From confidence-scorer
Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.
How this skill is triggered — by the user, by Claude, or both
Slash command
/confidence-scorer:confidence-scorerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Assign a numerical confidence score to every claim, so users know exactly how much to trust each part of your response.
Assign a numerical confidence score to every claim, so users know exactly how much to trust each part of your response.
| Score | Meaning | Example |
|---|---|---|
| 95-100 | Verified against code just now | "src/auth.ts exports validateToken (I just read it)" |
| 80-94 | Confirmed by search/tool output | "Grep found 3 references to this function" |
| 60-79 | Strong inference from evidence | "Based on the error handling pattern, this likely..." |
| 40-59 | Educated guess from general knowledge | "Express middleware typically handles this by..." |
| 20-39 | Uncertain, limited evidence | "This might be related to the session config..." |
| 0-19 | Speculation, no evidence | "It could be a race condition, but I haven't checked" |
After making claims, add confidence annotations:
"The authentication flow works as follows:
| Situation | Minimum score to state as fact |
|---|---|
| Code changes | 80+ (must have read the code) |
| Security advice | 90+ (must have verified) |
| Production commands | 95+ (must be certain) |
| Explanations | 60+ (inference OK if labeled) |
| Suggestions | 40+ (clearly framed as suggestions) |
Use confidence scoring when:
If a claim scores below the threshold:
npx claudepluginhub a-ariff/ariff-claude-plugins --plugin confidence-scorerValidates claims through tool execution, avoids superlatives and unsubstantiated metrics. Use when reviewing codebases, analyzing systems, or reporting test results.
Validates factual claims in code reviews, system analysis, documentation, and test reports using tools; prohibits superlatives and unverified metrics.
Mandates fact-finding protocol for SME agents: read code/docs, search patterns, use tools before evidence-grounded analysis with per-finding confidence, risk assessment, and info gaps.