daymade

Fact Checker — AI skill for Claude Code

AI community Intermediate

Verify claims and facts with sources.

How to install Fact Checker

Installs to ~/.claude/skills/fact-checker/

Terminal

git clone --depth 1 https://github.com/daymade/claude-code-skills /tmp/claude-code-skills \
  && mkdir -p ~/.claude/skills \
  && cp -r /tmp/claude-code-skills/fact-checker ~/.claude/skills/fact-checker

Clones the whole repository, because a skill folder can carry scripts and resources beside its SKILL.md.

What Fact Checker does

Verify factual claims in documents using web search and official sources, then apply corrections with user confirmation.

Alternatives in AI

Academic Humanizer — Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying clai 1.1k ★
Karpathy LLM Wiki — Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex 618 ★
Wiki Synthesize — Synthesize wiki/sources/ .md pages from raw session transcripts using the configured LLM backend 375 ★

Repository README

This is the README for daymade/claude-code-skills, shared by 5 entries in this directory. It describes the repository, not this entry specifically.

Fact Checker

Verify factual claims in documents using web search and official sources, then apply corrections with user confirmation.

Features

✅ Comprehensive fact verification across multiple domains
🔍 Searches authoritative sources (official docs, API specs, academic papers)
📊 Generates detailed correction reports with sources
🤖 Auto-applies corrections after user approval
🕐 Adds temporal context to prevent information decay

Supported Claim Types

AI Model Specifications: Context windows, pricing, features, benchmarks
Technical Documentation: API capabilities, version numbers, library features
Statistical Data: Metrics, benchmark scores, performance data
General Facts: Any verifiable factual statement

Usage Examples

Example 1: Update Outdated AI Model Info

User: Fact-check the AI model specifications in section 2.1

**What happens:**

Identifies claims: "Claude 3.5 Sonnet: 200K tokens", "GPT-4o: 128K tokens"
Searches official documentation for current models
Finds: Claude Sonnet 4.5, GPT-5.2 with updated specs
Generates correction report with sources
Applies fixes after user confirms

Example 2: Verify Technical Claims

User: Check if these library versions are still current

**What happens:**

Extracts version numbers from document
Checks package registries (npm, PyPI, etc.)
Identifies outdated versions
Suggests updates with changelog references

Example 3: Validate Statistics

User: Verify the benchmark scores in this section

**What happens:**

Identifies numerical claims and metrics
Searches official benchmark publications
Compares document values vs. source data
Flags discrepancies with authoritative links

Workflow

The skill follows a 5-step process:

Fact-checking Progress:
- [ ] Step 1: Identify factual claims
- [ ] Step 2: Search authoritative sources
- [ ] Step 3: Compare claims against sources

...