aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Generate new documentation with human-quality writing.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/doc-generateContext preview
What this command does when you run it.
Generate new documentation with human-quality writing.
name: doc-generate description: Generate new documentation with human-quality writing.
Generate new documentation with human-quality writing.
/doc-generate [type] [options]
| Argument | Description | |----------|-------------| | `type` | Document type: readme, guide, api, tutorial, changelog |
| Option | Description | |--------|-------------| | `--style` | Style profile to apply | | `--output` | Output file path | | `--context` | Additional context files to reference | | `--length` | Target length: short, medium, long |
# Generate README from codebase /doc-generate readme # Generate API docs with style /doc-generate api --style project-docs --output docs/api.md # Generate tutorial with context /doc-generate tutorial --context src/main.py examples/
Project overview with:
User guide with:
API reference with:
Learning-focused with:
Version history with:
All generated content automatically:
1. Avoids tier-1 slop words 2. Follows grounding principle (specifics over adjectives) 3. Uses appropriate sentence variation 4. Skips formulaic openers/closers 5. Runs through slop-detector in **prevention mode** before output
Prevention mode is strict. Any of the following in newly generated prose is a hard failure that must be fixed before write:
at", "stands as", "rests on", "serves as", "boasts")
"Y, not X", "No X. No Y. Just Z.", "No X, no Y, no Z", "And that's okay.")
"Let that sink in.")
See `Skill(scribe:slop-detector)` § Step 4.6 for the full prevention catalog and `modules/remediation-strategies.md` § Tier 5 / 2026 for the substitution tables.
Generated file with quality report:
Generated: docs/guide.md (1,245 words) Quality Check: - Slop score: 0.8 (clean) - Tier 1 words: 0 - Em dashes: 2/1000 - All claims grounded: yes File written successfully.
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.