Skill · em Automatizar e estender

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…

Procedência

Origem: obra/superpowers
Caminho: skills/diagnosing-superpowers
Versão fixada: 5bf4e78011075bcfc0dc295f0724994cd123ee71
Licença: MIT
Espelhado em 25/09/2026
4 mil instalações no skills.sh (lido em 25/09/2026)

Antes de instalar

20 arquivos · 39,9 KB · só texto, nenhum script

Instalar na sua CLI

O comando baixa a versão fixada (commit 5bf4e78) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/diagnosing-superpowers/.

d=".claude/skills/diagnosing-superpowers"
u="https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/diagnosing-superpowers"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/prompts/analyst-common.md" "$u/prompts/analyst-common.md" \
  -o "$d/prompts/cost-and-time.md" "$u/prompts/cost-and-time.md" \
  -o "$d/prompts/plan-adherence.md" "$u/prompts/plan-adherence.md" \
  -o "$d/prompts/quality-evidence.md" "$u/prompts/quality-evidence.md" \
  -o "$d/prompts/repeated-work.md" "$u/prompts/repeated-work.md" \
  -o "$d/prompts/request-conflicts.md" "$u/prompts/request-conflicts.md" \
  -o "$d/prompts/scrub-audit.md" "$u/prompts/scrub-audit.md" \
  -o "$d/prompts/scrub.md" "$u/prompts/scrub.md" \
  -o "$d/prompts/similar-session.md" "$u/prompts/similar-session.md" \
  -o "$d/prompts/skill-timeline.md" "$u/prompts/skill-timeline.md" \
  -o "$d/prompts/stumbles.md" "$u/prompts/stumbles.md" \
  -o "$d/references/context-safety.md" "$u/references/context-safety.md" \
  -o "$d/references/github-issues.md" "$u/references/github-issues.md" \
  -o "$d/references/redaction-policy.md" "$u/references/redaction-policy.md" \
  -o "$d/references/session-discovery.md" "$u/references/session-discovery.md" \
  -o "$d/templates/bundle-README.md" "$u/templates/bundle-README.md" \
  -o "$d/templates/case.md" "$u/templates/case.md" \
  -o "$d/templates/issue.md" "$u/templates/issue.md" \
  -o "$d/templates/report.md" "$u/templates/report.md" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"

Global: instala em ~/.claude/skills/diagnosing-superpowers/.

d="$HOME/.claude/skills/diagnosing-superpowers"
u="https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/diagnosing-superpowers"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/prompts/analyst-common.md" "$u/prompts/analyst-common.md" \
  -o "$d/prompts/cost-and-time.md" "$u/prompts/cost-and-time.md" \
  -o "$d/prompts/plan-adherence.md" "$u/prompts/plan-adherence.md" \
  -o "$d/prompts/quality-evidence.md" "$u/prompts/quality-evidence.md" \
  -o "$d/prompts/repeated-work.md" "$u/prompts/repeated-work.md" \
  -o "$d/prompts/request-conflicts.md" "$u/prompts/request-conflicts.md" \
  -o "$d/prompts/scrub-audit.md" "$u/prompts/scrub-audit.md" \
  -o "$d/prompts/scrub.md" "$u/prompts/scrub.md" \
  -o "$d/prompts/similar-session.md" "$u/prompts/similar-session.md" \
  -o "$d/prompts/skill-timeline.md" "$u/prompts/skill-timeline.md" \
  -o "$d/prompts/stumbles.md" "$u/prompts/stumbles.md" \
  -o "$d/references/context-safety.md" "$u/references/context-safety.md" \
  -o "$d/references/github-issues.md" "$u/references/github-issues.md" \
  -o "$d/references/redaction-policy.md" "$u/references/redaction-policy.md" \
  -o "$d/references/session-discovery.md" "$u/references/session-discovery.md" \
  -o "$d/templates/bundle-README.md" "$u/templates/bundle-README.md" \
  -o "$d/templates/case.md" "$u/templates/case.md" \
  -o "$d/templates/issue.md" "$u/templates/issue.md" \
  -o "$d/templates/report.md" "$u/templates/report.md" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"

Codex

Neste projeto: instala em .agents/skills/diagnosing-superpowers/.

