Trust 50/100Medium risk1 skills

Package

obra/superpowers

An agentic skills framework & software development methodology that works.

Trust means

Trust score is a heuristic blend of popularity, freshness, structure quality, and safety penalties. Useful for ranking, not a guarantee.

Risk means

Risk is generated by automated scans of skills, files, and allowed tools. It is not the same thing as a human security review.

Review status

Auto-scanned only. High-risk signals exist, so manual review is strongly recommended before install.

Risk: Medium (auto-imported from GitHub; risk not assessed)

Stars

134,223

Forks

11,183

Skills

14

Files

45

Suitable for

Ops-minded users and teams that need repeatable runbooks, incident steps, or environment setup workflows with visible boundaries.

Not suitable for

Not a good fit for lightweight personal prompting or environments where shell-heavy automation is banned.

Install prerequisites

What to verify before touching install

  • Confirm where the workflow runs and whether it assumes shell, network, or repo access.
  • Check if the target environment allows the scripts and tools referenced by the skills.
  • Decide who owns approval before using it in shared or production-adjacent contexts.

Recommended first read

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Path: skills/finishing-a-development-branch

Risk level: Low

After install

How to verify it actually works

Run one low-stakes operational task end-to-end in a non-production environment.
Confirm logs, outputs, or generated artifacts look like the skill description promises.
Verify the team can explain what the workflow changed and how to roll it back.
Pay extra attention to any skill that can execute scripts, access the network, or ask for elevated actions.

Core skills

What this package actually helps you do

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

skills/finishing-a-development-branch · 1 file

Low
dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

skills/dispatching-parallel-agents · 1 file

Low
receiving-code-review

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

skills/receiving-code-review · 1 file

Low
using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

skills/using-git-worktrees · 1 file

Low
verification-before-completion

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

skills/verification-before-completion · 1 file

Low
requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

skills/requesting-code-review · 2 files

Low
test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

skills/test-driven-development · 2 files

Low
writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

skills/writing-plans · 2 files

Low
using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

skills/using-superpowers · 3 files

Low
subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

skills/subagent-driven-development · 4 files

Low
executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

skills/executing-plans · 1 file

Low
systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

skills/systematic-debugging · 11 files

Medium
writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

skills/writing-skills · 7 files

Medium
brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

skills/brainstorming · 8 files

High

Package contents

Folders and files

finishing-a-development-branch

skills/finishing-a-development-branch

1 file

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

  • SKILL.md.md

dispatching-parallel-agents

skills/dispatching-parallel-agents

1 file

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

  • SKILL.md.md

receiving-code-review

skills/receiving-code-review

1 file

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

  • SKILL.md.md

using-git-worktrees

skills/using-git-worktrees

1 file

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

  • SKILL.md.md

verification-before-completion

skills/verification-before-completion

1 file

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

  • SKILL.md.md

requesting-code-review

skills/requesting-code-review

2 files

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

  • SKILL.md.md
  • code-reviewer.md.md

test-driven-development

skills/test-driven-development

2 files

Use when implementing any feature or bugfix, before writing implementation code

  • SKILL.md.md
  • testing-anti-patterns.md.md

writing-plans

skills/writing-plans

2 files

Use when you have a spec or requirements for a multi-step task, before touching code

  • SKILL.md.md
  • plan-document-reviewer-prompt.md.md

using-superpowers

skills/using-superpowers

3 files

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

  • SKILL.md.md
  • references/codex-tools.md.md
  • references/gemini-tools.md.md

subagent-driven-development

skills/subagent-driven-development

4 files

Use when executing implementation plans with independent tasks in the current session

  • SKILL.md.md
  • code-quality-reviewer-prompt.md.md
  • implementer-prompt.md.md
  • spec-reviewer-prompt.md.md

executing-plans

skills/executing-plans

1 file

Use when you have a written implementation plan to execute in a separate session with review checkpoints

  • SKILL.md.md

systematic-debugging

skills/systematic-debugging

11 files

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

  • CREATION-LOG.md.md
  • SKILL.md.md
  • condition-based-waiting-example.ts.ts
  • condition-based-waiting.md.md
  • defense-in-depth.md.md
  • find-polluter.sh.sh
  • root-cause-tracing.md.md
  • test-academic.md.md
  • test-pressure-1.md.md
  • test-pressure-2.md.md
  • test-pressure-3.md.md

writing-skills

skills/writing-skills

7 files

Use when creating new skills, editing existing skills, or verifying skills work before deployment

  • SKILL.md.md
  • anthropic-best-practices.md.md
  • examples/CLAUDE_MD_TESTING.md.md
  • graphviz-conventions.dot.dot
  • persuasion-principles.md.md
  • render-graphs.js.js
  • testing-skills-with-subagents.md.md

brainstorming

skills/brainstorming

8 files

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

  • SKILL.md.md
  • scripts/frame-template.html.html
  • scripts/helper.js.js
  • scripts/server.cjs.cjs
  • scripts/start-server.sh.sh
  • scripts/stop-server.sh.sh
  • spec-document-reviewer-prompt.md.md
  • visual-companion.md.md

Last step

Install only after the checks above

If the package fits your workflow, the starter skill makes sense, and the auto-scan signals are acceptable for your environment, then use the exact install command below.

Install command

npx skills add obra/superpowers

Claude Code

Copy to .claude/skills/

GitHub Copilot

Copy to .github/skills/

Codex CLI

Copy to .agents/skills/

Gemini CLI

Copy to .gemini/skills/

Community Signals

What users think

🟢 Active

Related packages

Similar packages worth comparing

No related packages found.

obra/superpowers - Install Agent Skills