/voice-extract
Path to directory containing writing samples (.md/.txt)
$ npx -y skills add athola/claude-night-market --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/voice-extract
Context preview
What this command does when you run it.
Path to directory containing writing samples (.md/.txt)
Command definition
voice-extract.mdname: voice-extract
description: Extract your writing voice from samples into a reusable profile
arguments:
- name: profile-name
description: Name for the voice profile (e.g., "personal", "work")
required: true
- name: samples-dir
description: Path to directory containing writing samples (.md/.txt)
required: false/voice-extract Command
Extract a voice profile from writing samples using SICO comparative analysis.
Usage
# From a directory of samples /voice-extract myvoice --samples-dir ~/writing-samples/ # Interactive mode (paste samples one at a time) /voice-extract myvoice
What This Does
1. Collects writing samples (directory or interactive paste) 2. Anonymizes samples (strips context labels) 3. Generates Claude's baseline output on matched topics 4. Runs SICO Pass 1 (broad comparative extraction) 5. Runs Pass 2 (pressure test for specificity) 6. Creates voice profile at ~/.claude/voice-profiles/{name}/ 7. Generates default register
After Extraction
- Review the extraction: `cat ~/.claude/voice-profiles/{name}/extraction.md`
- Generate in voice: `/voice-generate {name}`
- Add more samples later: `/voice-extract {name} --add`
Skill Invocation
Skill(scribe:voice-extract)
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.
Other commands on claude-night-market.
- /aggregate-logs
Generate LEARNINGS.md from skill execution logs.
Open command - /analyze-skill
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Open command - /bulletproof-skill
Harden skills against rationalization and bypass behaviors
Open command - /context-report
Generate context optimization report for skill directories
Open command - /create-command
Create slash commands with brainstorming and best practices
Open command - /create-hook
Create hooks with brainstorming and security-first design
Open command

