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.
2.5 KiB
2.5 KiB
name, description, estimated_time, phases
| name | description | estimated_time | phases |
|---|---|---|---|
| continuous-improvement | Ongoing system optimization and pattern refinement | Ongoing (periodic) | 4 |
Continuous Improvement Workflow
Purpose: Systematically improve system quality over time
When to use:
- Weekly/monthly reviews (extract learnings)
- After major milestones (retrospective)
- Pattern refinement (improve reusable patterns)
- Technical debt reduction (systematic cleanup)
Token budget: 30-50k tokens per cycle
Workflow Phases
Phase 1: Review (10-15% context)
↓
Phase 2: Identify (5-10% context)
↓
Phase 3: Prioritize (5-10% context)
↓
Phase 4: Improve (10-15% context)
Phase 1: Review
Goal: Assess recent work
Commands:
/retro --retrospective --since "30 days ago"
Activities:
- Review git commits
- Analyze patterns used
- Identify repeated problems
- Note what worked well
Output: Review summary
Phase 2: Identify
Goal: Find improvement opportunities
Activities:
- Code quality issues
- Documentation gaps
- Process inefficiencies
- Pattern opportunities
Output: Improvement candidates list
Phase 3: Prioritize
Goal: Rank by impact and effort
Matrix:
High Impact, Low Effort → DO FIRST
High Impact, High Effort → PLAN
Low Impact, Low Effort → MAYBE
Low Impact, High Effort → SKIP
Output: Prioritized improvement backlog
Phase 4: Improve
Goal: Execute improvements
Commands:
# For each improvement:
/plan [improvement]
/implement [improvement]-plan
/vibe recent
/retro --quick [improvement]
Output: Improved system + new patterns
Example: Monthly Improvement Cycle
# Phase 1: Review
/retro --retrospective --since "2025-10-01"
# Findings:
# - 15 commits reviewed
# - 3 patterns emerged (used 5+ times each)
# - 2 repeated issues (test failures, linting)
# Phase 2: Identify
# Opportunities:
# 1. Extract 3 patterns to pattern catalog
# 2. Fix recurring test flakiness
# 3. Add pre-commit hook for linting
# Phase 3: Prioritize
# Priority 1: Pre-commit hook (high impact, low effort)
# Priority 2: Fix test flakiness (high impact, medium effort)
# Priority 3: Extract patterns (medium impact, low effort)
# Phase 4: Improve
/plan pre-commit-hook
/implement pre-commit-hook-plan
/vibe recent
/retro --quick pre-commit-improvement
# Result: 90% reduction in linting issues
Start continuous improvement with: /post-mortem --retrospective