Individual skill
diagnosing-superpowers
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.
skills/diagnosing-superpowers/SKILL.md
Source commit 22f0b463e7a5e579904dd6211a520321035526f7
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 313,261
- Repository last updated
- Nov 3, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- brainstorming Repository topic
- coding Repository topic
- obra Repository topic
- sdlc Repository topic
- skills Repository topic
- superpowers Repository topic
- subagent-driven-development Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 6,941 bytesprompts/analyst-common.mddoc · 1,582 bytesprompts/cost-and-time.mddoc · 1,640 bytesprompts/plan-adherence.mddoc · 1,637 bytesprompts/quality-evidence.mddoc · 1,476 bytesprompts/repeated-work.mddoc · 1,469 bytesprompts/request-conflicts.mddoc · 1,011 bytesprompts/scrub-audit.mddoc · 1,363 bytesprompts/scrub.mddoc · 1,471 bytesprompts/similar-session.mddoc · 1,711 bytesprompts/skill-timeline.mddoc · 1,646 bytesprompts/stumbles.mddoc · 1,330 bytesreferences/context-safety.mddoc · 990 bytesreferences/github-issues.mddoc · 1,636 bytesreferences/redaction-policy.mddoc · 2,243 bytesreferences/session-discovery.mddoc · 1,859 bytestemplates/bundle-README.mddoc · 3,672 bytestemplates/case.mddoc · 2,983 bytestemplates/issue.mddoc · 2,680 bytestemplates/report.mddoc · 2,359 bytes
Read excerpt
# 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.
## Workflow