mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
boshu
4a7c6a0701
Add an --all-docs mode to check-doc-skill-refs.sh that scans the union of the pinned doctrine files PLUS the full LIVE docs/** set (scripts/lib/docs-scope.sh), ratcheted by a new filename-pinned shrink baseline (scripts/.docs-skill-refs-baseline). Two-way ratchet: a non-baselined live doc with a dead `/skill` ref FAILS; a baselined file that no longer offends FAILS demanding a prune. Detection stays slash-syntax + headings only (never bare skill names). Default (no-flag) behavior is byte-identical. docs/SKILL-ROUTER.md (the curated router) is covered by --all-docs (a live docs/** file, never baselined) so a dead ref there FAILS strict, without perturbing the byte-identical default doc count. seed.go docs.skill-refs row: Match widened to docs/** + the baseline + the lib; Args set to [--all-docs --strict]. Burn-down (long-tail only): repointed retired `/retro`->/post-mortem, `/vibe`->/validate, `/ratchet`->/flywheel, `/research-multi`->/research, `/implement-wave`->/crank, and reworded the retired `/dream` across 13 docs/levels + docs/workflows + docs/philosophy pages, then pruned them from the baseline (91 -> 78 offenders). Owner-locked pages (comparisons/getting-started/positioning) stay baselined. Bats twin tests/scripts/check-doc-skill-refs-all-docs.bats covers all the modes.
2.2 KiB
2.2 KiB
name, description, estimated_time, phases
| name | description | estimated_time | phases |
|---|---|---|---|
| knowledge-synthesis | Extract and synthesize knowledge from multiple sources | 30-60 minutes | 3 |
Knowledge Synthesis Workflow
Purpose: Combine knowledge from code, docs, history, and patterns
When to use:
- Onboarding (understand new codebase)
- Documentation (create comprehensive guides)
- Pattern extraction (learn from multiple implementations)
- Architecture review (understand system design)
Token budget: 40-60k tokens (single session)
Workflow Phases
Phase 1: Gather (15-20% context)
↓
Phase 2: Synthesize (10-15% context)
↓
Phase 3: Document (5-10% context)
Phase 1: Gather
Goal: Collect knowledge from multiple sources
Commands:
/research-multi "[topic]"
# Launches 3 agents in parallel:
# - code-explorer: Code structure
# - doc-explorer: Documentation
# - history-explorer: Git history
Output: Combined research from 3 perspectives
Phase 2: Synthesize
Goal: Connect insights, identify patterns
Activities:
- Cross-reference findings
- Extract common patterns
- Identify best practices
- Note gaps or inconsistencies
Output: Synthesized understanding
Phase 3: Document
Goal: Capture knowledge for future use
Commands:
/retro --quick [topic]
# Creates pattern documentation
# Updates knowledge base
Output: Documentation + pattern catalog
Example: Understand Auth System
Read CLAUDE.md
/research-multi "authentication and authorization system"
# Agent 1 (Code):
# - auth/ directory structure
# - JWT validation in middleware
# - Session management in handlers
# Agent 2 (Docs):
# - docs/auth-design.md explains OAuth2 flow
# - examples/auth-example/ shows usage
# Agent 3 (History):
# - Added in commit abc123 (2024-03)
# - Refactored in commit def456 (2024-08)
# - Pattern: Standard OAuth2 + custom claims
# Synthesis:
# Authentication: OAuth2 with JWT
# Authorization: Role-based (admin, user, guest)
# Pattern: Middleware-based validation
# Best practice: Separate auth concerns from business logic
/retro --quick auth-system-knowledge
# Documented for future reference
Start knowledge synthesis with: Read CLAUDE.md + /research