메뉴
Mine transcripts for knowledge - decisions, learnings, failures, patterns. Triggers: "forge insights", "mine transcripts", "extract knowledge".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | forge |
| description | Mine transcripts for knowledge - decisions, learnings, failures, patterns. Triggers: "forge insights", "mine transcripts", "extract knowledge". |
Typically runs automatically via SessionEnd hook.
Extract knowledge from session transcripts.
The SessionEnd hook runs:
ao forge transcript --last-session --queue --quiet
This queues the session for knowledge extraction.
Given /forge [path]:
With ao CLI:
# Mine recent sessions
ao forge --recent
# Mine specific transcript
ao forge transcript <path>
Without ao CLI: Look at recent conversation history and extract learnings manually.
Look for these patterns in the transcript:
| Type | Signals | Weight |
|---|---|---|
| Decision | "decided to", "chose", "went with" | 0.8 |
| Learning | "learned that", "discovered", "realized" | 0.9 |
| Failure | "failed because", "broke when", "didn't work" | 1.0 |
| Pattern | "always do X", "the trick is", "pattern:" | 0.7 |
Write to: .agents/forge/YYYY-MM-DD-forge.md
# Forged: YYYY-MM-DD
## Decisions
- [D1] <decision made>
- Source: <where in conversation>
- Confidence: <0.0-1.0>
## Learnings
- [L1] <what was learned>
- Source: <where in conversation>
- Confidence: <0.0-1.0>
## Failures
- [F1] <what failed and why>
- Source: <where in conversation>
- Confidence: <0.0-1.0>
## Patterns
- [P1] <reusable pattern>
- Source: <where in conversation>
- Confidence: <0.0-1.0>
ao forge index .agents/forge/YYYY-MM-DD-forge.md 2>/dev/null
Tell the user:
Forged candidates enter at Tier 0:
Transcript → /forge → .agents/forge/ (Tier 0)
↓
Human review or 2+ citations
↓
.agents/learnings/ (Tier 1)
This skill should be used when the user asks to "track issues", "create beads issue", "show blockers", "what's ready to work on", "beads routing", "prefix routing", "cross-rig beads", "BEADS_DIR", "two-level beads", "town vs rig beads", "slingable beads", or needs guidance on git-based issue tracking with the bd CLI.
Investigate suspected bugs with git archaeology and root cause analysis. Triggers: "bug", "broken", "doesn't work", "failing", "investigate bug".
Analyze code complexity and find refactor targets using radon/gocyclo. Triggers: "complexity", "analyze complexity", "find complex code", "refactor targets", "cyclomatic complexity", "code metrics".
Fully autonomous epic execution. Runs until ALL children are CLOSED. Level 1 uses /swarm (Task tool). Level 2 uses /spawn + Agent Mail for cross-session orchestration with Chiron help routing. NO human prompts, NO stopping.
This skill should be used when the user asks to "generate documentation", "validate docs", "check doc coverage", "find missing docs", "create code-map", "sync documentation", "update docs", or needs guidance on documentation generation and validation for any repository type. Triggers: doc, documentation, code-map, doc coverage, validate docs.
Extract decisions and learnings from Claude session transcripts. Triggers: "extract learnings", "process pending", SessionStart hook.