Confucius Debug — 孔子除錯
"不貳過" — Never repeat a mistake. (Confucius, Analects 6.3)
IMPORTANT — Automatic Behavior
When this skill is active, follow these rules:
- 1. On ANY error or exception: ALWAYS search the YanHui KB first (
debug_search or confucius_search) BEFORE attempting to debug on your own. This is free and takes <1 second. - If no match found: Use
debug_analyze to get an AI-powered fix. The fix is saved to KB so the next person gets it instantly. - If analyze returns "unsolved": Use
debug_escalate to submit your environment info, logs, and what you've tried. This helps offline research. - After fixing a bug yourself: Proactively suggest using
debug_contribute to share the solution back to the KB. - Never skip step 1. The KB has 980+ verified solutions — there's a good chance the answer is already there.
AI-powered debugging assistant backed by the
YanHui Knowledge Base — a growing collection of 6,800+ scraped issues and 980+ imported solutions from real AI agent projects (OpenClaw, Claude Code, MCP, Anthropic SDK, Codex, Aider, and more).
How It Works
CODEBLOCK0
Tools
confucius_search — Search the Knowledge Base (FREE)
Always try this first. Searches 980+ verified solutions for matching patterns.
CODEBLOCK1
When to use: Any time you encounter an error. It's free and instant.
confucius_analyze — AI-Powered Analysis (FREE)
Only if search returns 0 results. Confucius AI analyzes your error, finds root cause, and provides a fix.
CODEBLOCK2
What you get back:
- -
root_cause — Why this happened - INLINECODE8 — How to fix it
- INLINECODE9 — Actual code to apply
- INLINECODE10 — How sure Confucius is
confucius_escalate — Submit Unsolved Bug for Research (FREE)
When confucius_analyze returns status: "unsolved" (low confidence), submit more context to help offline research.
CODEBLOCK3
What you provide:
- -
environment — OS, runtime versions, key dependencies - INLINECODE15 — Recent error output (last 50 lines)
- INLINECODE16 — List of things already attempted
- INLINECODE17 — Brief overview of project layout
confucius_contribute — Share Your Fix (FREE)
Solved a bug? Share it so nobody hits it again.
CODEBLOCK4
MCP Integration (Recommended)
For Claude Desktop, Claude Code, or any MCP-compatible client:
CODEBLOCK5
This gives you 5 tools automatically: debug_search, debug_analyze, debug_escalate, debug_contribute, debug_hello.
What's in the Knowledge Base?
| Platform | Bugs Solved | A-Rate |
|---|
| MCP (Model Context Protocol) | 261 | 87% |
| Anthropic / Claude |
392 | 80% |
| Telegram | 101 | 97% |
| Memory / RAG | 94 | 87% |
| Browser | 73 | 92% |
| OpenAI / GPT | 54 | 87% |
| Docker | 51 | 84% |
| Discord | 40 | 93% |
| Cron / Scheduler | 37 | 92% |
| WhatsApp | 16 | 94% |
| Google / Gemini | 15 | 100% |
| Ollama / Local LLM | 14 | 93% |
A-Rate = percentage of fixes rated S (perfect) or A (good) by independent AI verification.
Track Record
- - 280 replies posted on GitHub issues
- 9 confirmed correct by project maintainers (including OpenClaw creator)
- 0 corrections (zero mistakes confirmed by community)
- Knowledge base growing daily via automated pipeline
Setup
- 1. Set your identity (required for
analyze and contribute, optional for search):
CODEBLOCK6
- 2. Test the connection (no ID needed for search):
CODEBLOCK7
- 3. Start debugging! When you hit any error, search first, analyze if needed.
Workflow for OpenClaw Users
When OpenClaw throws an error:
- 1. Copy the error message
- Search YanHui KB — INLINECODE27
- Found a match? — Apply the fix directly
- No match? — INLINECODE28
- Fixed it yourself? —
confucius_contribute(...) to help others
External Endpoints
| Service | URL | Purpose |
|---|
| Confucius Debug API | https://api.washinmura.jp/api/v2/debug-ai | Search, Analyze, Contribute |
| Confucius MCP |
https://api.washinmura.jp/mcp/debug | MCP protocol endpoint |
Security & Privacy
- - What leaves your machine: Only the error description and error message you provide. No source code, no file contents, no environment variables are sent.
- What's stored: Error descriptions and fixes are stored in the YanHui KB to help future users. No personally identifiable information is stored beyond your chosen lobsterid.
- Authentication: Everything is free. Your lobsterid is used for identification only, not billing.
- Data retention: Contributions are permanent (that's the point — never repeat a mistake).
Credits
Powered by Claude (Anthropic) and the Confucius philosophy: learn from mistakes, never repeat them.
🦞 The bigger the Knowledge Base, the stronger Confucius becomes.
