Start Over
- Example: Bug Fix
- Verification Checklist
- When Stuck
- Debugging Integration
- Final Rule
Files
SKILL.mdcore9,578 bytesSKILL.mdcore9,578 bytesSKILL.mdcore9,578 bytesSKILL.mdcore9,578 bytesSKILL.mdcore9,578 byteswriting-good-tests.mddoc8,268 bytes
Read SKILL.md
# Test-Driven Development (TDD)
## Overview
Write the test first. Watch it fail. Write minimal code to pass.
**Core principle:** If you didn't watch the test fail, you don't know if it tests the right thing.
**Violating the letter of the rules is violating the spirit of the rules.**
## When to Use
**Always:**
- New featuresView the complete source on GitHubusing-git-worktrees
When your agent uses it
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
1,623 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Step 0: Detect Existing Isolation
- Step 1: Create Isolated Workspace
- Step 2: Project Setup
- Step 3: Verify Clean Baseline
- Quick Reference
- Common Rationalizations
Files
SKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytesSKILL.mdcore6,813 bytes
Read SKILL.md
# Using Git Worktrees
## Overview
Ensure work happens in an isolated workspace. Prefer your platform's native worktree tools. Fall back to manual git worktrees only when no native tool is available.
**Core principle:** Detect existing isolation first. Then use native tools. Then fall back to git. Never fight the harness.
**Announce at start:** "I'm using the using-git-worktrees skill to set up an isolated workspace."
## Step 0: Detect Existing Isolation
**Before creating anything, check if you are already in an isolated workspace.**
View the complete source on GitHubusing-superpowers
When your agent uses it
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
735 tokensWhen the skill is activated
Reference documents
4,151 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The Rule
- Skill Priority
- Red Flags
- Platform Adaptation
- User Instructions
Files
SKILL.mdcore3,192 bytesreferences/antigravity-tools.mddoc1,495 bytesreferences/claude-code-tools.mddoc1,469 bytesreferences/codex-tools.mddoc4,762 bytesreferences/gemini-tools.mddoc4,598 bytesreferences/hermes-tools.mddoc1,964 bytesreferences/muse-tools.mddoc1,908 bytesreferences/pi-tools.mddoc1,242 bytes
Read SKILL.md
<SUBAGENT-STOP>
If you were dispatched as a subagent to execute a specific task, ignore this skill.
</SUBAGENT-STOP>
<EXTREMELY-IMPORTANT>
If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. You cannot rationalize your way out of this.
</EXTREMELY-IMPORTANT>
## The Rule
View the complete source on GitHubverification-before-completion
When your agent uses it
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
854 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- The Iron Law
- The Gate Function
- Common Failures
- Red Flags - STOP
- Rationalization Prevention
- Key Patterns
- When To Apply
Files
SKILL.mdcore3,646 bytes
Read SKILL.md
# Verification Before Completion
## Overview
**Core principle:** Evidence before claims, always.
**Violating the letter of this rule is violating the spirit of this rule.**
## The Iron Law
```
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
```
View the complete source on GitHubwriting-plans
When your agent uses it
Use when you have a spec or requirements for a multi-step task, before touching code
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
2,313 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Scope Check
- File Structure
- Task Right-Sizing
- Step Granularity
- Plan Document Header
- Task Structure
- What a Step Contains
- Self-Review
- Execution Handoff
Files
SKILL.mdcore10,335 bytesSKILL.mdcore10,335 bytesSKILL.mdcore10,335 bytes
Read SKILL.md
# Writing Plans
## Overview
Write implementation plans for an engineer who has not seen this codebase or this spec. Assume they write idiomatic code in the project's language once they know the exact interface and the exact test, and that they will make a reasonable choice wherever the plan leaves one open. What they cannot know is what you decided: which files, which names and signatures, which values from the spec, which tests prove each task. Document those. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
**Announce at start:** "I'm using the writing-plans skill to create the implementation plan."
**Context:** If working in an isolated worktree, it should have been created via the `superpowers:using-git-worktrees` skill at execution time.
**Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
- (User preferences for plan location override this default)
## Scope CheckView the complete source on GitHubwriting-skills
When your agent uses it
Use when creating new skills, editing existing skills, or verifying skills work before deployment
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
3,651 tokensWhen the skill is activated
Reference documents
21,328 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- What is a Skill?
