JordanGunn/nunchuck / skills/doctor
doctor
VerifiedDiagnoses 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.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 5.7 KB |
| SKILL.md | skill md | 640 B |
| assets/schemas/session.schema.yaml | config | 1.7 KB |
| assets/schemas/treatment.schema.yaml | config | 1.4 KB |
| references/00_ROUTER.md | markdown | 1.6 KB |
| references/01_SUMMARY.md | markdown | 1.3 KB |
| references/02_TRIGGERS.md | markdown | 1.0 KB |
| references/03_ALWAYS.md | markdown | 1.1 KB |
| references/04_NEVER.md | markdown | 1.1 KB |
| references/05_PROCEDURE.md | markdown | 2.1 KB |
| references/06_FAILURES.md | markdown | 1.9 KB |
| scripts/include/.doctor/session.yaml | config | 236 B |
| scripts/include/doctor_cli.py | script | 11.2 KB |
| scripts/include/doctor_parse.py | script | 10.7 KB |
| scripts/include/pyproject.toml | manifest | 236 B |
| scripts/router_checks.shexecutable | script | 1.7 KB |
| scripts/skill.ps1 | script | 1.5 KB |
| scripts/skill.shexecutable | script | 1.2 KB |
assets/schemas/treatment.schema.yaml
View on GitHub# Treatment Plan Schema
# Artifact: .doctor/treatment.md (generated from this schema)
type: object
required:
- diagnosis_summary
- confidence
- options
properties:
diagnosis_summary:
type: string
description: One-line diagnosis
confidence:
type: integer
minimum: 0
maximum: 100
description: Diagnosis confidence percentage
root_cause:
type: string
description: Identified root cause
options:
type: array
minItems: 1
items:
type: object
required:
- name
- description
- risk
properties:
name:
type: string
description: Short option name
description:
type: string
description: What this option does
risk:
type: string
enum: [low, medium, high]
effort:
type: string
enum: [trivial, small, medium, large]
reversible:
type: boolean
steps:
type: array
items:
type: string
description: Ordered implementation steps
description: Treatment options (at least one required)
recommended:
type: string
description: Name of recommended option
caveats:
type: array
items:
type: string
description: Warnings or considerations
follow_up:
type: array
items:
type: string
description: Suggested follow-up actions
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |