Diagnosing Superpowers
Diagnosing Superpowers is an agent skill (a SKILL.md file) from obra/superpowers. Agents load it when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans… It works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode and has 318,258 GitHub stars across a repository of 9 listed skills.
github.com/obra/superpowers/skills/diagnosing-superpowers (opens in a new tab)
Data as of from the GitHub API and skills.sh; description from the skill's SKILL.md. Report an error
- Multi-skill repo
- Plugin marketplace
- Testing & QA
- Active
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add obra/superpowers
/plugin install superpowers@superpowers-devIn the Claude apps, zip the diagnosing-superpowers folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/obra/superpowers.git
cp -r superpowers/skills/diagnosing-superpowers .agents/skills/diagnosing-superpowers # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/obra/superpowers.git
cp -r superpowers/skills/diagnosing-superpowers .cursor/skills/diagnosing-superpowers # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
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.
When it triggers
- 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
- "it took too long"
- "why is it so expensive"
- "what is it doing"
More skills in obra/superpowers
9 skills are listed from this repository.
Systematic Debuggingobra/superpowers
Writing Plansobra/superpowers
Requesting Code Reviewobra/superpowers
Test Driven Developmentobra/superpowers
Verification Before Completionobra/superpowers
Receiving Code Reviewobra/superpowers
Writing Skillsobra/superpowers
Finishing A Development Branchobra/superpowers
Similar skills
More testing & qa skills
Migrate To Shoehorn
mattpocock/skills
Migrate test files from as type assertions to @total-typescript/shoehorn.
Active · last commit Nov 12, 2026
Testing & QAShellTeam Communication Protocols
wshobson/agents
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid.
Maintained · last commit Nov 8, 2026
Testing & QAPythonBreakdown Diagnosis
anthropics/claude-plugins-official
When a machine goes down, reads the sensor window before the failure, the asset's maintenance history including the free-text close-out notes technicians actually wrote, photos of what they can see…
Maintained · last commit Nov 14, 2026
OfficialTesting & QAPythonBrowser Testing With Devtools
addyosmani/agent-skills
Tests in real browsers via Chrome DevTools MCP.
Active · last commit Nov 14, 2026
Testing & QAJavaScriptAgent Browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web…
Active · last commit Nov 15, 2026
OfficialTesting & QARustAgentic Eval
github/awesome-copilot
Patterns and techniques for evaluating and improving AI agent outputs.
Maintained · last commit Nov 16, 2026
OfficialTesting & QAJavaScript
How do I install the Diagnosing Superpowers skill?
In Claude Code, run /plugin marketplace add obra/superpowers and then /plugin install superpowers@superpowers-dev. For Codex or Cursor, copy the diagnosing-superpowers folder into .agents/skills/ or .cursor/skills/.
Is the Diagnosing Superpowers skill free?
Yes. The repository is open source under the MIT license.
Is Diagnosing Superpowers maintained?
The repository's most recent commit was on Nov 3, 2026. Its latest release is v7.0.2. appsgit only lists skills from repositories with a commit in the last six months.