- TDD Mapping for Skills
- When to Create a Skill
- Skill Types
- Directory Structure
- Writing SKILL.md
- Flowcharts
- Code Examples
- File Organization
- The Iron Law (Same as TDD)
- Testing All Skill Types
- Common Rationalizations for Skipping Testing
- Match the Form to the Failure
- Bulletproofing Against Rationalization
- RED-GREEN-REFACTOR for Skills
- Anti-Patterns
- STOP: Before Moving to Next Skill
- Skill Creation Checklist (TDD Adapted)
- Discovery Workflow
Scripts executed separately
render-graphs.js
Files
../using-superpowers/references/codex-tools.mddoc4,762 bytes../using-superpowers/references/gemini-tools.mddoc4,598 bytesSKILL.mdcore16,738 bytesSKILL.mdcore16,738 bytesSKILL.mdcore16,738 bytesreferences/CLAUDE_MD_TESTING.mddoc5,423 bytesreferences/anthropic-best-practices.mddoc46,197 bytesreferences/bulletproofing.mddoc2,577 bytesreferences/discovery.mddoc7,616 bytesreferences/flowcharts.mddoc1,262 bytesreferences/graphviz-conventions.dotasset5,970 bytesreferences/persuasion-principles.mddoc5,901 bytesreferences/testing-skills-with-subagents.mddoc12,557 bytesrender-graphs.jsruns4,968 bytes
Read SKILL.md
# Writing Skills
## Overview
**Writing skills IS Test-Driven Development applied to process documentation.**
**Personal skills live in your runtime's skills directory** (`~/.claude/skills/` on Claude Code) — see [codex-tools.md](../using-superpowers/references/codex-tools.md) or [gemini-tools.md](../using-superpowers/references/gemini-tools.md) for the path on those runtimes. Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.
You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
**REQUIRED BACKGROUND:** You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.
View the complete source on GitHubSkills included
- brainstorming
- diagnosing-superpowers
- dispatching-parallel-agents
- executing-plans
- finishing-a-development-branch
- receiving-code-review
- requesting-code-review
- subagent-driven-development
- systematic-debugging
- test-driven-development
- using-git-worktrees
- using-superpowers
- verification-before-completion
- writing-plans
- writing-skills
Repository facts
- License
- MIT
- Created
- Oct 9, 2025
- Last pushed
- Nov 3, 2026
- Forks
- 27,855
- Open issues
- 178
- Project activity
- Active
Rank over the last 12 weeks
Now #2 · best #1 · down 1 in 30 days
- #1 on Aug 2
- #1 from Aug 7 to Oct 25
- #1 from Oct 28 to Nov 3
- #2 since Nov 4
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 26 notes
skills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/finishing-a-development-branch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/requesting-code-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/subagent-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/systematic-debugging/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/test-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/test-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/test-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/test-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/using-git-worktrees/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/using-git-worktrees/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/using-git-worktrees/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/using-git-worktrees/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/using-git-worktrees/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 7 dangerous shell commandsin 4 files: brainstorming/scripts/stop-server.sh:22 brainstorming/scripts/start-server.sh:155 subagent-driven-development/references/final-review.md:45 and 1 more
- 38 network referencesin 7 files: writing-skills/references/anthropic-best-practices.md:7 brainstorming/visual-companion.md:40 .claude-plugin/plugin.json:7 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- 15 executable scriptsin 13 files: skills/subagent-driven-development/scripts/review-package:1 skills/subagent-driven-development/scripts/sdd-workspace:1 brainstorming/scripts/helper.js:1 and 10 more
- 5 references to secretsin 3 files: brainstorming/scripts/server.cjs:133 systematic-debugging/SKILL.md:98 brainstorming/visual-companion.md:53
- No requests to vote in Hot
Show all 65 signals by file
.claude-plugin/plugin.json
- Network accessline 7
"email": "jesse@fsck.com" }, "homepage": "https://github.com/obra/superpowers", - Network accessline 8
}, "homepage": "https://github.com/obra/superpowers", "repository": "https://github.com/obra/superpowers", - Network accessline 9
"homepage": "https://github.com/obra/superpowers", - Network accessline 10
"repository": "https://github.com/obra/superpowers",
skills/brainstorming/scripts/helper.js
- Executable scriptline 1
Executable file
skills/brainstorming/scripts/server.cjs
- Executable scriptline 1
Executable file - Network accessline 104
const STATE_DIR = path.join(SESSION_DIR, 'state'); const SUPERPOWERS_VERSION = readSuperpowersVersion(); const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png'; - Network accessline 105
const SUPERPOWERS_VERSION = readSuperpowersVersion(); const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png'; const TELEMETRY_DISABLE_ENV_VARS = [ - Network accessline 106
const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png'; - Access to secretsline 133
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Network accessline 251
return '<div class="brand"><a href="https://github.com/obra/superpowers">' + logo + '<span class="brand-copy">' + text + '</span></a></div>';
skills/brainstorming/scripts/start-server.sh
skills/brainstorming/scripts/stop-server.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 22
rm -f "${STATE_DIR}/server-info" - Dangerous shell operationline 79
rm -f "$PID_FILE" "$SERVER_ID_FILE" - Dangerous shell operationline 109
rm -f "$PID_FILE" "$SERVER_ID_FILE" "${STATE_DIR}/server.log" - Dangerous shell operationline 114
