debugging-agent
Self-Improving Agent that monitors all other agent skills, analyzes their logs, detects issues, and proposes improvements. AUTO-TRIGGERS: - Every 30 minutes (scheduled) - When error rate > 5% (any agent) - When 3+ recurring errors in 24h (same error type) - When performance degrades > 2x baseline
npx skills add majiayu000/claude-skill-registry --skill debugging-agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Debugging Agent **Self-Improving Agent System의 핵심 컴포넌트** 다른 모든 agent의 로그를 분석하여 문제를 발견하고 개선안을 제안합니다. --- ## 📋 Core Workflow ### 1. Log Collection (로그 수집) ```bash python backend/ai/skills/system/debugging-agent/scripts/log_reader.py \ --days 1 \ --categories system,war-room,analysis ``` **수집 대상:** - `backend/ai/skills/logs/*/*/execution-*.jsonl` - `backend/ai/skills/logs/*/*/errors-*.jsonl` - `backend/ai/skills/logs/*/*/performance-*.jsonl` **Output:** ```json { "agents": ["signal-consolidation", "war-room-debate", ...], "total_executions": 50, "total_errors": 3, "time_range": "2025-12-25 to 2025-12-26" } ``` --- ### 2. Pattern Detection (패턴 감지) ```bash python backend/ai/skills/system/debugging-agent/scripts/pattern_detector.py \ --input logs_summary.json \ --output patterns.json ``` **감지 패턴:** #### A. Recurring Errors (반복 에러) - **조건**: 동일한 error type이 24시간 내 3회 이상 - **예시**: `TypeError: missing required positional argument` (3회) - **우선순위**: HIGH #### B. Performance Degradation (성능 저하) - **조건**: duration_ms가 baseline 대비 2배 이상 - **예시**: 평균 1000ms → 최근 2500ms - **우선순위**: MEDIUM #### C. High Error Rate (높은 에러율) - **조건**: error rate > 5% - **예시**: 50 executions, 4 errors = 8% - **우선순위*
- 📋 Core Workflow
- 1. Log Collection (로그 수집)
- 2. Pattern Detection (패턴 감지)
- 3. Context Synthesis (맥락 통합)
- 4. Improvement Proposal (개선안 생성)
- 🎯 Confidence Scoring (5 Metrics)
- 🔄 Usage Examples
- Manual Trigger
- Scheduled Execution (via orchestrator)
- 📁 Output Structure
- ⚠️ Important Notes
- 🚀 Next Steps
python backend/ai/skills/system/debugging-agent/scripts/log_reader.py \ python backend/ai/skills/system/debugging-agent/scripts/pattern_detector.py \ Read related skills cat backend/ai/skills/war-room/war-room-debate/SKILL.md cat backend/api/war_room_router.py python backend/ai/skills/system/debugging-agent/scripts/improvement_proposer.py \ Analyze recent logs python backend/ai/skills/system/debugging-agent/scripts/log_reader.py --days 1 Detect patterns python backend/ai/skills/system/debugging-agent/scripts/pattern_detector.py
What does the debugging-agent skill do?
Self-Improving Agent that monitors all other agent skills, analyzes their logs, detects issues, and proposes improvements. AUTO-TRIGGERS: - Every 30 minutes (scheduled) - When error rate > 5% (any agent) - When 3+ recurring errors in 24h (same error type) - When performance degrades > 2x baseline
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill debugging-agent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.