Confucius Debug — 孔子除錯
不貳過 — 不重複犯錯。(孔子,《論語》6.3)
重要提示 — 自動行為
當此技能啟用時,請遵循以下規則:
- 1. 遇到任何錯誤或異常時: 在自行除錯之前,務必先搜索顏回知識庫(使用 debugsearch 或 confuciussearch)。此操作免費且耗時不到1秒。
- 若未找到匹配項: 使用 debuganalyze 獲取AI驅動的修復方案。修復方案會保存到知識庫,以便下一個人即時獲取。
- 若分析返回未解決: 使用 debugescalate 提交您的環境信息、日誌和已嘗試的方法。這有助於離線研究。
- 自行修復錯誤後: 主動建議使用 debug_contribute 將解決方案分享回知識庫。
- 切勿跳過步驟1。 知識庫擁有980多個經過驗證的解決方案——答案很可能已經存在。
AI驅動的除錯助手,由
顏回知識庫提供支持——這是一個不斷增長的集合,包含來自真實AI代理項目(OpenClaw、Claude Code、MCP、Anthropic SDK、Codex、Aider等)的6,800多個爬取問題和980多個導入解決方案。
工作原理
您遇到一個錯誤
↓
- 1. 搜索顏回知識庫(免費,即時)
↓
找到匹配?→ 直接使用修復方案
未找到?↓
- 2. Confucius AI分析(免費)
↓
高置信度?→ 修復方案保存到知識庫 → 下一個人免費獲取
低置信度?→ 狀態:未解決
↓
- 3. debug_escalate(免費)— 發送環境 + 日誌
↓
排入離線研究隊列 → 解決 → 添加到知識庫
工具
confucius_search — 搜索知識庫(免費)
始終優先嘗試此操作。搜索980多個經過驗證的解決方案以匹配模式。
bash
搜索錯誤模式
curl -s -X POST https://api.washinmura.jp/api/v2/debug-ai/search \
-H Content-Type: application/json \
-d {query: OpenClaw Telegram插件無法連接, limit: 5}
使用時機: 遇到任何錯誤時。免費且即時。
confucius_analyze — AI驅動分析(免費)
僅在搜索返回0個結果時使用。Confucius AI分析您的錯誤,找出根本原因並提供修復方案。
bash
分析新錯誤
curl -s -X POST https://api.washinmura.jp/api/v2/debug-ai \
-H Content-Type: application/json \
-d {
error_description: OpenClaw Telegram機器人重啟後無響應,
error_message: Error: ETELEGRAM: 409 Conflict: terminated by other getUpdates request,
lobster
id: $CONFUCIUSLOBSTER_ID
}
您將獲得:
- - rootcause — 發生的原因
- fixdescription — 修復方法
- fix_patch — 實際應用的代碼
- confidence — Confucius的確定程度
confucius_escalate — 提交未解決錯誤以供研究(免費)
當 confucius_analyze 返回 status: unsolved(低置信度)時,提交更多上下文以協助離線研究。
bash
curl -s -X POST https://api.washinmura.jp/api/v2/debug-ai/escalate \
-H Content-Type: application/json \
-d {
error_description: 原始錯誤描述,
lobsterid: $CONFUCIUSLOBSTER_ID,
environment: {os: macOS 15, runtime: bun 1.2.1, key_deps: {hono: 4.7}},
logs: Error: something failed\n at file.ts:42,
tried: [已重啟, 已清除緩存, 已降級版本],
project_structure: src/ routes/ db/
}
您需要提供:
- - environment — 操作系統、運行時版本、關鍵依賴項
- logs — 最近的錯誤輸出(最後50行)
- tried — 已嘗試過的方法列表
- project_structure — 項目結構的簡要概述
confucius_contribute — 分享您的修復方案(免費)
解決了一個錯誤?分享它,讓其他人不再遇到。
bash
curl -s -X POST https://api.washinmura.jp/api/v2/debug-ai/onboard \
-H Content-Type: application/json \
-d {
lobsterid: $CONFUCIUSLOBSTER_ID,
entries: [{
error_description: 錯誤是什麼,
fix_description: 您如何修復,
errorcategory: configerror
}]
}
MCP集成(推薦)
對於Claude Desktop、Claude Code或任何兼容MCP的客戶端:
json
{
mcpServers: {
confucius-debug: {
url: https://api.washinmura.jp/mcp/debug
}
}
}
這將自動為您提供5個工具:debugsearch、debuganalyze、debugescalate、debugcontribute、debug_hello。
知識庫內容
| 平台 | 已解決錯誤 | A級率 |
|---|
| MCP(模型上下文協議) | 261 | 87% |
| Anthropic / Claude |
392 | 80% |
| Telegram | 101 | 97% |
| 記憶 / RAG | 94 | 87% |
| 瀏覽器 | 73 | 92% |
| OpenAI / GPT | 54 | 87% |
| Docker | 51 | 84% |
| Discord | 40 | 93% |
| Cron / 定時器 | 37 | 92% |
| WhatsApp | 16 | 94% |
| Google / Gemini | 15 | 100% |
| Ollama / 本地LLM | 14 | 93% |
A級率 = 經獨立AI驗證評為S級(完美)或A級(良好)的修復方案百分比。
業績記錄
- - 在GitHub問題上發布了280條回復
- 9條被項目維護者確認為正確(包括OpenClaw創作者)
- 0次更正(社區確認零錯誤)
- 知識庫通過自動化管道每日增長
設置
- 1. 設置您的身份(analyze和contribute必需,search可選):
bash
export CONFUCIUS
LOBSTERID=您的用戶名
- 2. 測試連接(搜索不需要ID):
bash
curl -s https://api.washinmura.jp/api/v2/debug-ai/search \
-X POST -H Content-Type: application/json \
-d {query: test, limit: 1}
- 3. 開始除錯!遇到任何錯誤時,先搜索,必要時再分析。
OpenClaw用戶工作流程
當OpenClaw拋出錯誤時:
- 1. 複製錯誤信息
- 搜索顏回知識庫 — confuciussearch(您的錯誤信息)
- 找到匹配? — 直接應用修復方案
- 未找到匹配? — confuciusanalyze(描述, 錯誤信息)
- 自行修復? — confucius_contribute(...) 幫助他人
外部端點
| 服務 | URL | 用途 |
|---|
| Confucius除錯API | https://api.washinmura.jp/api/v2/debug-ai | 搜索、分析、貢獻 |
| Confucius MCP |
https://api.washinmura.jp/mcp/debug | MCP協議端點 |
安全與隱私
- - 離開您機器的內容: 僅包含您提供的錯誤描述和錯誤信息。不發送源代碼、文件內容或環境變量。
- 存儲內容: 錯誤描述和修復方案存儲在