rm -rf "$SESSION_DIR"
skills/brainstorming/visual-companion.md
- Network accessline 40
# Returns: {"type":"server-started","port":52341, # "url":"http://localhost:52341/?key=ab12…", - Network accessline 41
# "url":"http://localhost:52341/?key=ab12…", - Network accessline 48
**The URL contains a session key (`?key=…`).** The server rejects any request without it, so always give the user the **complete** URL from the `url` field — never strip the query string, and never hand out a bare `http://host:port`. The - Network accessline 49
without it, so always give the user the **complete** URL from the `url` field — never strip the query string, and never hand out a bare `http://host:port`. The key gates HTTP and WebSocket access so a stray browser tab or another machine on - Network accessline 50
never strip the query string, and never hand out a bare `http://host:port`. The - Access to secretsline 53
[Credential-related source omitted]
skills/diagnosing-superpowers/references/github-issues.md
- Network accessline 17
curl -s -H "Accept: application/vnd.github+json" \ - Network accessline 18
"https://api.github.com/search/issues?q=repo:obra/superpowers+is:issue+<url-encoded terms>&per_page=10" \ - Network accessline 22
Without curl, hand over `https://github.com/obra/superpowers/issues?q=<terms>`. - Network accessline 43
https://github.com/obra/superpowers/issues/new?template=bug_report.md&title=<url-encoded title>&body=<url-encoded body>
skills/executing-plans/scripts/task-done
- Executable scriptline 1
#!/usr/bin/env bash
skills/executing-plans/scripts/task-start
- Executable scriptline 1
#!/usr/bin/env bash
skills/subagent-driven-development/references/final-review.md
- Dangerous shell operationline 45
delete this plan's workspace (`rm -rf <workspace>`) — the git history is
skills/subagent-driven-development/scripts/review-package
skills/subagent-driven-development/scripts/sdd-repo
- Executable scriptline 1
#!/usr/bin/env bash
skills/subagent-driven-development/scripts/sdd-workspace
skills/subagent-driven-development/scripts/task-brief
skills/systematic-debugging/SKILL.md
skills/systematic-debugging/condition-based-waiting-example.ts
- Executable scriptline 1
Executable file
skills/systematic-debugging/find-polluter.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/writing-skills/SKILL.md
- Network accessline 356
**GREEN Phase - Write Minimal Skill:** - [ ] Name uses only letters, numbers, hyphens (no parentheses/special chars) - [ ] YAML frontmatter with required `name` and `description` fields (max 1024 chars; see [spec](https://agentskills.io/spe - Network accessline 357
- [ ] Name uses only letters, numbers, hyphens (no parentheses/special chars) - [ ] YAML frontmatter with required `name` and `description` fields (max 1024 chars; see [spec](https://agentskills.io/specification)) - [ ] Description starts w - Network accessline 358
- [ ] YAML frontmatter with required `name` and `description` fields (max 1024 chars; see [spec](https://agentskills.io/specification))
skills/writing-skills/references/anthropic-best-practices.md
- Network accessline 7
For conceptual background on how Skills work, see the [Skills overview](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview). - Network accessline 13
The [context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is a public good. Your Skill shares the context window with everything else your agent needs to know, including: - Network accessline 152
For complete Skill structure details, see the [Skills overview](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview#skill-structure). - Network accessline 237
SKILL.md serves as an overview that points agents to detailed materials as needed, like a table of contents in an onboarding guide. For an explanation of how progressive disclosure works, see [How Skills work](https://platform.claude.com/do - Network accessline 249
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="Simple SKILL.md file showing YAML frontmatter and - Network accessline 253
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="Bundling additional reference files like refe - Network accessline 919
<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="Bundling executable scripts alongside instr - Network accessline 1011
List required packages in your SKILL.md and verify they're available in the [code execution tool documentation](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool). - Network accessline 1015
Skills run in a code execution environment with filesystem access, bash commands, and code execution capabilities. For the conceptual explanation of this architecture, see [The Skills architecture](https://platform.claude.com/docs/en/agents - Network accessline 1051
For complete details on the technical architecture, see [How Skills work](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview#how-skills-work) in the Skills overview. - Network accessline 1095
The SKILL.md frontmatter requires `name` (64 characters max) and `description` (1024 characters max) fields. See the [Skills overview](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview#skill-structure) for complete - Network accessline 1099
Keep SKILL.md body under 500 lines for optimal performance. If your content exceeds this, split it into separate files using the progressive disclosure patterns described earlier. For architectural details, see the [Skills overview](https:/ - Network accessline 1138
<CardGroup cols={2}> <Card title="Get started with Agent Skills" icon="rocket" href="https://platform.claude.com/docs/en/agents-and-tools/agent-skills/quickstart"> - Network accessline 1139
<Card title="Get started with Agent Skills" icon="rocket" href="https://platform.claude.com/docs/en/agents-and-tools/agent-skills/quickstart"> - Network accessline 1143
<Card title="Use Skills in Claude Code" icon="terminal" href="https://code.claude.com/docs/en/skills"> - Network accessline 1147
