Calibrate Voice — Development skill for Claude Code
Run an empirical calibration round: regenerate the 8-brief matrix, measure, collect owner ratings, codify every reaction into a logged pack change.
How to install Calibrate Voice
Installs to ~/.claude/skills/solanabr-writer-style-skill-calibrate-voice/SKILL.md
mkdir -p ~/.claude/skills/solanabr-writer-style-skill-calibrate-voice && curl -fsSL https://raw.githubusercontent.com/solanabr/writer-style-skill/HEAD/commands/calibrate-voice.md -o ~/.claude/skills/solanabr-writer-style-skill-calibrate-voice/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Calibrate Voice does
description: "Run an empirical calibration round: regenerate the 8-brief matrix, measure, collect owner ratings, codify every reaction into a logged pack change"
Run one calibration round of the writer-style pack against the fixed test matrix. The loop: **measure → owner rates → codify → apply → re-measure.** Protocol details: `the calibration protocol (local, gitignored: profiles/kaue/calibration/)`; matrix + briefs: `$SKILL/testbed/MATRIX.md`; ledger: `profiles/kaue/calibration/ROUNDS
Alternatives in Development
- Swarm Collect — Collect and synthesize results from a completed swarm 508 ★
- Engage.Crash — Crash → root cause → reachability → empirical exploitability verdict (native bugs) 348 ★
- PokeTokenBar — Use your tokens to raise, evolve, and collect Pokémon 345 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
TS Calibrate
TS ta-coordinator calibration mode — grading norming session
Spark
Spark — divergent thinking protocol for ideation sessions. Ping-pong chain reaction with trace-back.
Codify
Load phase 05 (codify) for the current workspace. Update existing agents and skills with new knowledge.
Corrections
Review captured prose-correction candidates and codify approved ones into the project CLAUDE.md word-level dis
Search The Web
Search the web from your coding agent. Type /s and a query, get 3 synthesized mini-briefings with verdicts, ra
Agentic Eval
Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-ti
Related Agents
Foundry Voss
Use this agent for agent quality calibration, SKILL.md creation and refinement, agent output evaluation, crew
Football Forecaster
Expert statistician for football (soccer) match & tournament forecasting. Knows the literature (Dixon-Coles, b
Lead Consistency
Cross-unit consistency pass and deduction-matrix arbitration for an audit-style evaluation run. Runs ONCE per