knowledgelisted

# Knowledge Extraction & Documentation Sync Extracts knowledge from Amp threads and synchronizes project documentation. ## Pipeline ``` REQUEST → THREADS → TOPICS → CODE → DOCS ``` | Phase | Action | Tools | | ------------ | -------------------------- | ---------------------- | | 1. Discover | Find threads by query/time | `find_thread` | | 2. Extract | Parallel topic extraction | `Task` + `read_thread` | | 3. Verify | Ground topics in code | `gkg`, `finder` | | 4. Map | Find target docs | `Read`, `Grep` | | 5. Reconcile | Compare all sources | `Oracle` | | 6. Apply | Surgical updates | `edit_file`, `mermaid` | ## Phase 1: Discover Threads Start from user request: ```bash # "Document last 2 weeks" find_thread after:2w # "Summarize auth work" find_thread "authentication" # "What touched the SDK?" find_thread file:packages/sdk # Combined find_thread "refactor" after:1w file:packages/api ``` ## Phase 2: Extract Topics Spawn parallel `Task` agents (2-3 threads each): ``` Task prompt: "Read threads [T-xxx, T-yyy] using read_thread. Goal: 'Extract topics, decisions, changes' Return JSON: { 'topics': [{ 'name': 'topic name', 'threads': ['T-xxx'], 'summary': '1-2 sentences', 'decisions': ['...'], 'patterns': ['...'], 'changes': ['...'] }] }" ``` Collect outputs → Oracle synthesizes: ``` Oracle: "Cluster these ext