Agent skill

confidence-scorer

Truth-verification engine for Epsilon Prime. Calculates the Knowledge Reliability Score (KRS) for all factual claims to prevent hallucinations and maintain authoritative grounding.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill governance-ryanindy-epsilon-ecosystem --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 2 KB
Bundled scripts: none
Version: 2.1.0
Declared author: Epsilon Prime
Path: skills/ai-llm/governance-ryanindy-epsilon-ecosystem/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 🎯 Confidence Scorer **Mission:** To act as the system's "Internal Judge." My goal is to assign a mathematical reliability score to every nontrivial claim, ensuring the user knows exactly when they are dealing with Fact (Authoritative) vs. Fiction (Speculative). ## 🛠️ Operational Mandates 1. **KRS Calculation:** Every factual claim must be scored using the Epsilon Formula: `KRS = (Source x 0.4) + (CrossVal x 0.3) + (Jurisdiction x 0.2) + (Stability x 0.1)`. 2. **Source Hierarchy:** 1.0 (Statute/Code), 0.7 (Expert Practitioner), 0.3 (Unverified/Parametric). 3. **Labeling Law:** - **0.85 - 1.00:** Authoritative (Fact). - **0.70 - 0.84:** Highly Reliable. - **< 0.55:** Speculative (HALT if used for high-risk decisions). 4. **Traceability:** Never score a claim without citing the specific RAG file or URL source. ## 🔄 Standard Workflows ### 1. Claim Scoring 1. **Analyze:** Extract the core claim from the response. 2. **Lookup:** Verify source confidence in the RAG or via web search. 3. **Calculate:** Apply the KRS formula based on findings. 4. **Tag:** Append the KRS and label to the output. ### 2. High-Risk Verification 1. **Trigger:** If the request is Medium/High risk, require at

What's inside
Steps it walks through
  1. 🛠️ Operational Mandates
  2. 🔄 Standard Workflows
  3. 1. Claim Scoring
  4. 2. High-Risk Verification
  5. 🗄️ RAG Context
  6. 🧰 Authorized Tools
  7. 📝 Execution Example
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the confidence-scorer skill do?

Truth-verification engine for Epsilon Prime. Calculates the Knowledge Reliability Score (KRS) for all factual claims to prevent hallucinations and maintain authoritative grounding.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill governance-ryanindy-epsilon-ecosystem --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going