Skip to content

JordanGunn/nunchuck / skills/doctor

doctor

Verified

Diagnoses software failures by combining deterministic evidence gathering with agent judgment. Models failures as medical cases. Idempotent — run repeatedly until confident diagnosis, then generate schema-based treatment.

references/01_SUMMARY.md

View on GitHub
---
description: What this skill is and is not.
index:
  - What It Does
  - What Problems It Solves
  - What It Is Not
  - Key Invariant
  - Artifact Location
---

# Summary

The **doctor** skill diagnoses software failures by combining deterministic evidence gathering with agent judgment.

## What It Does

- Models software failures as medical cases
- Gathers evidence through parameterized search (agent provides terms, script returns matches)
- Tracks symptoms, hypotheses, and confidence levels
- Produces schema-based treatment plans when diagnosis is confident

## What Problems It Solves

- Prevents premature action on incomplete understanding
- Separates observation from interpretation
- Makes uncertainty explicit (confidence percentages)
- Creates reviewable artifacts for handoff

## What It Is Not

- Not a fix-it skill (produces plans, not changes)
- Not a sequential pipeline (idempotent, run until confident)
- Not purely deterministic (balances scripts with agent reasoning)

## Key Invariant

**Execution means investigation, not implementation.** The skill gathers evidence and produces treatment plans. It does not execute fixes.

## Artifact Location

All artifacts stored in `.doctor/`:
- `session.yaml` — Current diagnosis state
- `evidence/` — Evidence snapshots
- `treatment.md` — Generated treatment plan
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse 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.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall