aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Enable learning mode (capture snapshots)
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/voice-generateContext preview
What this command does when you run it.
Enable learning mode (capture snapshots)
name: voice-generate
description: Generate text in your extracted writing voice
arguments:
- name: profile-name
description: Name of the voice profile to use
required: true
- name: register
description: Which register to use (default, casual, technical, etc.)
required: false
default: default
- name: --review
description: Run dual review agents after generation
required: false
default: "true"
- name: --learn
description: Enable learning mode (capture snapshots)
required: false
default: "true"Generate text in a trained writing voice.
# Generate with default register, review enabled /voice-generate myvoice # Use specific register, skip review /voice-generate myvoice --register casual --review false # Generate without learning snapshots /voice-generate myvoice --learn false
1. Loads voice profile and selected register 2. Asks for source material (notes, topic, outline) 3. Frames source material as "raw notes to think through" 4. Generates text using Opus with full voice features 5. Auto-fixes hard failures (banned phrases, em dashes) 6. Dispatches prose and craft review agents (if --review) 7. Presents advisory tables for user decisions 8. Saves snapshots (if --learn)
Provide your source material when prompted. Best results when framed as rough notes or ideas you're thinking through. The skill automatically reframes input as raw notes unless you explicitly request otherwise.
Skill(scribe:voice-generate)
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.