スキル一覧に戻る
JordanGunn

doctor

by JordanGunn

[DEPRECATED] Collection of agent skills (mostly) targeted at preventing typical issues that surface during agentic programming sessions.

6🍴 1📅 2026年1月13日
GitHubで見るManusで実行

SKILL.md


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. metadata: author: Jordan Godau version: 0.1.0

skillset: name: doctor schema_version: 1 skills: - doctor-intake - doctor-triage - doctor-exam - doctor-treatment

resources:
  root: .resources
  assets:
    - INTAKE_NOTE.md
    - TRIAGE_REPORT.md
    - EXAM_NOTE.md
    - TREATMENT_NOTE.md
  scripts: []
  references:
    - ONTOLOGY.md
    - PHILOSOPHY.md
    - OPERATING_RULES.md

pipelines:
  # Full diagnostic sequence
  default:
    - doctor-intake
    - doctor-triage
    - doctor-exam
    - doctor-treatment

  # Individual skills can run standalone
  allowed:
    - [doctor-intake]
    - [doctor-triage]
    - [doctor-exam]
    - [doctor-treatment]
    # Intake + Triage (common starting point)
    - [doctor-intake, doctor-triage]
    # Triage + Exam (when intake already exists)
    - [doctor-triage, doctor-exam]
    # Exam + Treatment (when triage already exists)
    - [doctor-exam, doctor-treatment]
    # Full protocol
    - [doctor-intake, doctor-triage, doctor-exam, doctor-treatment]

requires: []

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

SkillPurposeOutput
doctor-intakeConvert user's description into clinically precise intake noteIntake Note
doctor-triageBreadth-first hypothesis surfacing and prioritizationTriage Report
doctor-examFocused evidence gathering on one suspect areaExam Note
doctor-treatmentDiagnosis estimate + proposed treatment optionsTreatment 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.

スコア

総合スコア

70/100

リポジトリの品質指標に基づく評価

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

レビュー

💬

レビュー機能は近日公開予定です