From 30edba08bc1867aeab879d0975c6decabe5295e0 Mon Sep 17 00:00:00 2001 From: Kevin Veen-Birkenbach Date: Sat, 18 Jul 2026 01:30:02 +0200 Subject: [PATCH] feat(confidence): report calibrated confidence on every stage and fix Co-Authored-By: Claude Opus 4.8 --- skills/confidence/SKILL.md | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 skills/confidence/SKILL.md diff --git a/skills/confidence/SKILL.md b/skills/confidence/SKILL.md new file mode 100644 index 0000000..939aa60 --- /dev/null +++ b/skills/confidence/SKILL.md @@ -0,0 +1,29 @@ +--- +name: confidence +description: > + Report calibrated confidence unprompted. Trigger whenever you stage + changes, declare a fix or bundle ready, or summarize completed work the + operator may commit or deploy — the operator must never have to ask "how + sure are you?". Portable across projects. +--- + +Every stage summary, fix report, or ready-to-commit bundle ends with a +confidence block: + +1. **Fix confidence** (percent): probability the change does what it + claims. **Break risk** (percent): probability it breaks anything else. + Two separate numbers, never one blended figure. +2. **Evidence**: the strongest proof lines only — what was executed, + reproduced, enumerated, or read from authoritative source. Distinguish + proven (ran it, saw it) from derived (reasoned statically). +3. **Residuals**: name exactly what keeps the number below 100 and what + would close the gap (live deploy, missing artifact, unexercised path). + Never a bare percentage without its residuals. + +Calibration rules: +- Number the claim you verified, not the effort you spent; discount after + any error the operator caught in the same area. +- Distinguish "fixes the observed failure" from "makes the job green" when + hidden layers may follow, and give both numbers. +- Static analysis alone caps at the low nineties; only executed evidence + (test, reproduction, live probe) justifies more.