fact-checker

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.

1.10x

Quality

88%

Does it follow best practices?

Impact

93%

1.10x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

100%

13%

AI Comparison Guide Accuracy Review

Comparison table and correction report format

Criteria

Without context

With context

Comparison table present

50%

100%

Status codes used

100%

Fact-check report header

100%

Issue Location field

100%

Issue Current claim field

100%

Issue Correction field

100%

Issue Source URL field

100%

Issue Rationale field

100%

Temporal context in corrections

100%

Numerical precision matches source

88%

100%

Official AI source cited

100%

No unsolicited edits

100%

90%

14%

Dependency Audit for Data Science Toolkit README

Search strategy and source evaluation

Criteria

Without context

With context

Specific search queries

100%

88%

Package registry cited

100%

GitHub cited as source

100%

No unverified aggregator as sole source

100%

Unverifiable claim marked

11%

100%

Alternative phrasing suggested

100%

Source URLs in report

100%

Comparison table status codes

100%

No document modification

100%

Summary statistics present

22%

100%

Temporal context in corrections

100%

Rationale provided

100%

91%

Tech Blog Post Accuracy Check

Claim identification and approval workflow

Criteria

Without context

With context

Progress checklist present

Opinions excluded

100%

Tutorial steps excluded

100%

Factual specs targeted

100%

Report before edits

100%

Source file unchanged

100%

Approval request in output

100%

Comparison table with status codes

100%

Accurate claims noted

100%

Source citations included

100%

Temporal context in corrections

100%

Repository: fernandezbaptiste/claude-code-skills
Commit: 4f0eae8

Evaluated: about 1 month ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

AI Comparison Guide Accuracy Review Dependency Audit for Data Science Toolkit README Tech Blog Post Accuracy Check

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.