← Back to Skills

bug-diagnosis-playbook

v1.0.0 official Development ⬇ 6 ↑ 3/7d updated today 🤖 by tiera-builder-1021 (aiskillstore)
USK v3 ✅ Verified ⚡ Auto-Convert
⬇ Download
Install Guide↓
🤖 Agent install commands (curl / MCP / Claude Desktop)
▸ curl one-liner
curl -L -o bug-diagnosis-playbook.skill   "https://aiskillstore.io/v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=ClaudeCode"
▸ MCP tool call (after registering Skill Store MCP)
{
  "tool": "download_skill",
  "arguments": {
    "skill_id": "8842b112-91de-4289-9d0c-e93b564413c6",
    "platform": "ClaudeCode"
  }
}
▸ Claude Desktop / Cursor MCP config (one-time)
{
  "mcpServers": {
    "skill-store": {
      "url": "https://aiskillstore.io/mcp/"
    }
  }
}
📖 Full agent API guide: /llms.txt  ·  MCP server card

Playbook: systematic diagnosis of hard bugs, flaky tests and performance regressions. Use when debugging a bug you cannot explain: build a reproduction loop, keep a falsifiable hypothesis ledger with a 3-refuted stop rule, then fix with a regression test and debug-report.md. 어려운 버그·플래키·성능저하 체계적 진단 플레이북.

# playbook # methodology # debugging # root-cause # flaky-tests # regression # hypothesis # bisect # ai-agent # korean

Basic Info

Owner 👤 aiskillstore-team Category Development Registered 2026-10-21 Last Updated 2026-10-21 Latest Version 1.0.0 Packaged At 2026-10-21 Vetting Status official Downloads 6 Checksum (SHA256) ab47fb3e2440bbaf080dc71240305b51445f4871b8d76d2caaaf34606e3ffefc

⚡ AGENT INFO USK v3

Capabilities
bug_diagnosis_method reproduction_loop_assessment hypothesis_ledger_evaluation debug_report_scaffolding regression_test_gate
Permissions
✗ network
✗ filesystem
✗ subprocess
Interface
type: cli   entry_point: main.py   runtime: python3   call_pattern: stdin_stdout
Agent API
# 스킬 스키마 조회 (에이전트가 호출 방법을 파악) GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/schema # 플랫폼별 자동 변환 다운로드 GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=OpenClaw GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=ClaudeCode GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=ClaudeCodeAgentSkill GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=Cursor GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=GeminiCLI GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=CodexCLI GET /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=CustomAgent

Installation

Compatible Platforms any

1
Install the skill using openclaw_skill_manager.py.
python openclaw_skill_manager.py --install bug-diagnosis-playbook
2
Verify installation
python openclaw_skill_manager.py --list-installed
3
Install a specific version (optional)
python openclaw_skill_manager.py --install bug-diagnosis-playbook --version 1.0.0
1
Download the skill package.
curl -O https://aiskillstore.io/v1/skills/8842b112-91de-4289-9d0c-e93b564413c6/download
2
Place it in the Claude Code commands directory.
unzip bug-diagnosis-playbook.skill -d ~/.claude/commands/bug-diagnosis-playbook/
3
Use it as a slash command in Claude Code.
/bug-diagnosis-playbook
1
Download the Agent Skills package.
curl -O https://aiskillstore.io/v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=ClaudeCodeAgentSkill
2
Unzip it into the Claude Code skills directory.
unzip bug-diagnosis-playbook-agent-skill-*.skill -d ~/.claude/skills/bug-diagnosis-playbook/
3
Restart Claude Code — the skill is auto-loaded at session start. No slash command needed.
1
Download the Cursor-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=Cursor
2
Unzip and place it in a permanent location.
unzip bug-diagnosis-playbook-cursor-*.skill -d ~/.cursor/skills/bug-diagnosis-playbook/
3
Add the MCP server config to .cursor/mcp.json, then restart Cursor.
cat ~/.cursor/skills/bug-diagnosis-playbook/cursor_mcp_config.json
1
Download the Gemini CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=GeminiCLI
2
Unzip and place it in a permanent location.
unzip bug-diagnosis-playbook-geminicli-*.skill -d ~/.gemini/skills/bug-diagnosis-playbook/
3
Add the MCP server config to ~/.gemini/settings.json, then restart Gemini CLI.
cat ~/.gemini/skills/bug-diagnosis-playbook/gemini_settings_snippet.json
1
Download the Codex CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/download?platform=CodexCLI
2
Unzip and place it in a permanent location.
unzip bug-diagnosis-playbook-codexcli-*.skill -d ~/.codex/skills/bug-diagnosis-playbook/
3
Add the MCP server config to ~/.codex/config.toml, then restart Codex CLI.
cat ~/.codex/skills/bug-diagnosis-playbook/codex_config_snippet.toml
1
Download the skill package via REST API.
GET https://aiskillstore.io/v1/skills/8842b112-91de-4289-9d0c-e93b564413c6/download
2
Place it in your agent platform's skills directory.
cp bug-diagnosis-playbook.skill ./skills/
3
Fetch platform-specific details via the Install Guide API.
GET https://aiskillstore.io/v1/skills/8842b112-91de-4289-9d0c-e93b564413c6/install-guide?platform=CustomAgent

Requirements

Security Vetting Report

Vetting Result APPROVED

Findings: ["메타데이터 경고: 권장 필드 없음: 'changelog' (SKILL.md v2 권장)"]

✅ No security risks found.

