d-symptom
について
d-symptomスキルは、観察可能な動作と仮定を区別するための明確化質問を通じて、開発者がバグの症状を正確に定義・文書化することを支援します。期待される動作と実際の動作を再現可能かつ明確に記述することに焦点を当て、正しい診断を保証します。このスキルは最終的に確認された症状の文書を`./.gtd/debug/current/SYMPTOM.md`に出力します。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/d-symptomこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Core responsibilities:
- Listen to user's symptom description
- Ask clarifying questions to make symptoms precise
- Document expected vs actual behavior
- Get explicit confirmation before documenting </role>
Flow: Listen → Clarify → Mirror → Confirm → Document </objective>
<context> **Output:**./.gtd/debug/current/SYMPTOM.md</context>
Precision Over Speed
A vague symptom leads to wrong diagnosis. Take time to clarify.
Observable vs Interpretation
Focus on what can be observed, not assumptions about cause:
- ✓ "API returns 500 when posting to /users"
- ✗ "Database connection is broken"
Reproducibility
If you can't reproduce it, you can't verify the fix.
</philosophy> <process>1. Listen to User
User will describe the symptom. Let them finish.
2. Clarify Through Questions
Ask questions to make the symptom precise:
-
What is the expected behavior?
- What should happen?
-
What is the actual behavior?
- What happens instead?
- Error messages? Wrong output? Nothing happens?
-
How to reproduce?
- Exact steps to trigger the symptom
- Required conditions or data
-
When does it happen?
- Always? Sometimes? Under what conditions?
-
Environment/Context:
- Which environment? (dev, staging, prod)
- Recent changes?
- Specific data or user?
Keep asking until you can describe the symptom precisely.
3. Mirror Phase
Summarize your understanding:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GTD:DEBUG ► CONFIRMING SYMPTOM
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
**Expected Behavior:**
{What should happen}
**Actual Behavior:**
{What happens instead}
**Reproduction Steps:**
1. {step 1}
2. {step 2}
...
**Conditions:**
- {condition 1}
- {condition 2}
**Environment:**
{Environment details}
─────────────────────────────────────────────────────
Is this correct? (yes/no/clarify)
Wait for explicit confirmation.
4. Document SYMPTOM.md
mkdir -p ./.gtd/debug/current
Write to ./.gtd/debug/current/SYMPTOM.md:
# Bug Symptom
**Reported:** {date}
**Status:** CONFIRMED
## Expected Behavior
{What should happen}
## Actual Behavior
{What happens instead}
## Reproduction Steps
1. {step 1}
2. {step 2}
...
## Conditions
- {condition 1}
- {condition 2}
## Environment
- **Environment:** {dev/staging/prod}
- **Version/Commit:** {if known}
- **Recent Changes:** {if any}
## Additional Context
{Any other relevant information}
</process>
<offer_next>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GTD:DEBUG ► SYMPTOM DOCUMENTED ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Symptom documented: ./.gtd/debug/current/SYMPTOM.md
─────────────────────────────────────────────────────
▶ Next Up
/d-inspect — analyze code and form hypotheses
─────────────────────────────────────────────────────
</offer_next>
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
llamaindex
メタLlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.
canvas-design
メタThe canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.
