Agent skill · Code Review & Quality

confidence-scoring

Assess research quality with systematic confidence scoring, source validation, and uncertainty quantification.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill confidence-scoring-jlaws-dotfiles --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/analysis/confidence-scoring-jlaws-dotfiles/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

# Research Confidence Scoring ## Overview Apply systematic confidence scoring to research findings. Quantify uncertainty, validate sources, detect contradictions, and provide calibrated assessments of information reliability. ## The Process ### 1. Source Assessment Rate each source on a 0.0-1.0 scale: | Score | Source Quality | |-------|---------------| | 0.9-1.0 | Primary source, official docs, peer-reviewed | | 0.7-0.8 | Reputable secondary source, established experts | | 0.5-0.6 | Community content, blog posts, forums | | 0.3-0.4 | Unverified claims, single source only | | 0.0-0.2 | Contradicted by better sources, outdated | **Source Quality Factors:** - Authority: Is the source authoritative on this topic? - Recency: How current is the information? - Corroboration: Do multiple sources agree? - Methodology: Is reasoning/evidence provided? - Bias: Does the source have obvious bias? ### 2. Claim Validation For each research finding: ``` Claim: [Statement being assessed] Sources: [List of sources] Source Confidence: [0.0-1.0 per source] Corroboration: [Number of independent sources agreeing] Contradictions: [Sources that disagree] Final Confidence: [Weighted score] ``` **Confidence

What's inside
Steps it walks through
  1. Overview
  2. The Process
  3. 1. Source Assessment
  4. 2. Claim Validation
  5. 3. Uncertainty Quantification
  6. 4. Contradiction Detection
  7. 5. Confidence Reporting
  8. Confidence Calibration
  9. Red Flags (Lower confidence)
  10. Green Flags (Higher confidence)
  11. Key Principles
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the confidence-scoring skill do?

Assess research quality with systematic confidence scoring, source validation, and uncertainty quantification.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill confidence-scoring-jlaws-dotfiles --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