aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Update project documentation with consolidation, debloating, AI slop detection, capabilities sync, and accuracy verification.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/update-docsContext preview
What this command does when you run it.
Update project documentation with consolidation, debloating, AI slop detection, capabilities sync, and accuracy verification.
description: Update project documentation with consolidation, debloating, AI slop detection, capabilities sync, and accuracy verification. usage: /update-docs [--skip-consolidation] [--skip-slop] [--skip-capabilities] [--strict] [--book-style]
Update documentation files based on recent changes while enforcing project writing guidelines. Includes consolidation detection, AI slop detection, directory-specific style rules, and accuracy verification.
This command now addresses: 1. **Consolidation**: Detects redundant/bloated docs (like /merge-docs) 2. **Debloating**: Enforces directory-specific line limits and style rules 3. **AI Slop Detection**: Uses `scribe:slop-detector` to find AI-generated content markers 4. **Capabilities Sync**: Ensures plugin.json registrations are reflected in reference docs 5. **Accuracy**: Validates version numbers and counts against codebase 6. **LSP Integration (2.0.74+)**: **Default approach** for documentation verification
Load the required skills in order:
1. Run `Skill(sanctum:git-workspace-review)` to capture the change context 2. Run `Skill(sanctum:doc-updates)` and follow the enhanced checklist:
For enhanced writing quality, the workflow checks for external style guides:
# Primary: Use elements-of-style if installed (superpowers marketplace) Skill(elements-of-style:writing-clearly-and-concisely) # Fallback: Use scribe:doc-generator principles Skill(scribe:doc-generator) --remediate
If slop score exceeds threshold, use the interactive editor:
Agent(scribe:doc-editor) --target [file]
| Location | Style | Max File | Max Paragraph | |----------|-------|----------|---------------| | `docs/` | Strict reference | 500 lines | 4 sentences | | `book/` | Technical book | 1000 lines | 8 sentences | | `wiki/` | Wiki reference | 500 lines | 4 sentences | | `plugins/*/README.md` | Plugin summary | 300 lines | 4 sentences | | Other | Default strict | 500 lines | 4 sentences |
The `book/` directory has more leeway because it follows technical book format with longer explanations and tutorials. Plugin READMEs should be concise summaries.
Phase 2.5 scans for:
User approval is required before any:
Phase 5 validates documentation claims:
**LSP-Enhanced Verification (2.0.74+)**: When `ENABLE_LSP_TOOL=1` is set:
Warnings are non-blocking; user decides whether to fix.
# Standard documentation update /update-docs # Quick update without consolidation check /update-docs --skip-consolidation # Skip AI slop detection (faster, less thorough) /update-docs --skip-slop # Strict mode: treat all warnings as errors /update-docs --strict # Apply lenient rules everywhere (for book-like docs) /update-docs --book-style # Full cleanup with slop remediation /update-docs && /slop-scan docs/ --fix # Skip capabilities sync (faster for non-plugin repos) /update-docs --skip-capabilities
If a skill cannot be loaded, follow these steps:
pwd && git status -sb && git diff --stat
# docs/ - strict (500 lines)
find docs/ -name '*.md' -exec wc -l {} \; 2>/dev/null | awk '$1 > 500'
# book/ - lenient (1000 lines)
find book/ -name '*.md' -exec wc -l {} \; 2>/dev/null | awk '$1 > 1000'
# wiki/ - strict (500 lines)
find wiki/ -name '*.md' -exec wc -l {} \; 2>/dev/null | awk '$1 > 500'
# Plugin READMEs - summary (300 lines)
for f in plugins/*/README.md; do
[ -f "$f" ] && lines=$(wc -l < "$f") && [ "$lines" -gt 300 ] && echo "$lines $f"
donefor p in plugins/*/.claude-plugin/plugin.json; do jq -r '"\(.name): \(.version)"' "$p" 2>/dev/null done
When Phase 2.5 runs, you'll see a table of detected candidates:
## Phase 2.5: Consolidation Opportunities ### Untracked Reports (merge or delete) | File | Score | Markers | Recommendation | |------|-------|---------|----------------| | API_REVIEW_REPORT.md | 6 | Executive Summary, Findings | Merge to docs/api-overvie
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.