d=".agents/skills/diagnosing-superpowers"
u="https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/diagnosing-superpowers"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/prompts/analyst-common.md" "$u/prompts/analyst-common.md" \
  -o "$d/prompts/cost-and-time.md" "$u/prompts/cost-and-time.md" \
  -o "$d/prompts/plan-adherence.md" "$u/prompts/plan-adherence.md" \
  -o "$d/prompts/quality-evidence.md" "$u/prompts/quality-evidence.md" \
  -o "$d/prompts/repeated-work.md" "$u/prompts/repeated-work.md" \
  -o "$d/prompts/request-conflicts.md" "$u/prompts/request-conflicts.md" \
  -o "$d/prompts/scrub-audit.md" "$u/prompts/scrub-audit.md" \
  -o "$d/prompts/scrub.md" "$u/prompts/scrub.md" \
  -o "$d/prompts/similar-session.md" "$u/prompts/similar-session.md" \
  -o "$d/prompts/skill-timeline.md" "$u/prompts/skill-timeline.md" \
  -o "$d/prompts/stumbles.md" "$u/prompts/stumbles.md" \
  -o "$d/references/context-safety.md" "$u/references/context-safety.md" \
  -o "$d/references/github-issues.md" "$u/references/github-issues.md" \
  -o "$d/references/redaction-policy.md" "$u/references/redaction-policy.md" \
  -o "$d/references/session-discovery.md" "$u/references/session-discovery.md" \
  -o "$d/templates/bundle-README.md" "$u/templates/bundle-README.md" \
  -o "$d/templates/case.md" "$u/templates/case.md" \
  -o "$d/templates/issue.md" "$u/templates/issue.md" \
  -o "$d/templates/report.md" "$u/templates/report.md" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"

Global: instala em ~/.agents/skills/diagnosing-superpowers/.

d="$HOME/.agents/skills/diagnosing-superpowers"
u="https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/diagnosing-superpowers"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/prompts/analyst-common.md" "$u/prompts/analyst-common.md" \
  -o "$d/prompts/cost-and-time.md" "$u/prompts/cost-and-time.md" \
  -o "$d/prompts/plan-adherence.md" "$u/prompts/plan-adherence.md" \
  -o "$d/prompts/quality-evidence.md" "$u/prompts/quality-evidence.md" \
  -o "$d/prompts/repeated-work.md" "$u/prompts/repeated-work.md" \
  -o "$d/prompts/request-conflicts.md" "$u/prompts/request-conflicts.md" \
  -o "$d/prompts/scrub-audit.md" "$u/prompts/scrub-audit.md" \
  -o "$d/prompts/scrub.md" "$u/prompts/scrub.md" \
  -o "$d/prompts/similar-session.md" "$u/prompts/similar-session.md" \
  -o "$d/prompts/skill-timeline.md" "$u/prompts/skill-timeline.md" \
  -o "$d/prompts/stumbles.md" "$u/prompts/stumbles.md" \
  -o "$d/references/context-safety.md" "$u/references/context-safety.md" \
  -o "$d/references/github-issues.md" "$u/references/github-issues.md" \
  -o "$d/references/redaction-policy.md" "$u/references/redaction-policy.md" \
  -o "$d/references/session-discovery.md" "$u/references/session-discovery.md" \
  -o "$d/templates/bundle-README.md" "$u/templates/bundle-README.md" \
  -o "$d/templates/case.md" "$u/templates/case.md" \
  -o "$d/templates/issue.md" "$u/templates/issue.md" \
  -o "$d/templates/report.md" "$u/templates/report.md" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"

Antigravity

Neste projeto: instala em .agents/skills/diagnosing-superpowers/.

