Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jordangunn-doctor
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/doctor
What's inside
- Skill name
doctor- Description
- Orchestrator skill for the `doctor` skillset. A diagnostic protocol that models software failures as medical cases — preventing premature action, wrong-layer fixation, and false certainty in complex codebases.
- License
- MIT
- Metadata
- author: Jordan Godau · version: 0.1.0
- Instructions
- 45 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (29)
- EXAM_NOTE.md · .resources/assets/
- INTAKE_NOTE.md · .resources/assets/
- TREATMENT_NOTE.md · .resources/assets/
- TRIAGE_REPORT.md · .resources/assets/
- ONTOLOGY.md · .resources/references/
- OPERATING_RULES.md · .resources/references/
- PHILOSOPHY.md · .resources/references/
- SKILL.md
- SKILL.md · exam/
- 01_PURPOSE.md · exam/references/
- 02_SCOPE.md · exam/references/
- 03_BEHAVIOR.md · exam/references/
- 04_OUTPUT.md · exam/references/
- SKILL.md · intake/
- 01_PURPOSE.md · intake/references/
- 02_EPISTEMIC_STANCE.md · intake/references/
- 03_BEHAVIOR.md · intake/references/
- 04_OUTPUT.md · intake/references/
- SKILL.md · treatment/
- 01_PURPOSE.md · treatment/references/
- 02_DIAGNOSIS.md · treatment/references/
- 03_OPTIONS.md · treatment/references/
- 04_OUTPUT.md · treatment/references/
- SKILL.md · triage/
- 01_PURPOSE.md · triage/references/
- 02_SCOPE.md · triage/references/
- 03_BEHAVIOR.md · triage/references/
- 04_OUTPUT.md · triage/references/
- evidence.sh · triage/scripts/
SKILL.md (first lines)
# Doctor Protocol You are an agent operating under the **Doctor Protocol**, a skillset designed to prevent premature action, wrong-layer fixation, and false certainty when working in complex codebases. This protocol models software failures as **medical cases**, not puzzles to immediately solve. ## Core Philosophy 1. **Symptoms are not causes** — The user's description is a *witness statement*, not ground truth. 2. **Uncertainty is normal** — Early confidence is usually a sign of a bad mental model. 3. **Breadth before depth** — Many failures originate outside the layer where they manifest. 4. **Do no harm** — No fixes, refactors, or executions unless explicitly requested. 5. **Artifacts matter** — Outputs should be structured, reviewable, and reusable. 6. **Each skill must stand alone** — Any skill may be invoked in isolation and must produce a complete, useful artifact. ## Skills | Skill | Purpose | Output | |-------|---------|--------| | `doctor-intake` | Convert user's description into clinically precise intake note | Intake Note | | `doctor-triage` | Breadth-first hypothesis surfacing and prioritization | Triage Report | | `doctor-exam` | Focused evidence gathering on one suspect area | Exam Note | | `doctor-treatment` | Diagnosis estimate + proposed treatment options | Treatment Note | ## Shared Resources - `ONTOLOGY.md` — Shared vocabulary (patient, symptom, witness statement, etc.) - `PHILOSOPHY.md` — Epistemic stance and operating principles - `OPERATING_RULES.md` — Final rules and constraints ## Asset Templates - `INTAKE_NOTE.md` — Template for intake skill output - `TRIAGE_REPORT.md` — Template for triage skill output - `EXAM_NOTE.md` — Template for exam skill output - `TREATMENT_NOTE.md` — Template for treatment skill output ## Final Operating Rule > If the problem feels confusing, contradictory, or nonsensical — > **assume the mental model is wrong, not the system.** Your job is to restore epistemic clarity before action.
From JordanGunn/skills, MIT.
More from JordanGunn/skills
- 0.464score
prompt
Jordan Godau
Orchestrator skill for the `prompt` skillset.
SkillDFreshness: D★ 6Claude Code +9 - 0.439score
mimic
Jordan Godau
Persona overlay skill.
SkillDFreshness: D★ 6Claude Code +9 - 0.434score
refactor
Jordan Godau
Orchestrator skill for the `refactor` skillset.
SkillDFreshness: D★ 6Claude Code +9 - 0.434score
task
Jordan Godau
Orchestrator skill for the `task` skillset.
SkillDFreshness: D★ 6Claude Code +9 - 0.431score
md
Jordan Godau
Orchestrates markdown chunking workflows (split → index → summary)
SkillDFreshness: D★ 6Claude Code +9 - 0.431score
plan
Jordan Godau
Orchestrator skill for the `plan` skillset.
SkillDFreshness: D★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jan 9, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 0.1.0
- License
- MIT
- Repository
- github.com/JordanGunn/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Jordan Godau
- 0.472score
asi-onboard
Jordan Godau
Establish disk-backed repository context by reading ASI documentation entrypoints and recording a scoped context digest.
SkillDFreshness: D★ 10Claude Code +9 - 0.472score
asi-creator
Jordan Godau
Create ASI-compliant skills with deterministic governance.
SkillDFreshness: D★ 10Claude Code +9 - 0.470score
plan-exec
Jordan Godau
Execute tasks in the active plan under `.plan/active/`.
SkillDFreshness: D★ 9Claude Code +9 - 0.470score
doctor
Jordan Godau
Diagnoses software failures by combining deterministic evidence gathering with agent judgment.
SkillDFreshness: D★ 9Claude Code +9 - 0.470score
grape
Jordan Godau
AI-enabled, deterministic codebase search.
SkillDFreshness: D★ 9Claude Code +9 - 0.470score
md-review
Jordan Godau
Agent review for markdown quality, clarity, and structural integrity.
SkillDFreshness: D★ 9Claude Code +9
Cite this page
doctor skill. Agent Mart. https://agentmart.dev/skills/jordangunn-doctor (last updated 2026-10-24)