voice-extract
Voice Extraction Skill
Extract a user's writing voice through SICO comparative analysis.
Method: Comparative Feature Extraction
Rather than measuring surface metrics, this skill uses SICO Phase 1: feed the model user writing samples alongside its own default output on the same topics. The model describes what the user does differently. This produces voice descriptions that encode implicit structural patterns no metrics can capture.
Key Principles (from research)
-
Anonymize samples: Label as "Sample 1", "Sample 2", etc. Context labels cause the extractor to anchor on content rather than reading a unified voice.
-
Variety over volume: 10 samples across different topics
More from athola/claude-night-market
project-planning
Turn a specification into a phased implementation plan with dependency ordering.
126code-quality-principles
KISS, YAGNI, and SOLID code quality principles for clean code, reducing complexity and preventing over-engineering.
94project-brainstorming
Guide project ideation via Socratic questioning to generate project briefs.
92doc-generator
Generate or remediate documentation with human-quality writing and style.
81rigorous-reasoning
Anti-sycophancy reasoning checklist.
79project-specification
Transform project briefs into testable specifications with user stories, acceptance criteria, and measurable outcomes.
78