Use when you want a per-claim evidence-tier audit on a text artifact before it ships — assign T1-T6 tiers to every load-bearing claim, surface calibration mismatches (high confidence on weak evidence, or honesty-theater under-claiming), and flag P11 (citation-as-decoration), P17 (pile-of-anecdotes-as-evidence), P54 (unverifiable single-source) patterns.
Install
npx skills add Avyayalaya/agent-council --skill evidence-calibration-reviewnpx skills add Avyayalaya/agent-council --skill evidence-calibration-review -a claude-code -gnpx skills add Avyayalaya/agent-council --skill evidence-calibration-review -a codex -ggemini skills install https://github.com/Avyayalaya/agent-council.git --path skills/evidence-calibration-reviewgh skill install Avyayalaya/agent-council evidence-calibration-reviewgit clone --depth 1 https://github.com/Avyayalaya/agent-council /tmp/Avyayalaya__agent-council
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Avyayalaya__agent-council/skills/evidence-calibration-review ~/.claude/skills/evidence-calibration-review # Claude Code
cp -R /tmp/Avyayalaya__agent-council/skills/evidence-calibration-review ~/.agents/skills/evidence-calibration-review # Codex, Cursor, Gemini CLI, Copilot, OpenCode