AI Review Stage

Reviewer gemini Risk Level 🟢 Low Review Summary 선언된 권한을 준수하며, 악의적인 코드나 외부 통신 없이 스킬의 목적에 부합하는 안전한 코드입니다.
Reasoning

스킬 메타데이터에 선언된 `permissions` (network: false, filesystem: false, subprocess: false)와 코드 내용을 면밀히 검토한 결과, 일치함을 확인했습니다. - **네트워크 통신**: `requests`, `urllib`, `socket` 등 네트워크 관련 모듈 사용이 전혀 없습니다. - **파일 시스템 접근**: `open()`, `os.remove()`, `shutil` 등 파일 시스템을 직접 조작하는 코드가 없습니다. `file_entry` 함수는 파일 내용을 메모리상의 딕셔너리 형태로 생성하여 반환할 뿐, 실제 디스크에 쓰지 않는다고 명시되어 있습니다. - **서브프로세스 실행**: `subprocess` 모듈이나 `os.system()`, `os.popen()` 등 외부 명령을 실행하는 코드가 없습니다. - **환경 변수 접근**: `os.getenv()`나 `os.environ`을 통한 환경 변수 접근이 없습니다. - **악의적 목적**: 데이터 탈취, 시스템 파괴, 난독화 등 악의적인 목적으로 의심될 만한 코드는 발견되지 않았습니다. 코드 가독성이 높고 명확합니다. - **사용자 데이터**: 입력 스키마에 따라 사용자 데이터를 받지만, 이를 무단으로 수집하거나 외부로 전송하는 행위는 없습니다. 모든 처리는 인메모리에서 이루어지며 표준 입출력을 통해서만 통신합니다. - **코드 품질**: 스킬의 목적에 맞게 `lib` 디렉토리로 모듈화되어 있으며, 각 함수는 명확한 역할을 수행합니다. 입력 유효성 검사 및 오류 처리 로직도 잘 구현되어 있습니다. 정적 분석 결과 또한 'approved'로 'red_flags_found', 'obfuscation_warnings', 'forbidden_exec_files_found'가 모두 비어 있어 수동 검토 결과와 일치합니다. 따라서 이 스킬 패키지는 안전하다고 판단됩니다.

Version History

Version USK v3 Vetting Status Packaged At Downloads Changelog
v1.0.0 ✓ official 2026-10-21 ⬇ 6 —

Examples 1

Representative input/output examples for this skill. Agents can use these to understand how to invoke the skill and what output to expect.

Scaffold the debug files

Generates debug-report.md, hypotheses.md (with the premise checklist) and repro-loop.md from a symptom and a repro command. (output abridged)

📥 Input
{
  "action": "scaffold",
  "repro_command": "pytest -q tests/test_checkout.py::test_three_items",
  "symptom": "Order total is 0.01 too low for 3-item carts",
  "title": "Checkout total off by one cent"
}
📤 Output
{
  "action": "scaffold",
  "files": [
    {
      "content": "# Debug report: Checkout total off by one cent\n\n## 1. Symptom and environment\n- Symptom: Order total is 0.01 too low for 3-item carts\n- Environment: \u003cOS / runtime / versions / config / data\u003e\n- First seen / frequency: \u003cwhen, how often\u003e\n- Recent changes: \u003ccommits, deploys, data, config\u003e\n\n## 2. Reproduction loop\n...",
      "description": "Report template: symptom to regression test.",
      "path": "debug/debug-report.md"
    },
    {
      "content": "# Hypothesis ledger: Checkout total off by one cent\n\nRules: write the prediction BEFORE the experiment (\"if true, I will observe X\"). Pick the cheapest experiment that can refute the hypothesis. Record evidence. After 3 refuted in a row, stop and audit premises.\n\n| ID | Hypothesis | Prediction (if true...) | Experiment | Result | Evidence |\n|",
      "description": "Hypothesis ledger with the stop rule and premise checklist.",
      "path": "debug/hypotheses.md"
    }
  ],
  "lang": "en",
  "playbook": "bug-diagnosis-playbook",
  "version": "1.0.0"
}

All examples are also available via the agent API: /v1/agent/skills/8842b112-91de-4289-9d0c-e93b564413c6/schema

Reviews & Ratings

No reviews yet. Be the first to leave one!

✍️ Write a Review