d=".agents/skills/diagnosing-superpowers"
u="https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/diagnosing-superpowers"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/prompts/analyst-common.md" "$u/prompts/analyst-common.md" \
  -o "$d/prompts/cost-and-time.md" "$u/prompts/cost-and-time.md" \
  -o "$d/prompts/plan-adherence.md" "$u/prompts/plan-adherence.md" \
  -o "$d/prompts/quality-evidence.md" "$u/prompts/quality-evidence.md" \
  -o "$d/prompts/repeated-work.md" "$u/prompts/repeated-work.md" \
  -o "$d/prompts/request-conflicts.md" "$u/prompts/request-conflicts.md" \
  -o "$d/prompts/scrub-audit.md" "$u/prompts/scrub-audit.md" \
  -o "$d/prompts/scrub.md" "$u/prompts/scrub.md" \
  -o "$d/prompts/similar-session.md" "$u/prompts/similar-session.md" \
  -o "$d/prompts/skill-timeline.md" "$u/prompts/skill-timeline.md" \
  -o "$d/prompts/stumbles.md" "$u/prompts/stumbles.md" \
  -o "$d/references/context-safety.md" "$u/references/context-safety.md" \
  -o "$d/references/github-issues.md" "$u/references/github-issues.md" \
  -o "$d/references/redaction-policy.md" "$u/references/redaction-policy.md" \
  -o "$d/references/session-discovery.md" "$u/references/session-discovery.md" \
  -o "$d/templates/bundle-README.md" "$u/templates/bundle-README.md" \
  -o "$d/templates/case.md" "$u/templates/case.md" \
  -o "$d/templates/issue.md" "$u/templates/issue.md" \
  -o "$d/templates/report.md" "$u/templates/report.md" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"

Global: instala em ~/.gemini/antigravity-cli/skills/diagnosing-superpowers/.

d="$HOME/.gemini/antigravity-cli/skills/diagnosing-superpowers"
u="https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/diagnosing-superpowers"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/prompts/analyst-common.md" "$u/prompts/analyst-common.md" \
  -o "$d/prompts/cost-and-time.md" "$u/prompts/cost-and-time.md" \
  -o "$d/prompts/plan-adherence.md" "$u/prompts/plan-adherence.md" \
  -o "$d/prompts/quality-evidence.md" "$u/prompts/quality-evidence.md" \
  -o "$d/prompts/repeated-work.md" "$u/prompts/repeated-work.md" \
  -o "$d/prompts/request-conflicts.md" "$u/prompts/request-conflicts.md" \
  -o "$d/prompts/scrub-audit.md" "$u/prompts/scrub-audit.md" \
  -o "$d/prompts/scrub.md" "$u/prompts/scrub.md" \
  -o "$d/prompts/similar-session.md" "$u/prompts/similar-session.md" \
  -o "$d/prompts/skill-timeline.md" "$u/prompts/skill-timeline.md" \
  -o "$d/prompts/stumbles.md" "$u/prompts/stumbles.md" \
  -o "$d/references/context-safety.md" "$u/references/context-safety.md" \
  -o "$d/references/github-issues.md" "$u/references/github-issues.md" \
  -o "$d/references/redaction-policy.md" "$u/references/redaction-policy.md" \
  -o "$d/references/session-discovery.md" "$u/references/session-discovery.md" \
  -o "$d/templates/bundle-README.md" "$u/templates/bundle-README.md" \
  -o "$d/templates/case.md" "$u/templates/case.md" \
  -o "$d/templates/issue.md" "$u/templates/issue.md" \
  -o "$d/templates/report.md" "$u/templates/report.md" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/obra/superpowers/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/superpowers.diagnosing-superpowers

Prévia do SKILL.md

---
name: diagnosing-superpowers
description: 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 cur…
---

# 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

Create a todo per step. Steps 5–7 run only on their stated condition.

1. **Problem intake.** Ask one question at a time until you can write a
statement naming the session(s), the turn range if known, what your
partner expected, what happened, and the observable they care about
(wall-clock, tokens, repeated actions, one specific action). "It took
too long" is a complaint, not a problem statement. Note whether the
goal is a superpowers bug report.
2. **Locate.** Resolve each session to verified absolute filesystem paths using
`references/session-discovery.md`. Confirm a past session by quoting its
first prompt and timestamp, and list every candidate you rejected with the
reason, or "none". Enumerate subagent transcripts. Create
`~/.superpowers/diagnosing-superpowers/<session-id>/`, tell your
partner the path, and fill `templates/case.md` there, following its
provenance rules for environment and skill observations.
3. **Triage.** Read the region around the reported problem yourself. Then
dispatch one analyst subagent per dimension in parallel, each given the
case file path, `prompts/analyst-common.md`, and one dimension file from
`prompts/`: `skill-timeline.md`,
`plan-adherence.md`, `repeated-work.md`, `stumbles.md`,
…

Ver todo o marketplace