<Card title="Use Skills with the API" icon="code" href="https://platform.claude.com/docs/en/build-with-claude/skills-guide">
skills/writing-skills/references/discovery.md
- Network accessline 8
**Frontmatter (YAML):** - Two required fields: `name` and `description` (see [agentskills.io/specification](https://agentskills.io/specification) for all supported fields) - Network accessline 9
- Two required fields: `name` and `description` (see [agentskills.io/specification](https://agentskills.io/specification) for all supported fields)
skills/writing-skills/render-graphs.js
- Executable scriptline 1
#!/usr/bin/env node
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 2 facts
- Contacts primeradiant.com, which SKILL.md, the README and the plugin manifest do not mentionbrainstorming/scripts/server.cjs:106High confidence
- Contacts github.com, which SKILL.md, the README and the plugin manifest do not mentionbrainstorming/scripts/server.cjs:251High confidence
Signal confidence: 61 facts
- Executable script in code of a file that runsbrainstorming/scripts/helper.js:1High confidence
- Executable script in code of a file that runsbrainstorming/scripts/server.cjs:1High confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:104High confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:105High confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:106High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuebrainstorming/scripts/server.cjs:133Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuebrainstorming/scripts/server.cjs:134Low confidence
- Network access in code of a file that runsbrainstorming/scripts/server.cjs:251High confidence
- Executable script in code of a file that runsbrainstorming/scripts/start-server.sh:1High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/start-server.sh:155High confidence
- Executable script in code of a file that runsbrainstorming/scripts/stop-server.sh:1High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:22High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:79High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:109High confidence
- Dangerous shell operation in code of a file that runsbrainstorming/scripts/stop-server.sh:114High confidence
- Network access in code of documentationbrainstorming/visual-companion.md:40Low confidence
- Network access in code of documentationbrainstorming/visual-companion.md:41Low confidence
- Network access in prose of documentationbrainstorming/visual-companion.md:48Low confidence
- Network access in prose of documentationbrainstorming/visual-companion.md:49Low confidence
- Network access in prose of documentationbrainstorming/visual-companion.md:50Low confidence
- Access to secrets in prose of documentationbrainstorming/visual-companion.md:53Low confidence
- Network access in code of documentationdiagnosing-superpowers/references/github-issues.md:17Low confidence
- Network access in code of documentationdiagnosing-superpowers/references/github-issues.md:18Low confidence
- Network access in prose of documentationdiagnosing-superpowers/references/github-issues.md:22Low confidence
- Network access in code of documentationdiagnosing-superpowers/references/github-issues.md:43Low confidence
- Executable script in code of a file that runsexecuting-plans/scripts/task-done:1High confidence
- Executable script in code of a file that runsexecuting-plans/scripts/task-start:1High confidence
- Dangerous shell operation in prose of documentationsubagent-driven-development/references/final-review.md:45Low confidence
- Executable script in code of a file that runsskills/subagent-driven-development/scripts/review-package:1High confidence
- Executable script in code of a file that runssubagent-driven-development/scripts/review-package:1High confidence
- Executable script in code of a file that runssubagent-driven-development/scripts/sdd-repo:1High confidence
- Executable script in code of a file that runsskills/subagent-driven-development/scripts/sdd-workspace:1High confidence
- Executable script in code of a file that runssubagent-driven-development/scripts/sdd-workspace:1High confidence
- Executable script in code of a file that runssubagent-driven-development/scripts/task-brief:1High confidence
- Dangerous shell operation in code of a file that runssubagent-driven-development/scripts/task-brief:99High confidence
- Access to secrets in code of the SKILL.mdsystematic-debugging/SKILL.md:98High confidence
- Access to secrets in code of the SKILL.mdsystematic-debugging/SKILL.md:99High confidence
- Executable script in a comment of a file that runssystematic-debugging/condition-based-waiting-example.ts:1Low confidence
- Executable script in code of a file that runssystematic-debugging/find-polluter.sh:1High confidence
- Network access in prose of the SKILL.mdwriting-skills/SKILL.md:356Low confidence
- Network access in prose of the SKILL.mdwriting-skills/SKILL.md:357Low confidence
- Network access in prose of the SKILL.mdwriting-skills/SKILL.md:358Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:7Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:13Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:152Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:237Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:249Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:253Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:919Low confidence
- Network access in prose of documentationwriting-skills/references/anthropic-best-practices.md:1011Low confidence
and 11 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/brainstorming/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/brainstorming/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Native | Path .opencode/INSTALL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/obra-superpowers/)