aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Consolidate ephemeral LLM-generated markdown into permanent documentation.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/merge-docsContext preview
What this command does when you run it.
Consolidate ephemeral LLM-generated markdown into permanent documentation.
description: Consolidate ephemeral LLM-generated markdown into permanent documentation. usage: /merge-docs [file...] [--scan-only] [--docs-dir PATH]
Consolidates ephemeral LLM-generated markdown files (reports, analyses, reviews) into permanent documentation.
# Scan and consolidate all detected candidates /merge-docs # Consolidate specific files /merge-docs API_REVIEW_REPORT.md REFACTORING_REPORT.md # Preview without executing /merge-docs --scan-only # Target a different docs directory /merge-docs --docs-dir plugins/abstract/docs/
Use the `sanctum:doc-consolidation` skill to orchestrate this workflow:
1. **Load the skill**: `Skill(sanctum:doc-consolidation)` 2. **Follow the two-phase workflow**:
If the user provides file paths, skip candidate detection and directly analyze those files:
python scripts/consolidation_planner.py analyze FILE1.md FILE2.md python scripts/consolidation_planner.py plan FILE1.md --docs-dir docs/
Scan the repository for all consolidation candidates:
python scripts/consolidation_planner.py scan --repo-path .
Then generate plans for each detected candidate.
The skill identifies files by:
Content is routed based on category:
| Category | Default Destination | |----------|---------------------| | Actionable Items | `docs/plans/YYYY-MM-DD-{topic}.md` | | Decisions Made | `docs/adr/NNNN-{date}-{topic}.md` | | Findings/Insights | Best-match existing doc | | Metrics/Baselines | `docs/benchmarks/` | | Migration Guides | `docs/migration-guide.md` | | API Changes | `CHANGELOG.md` or API docs | | **Redundant (delete)** | None - content already exists elsewhere |
Before merging, check if content is already covered in existing documentation:
# Search for similar content in existing docs rg "key topic phrase" docs/ book/ plugins/*/README.md # fallback: grep -r "key topic phrase" docs/ book/ plugins/*/README.md # Check if a command/skill doc already covers the content rg -l "topic" plugins/*/commands/*.md plugins/*/skills/*/SKILL.md # fallback: ls plugins/*/commands/*.md plugins/*/skills/*/SKILL.md | xargs grep -l "topic"
**When to delete instead of merge:**
**Recommendation format:**
| File | Action | Reason | |------|--------|--------| | PALACE_UNIFICATION.md | Delete | Content already in commands/palace.md | | API_NOTES.md | Merge | New insights not in api-overview.md |
This command invokes the `doc-consolidation` skill. For manual control:
# Direct script usage python plugins/sanctum/scripts/consolidation_planner.py scan python plugins/sanctum/scripts/consolidation_planner.py plan FILE.md
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.