aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Extract writing style from exemplar text to create a reusable style profile.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/style-learnContext preview
What this command does when you run it.
Extract writing style from exemplar text to create a reusable style profile.
name: style-learn description: Extract writing style from exemplar text to create a reusable style profile.
Extract writing style from exemplar text to create a style profile.
/style-learn [sources...] [options]
| Argument | Description | |----------|-------------| | `sources` | Files to analyze as style exemplars |
| Option | Description | |--------|-------------| | `--name` | Profile name (default: "default") | | `--output` | Output location (default: .scribe/style-profile.yaml) | | `--merge` | Merge with existing profile | | `--interactive` | Select exemplar passages interactively |
# Learn from README /style-learn README.md # Learn from multiple files /style-learn docs/*.md --name project-docs # Interactive exemplar selection /style-learn blog-posts/ --interactive
Creates a style profile with:
# Style Profile: project-docs
# Generated: 2024-01-15
# Sources: README.md, docs/guide.md
voice:
tone: professional
perspective: first-person-plural
formality: neutral
vocabulary:
average_word_length: 5.2
jargon_level: moderate
contractions: frequent
preferred_terms:
- "use" over "utilize"
avoided_terms:
- delve
- leverage
sentences:
average_length: 16
length_variance: high
exemplars:
- label: "Technical explanation"
text: |
The cache sits between API and database...1. Collect source files 2. Extract quantitative metrics 3. Select representative passages 4. Generate profile YAML 5. Validate with sample generation
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.