Fact Checker
Run a structured pass over docs or specs to verify claims against authoritative sources and apply corrections only after you approve.
Overview
fact-checker is an agent skill most often used in Ship (also Build/docs, Grow/content) that verifies document claims via web search and applies source-backed corrections after user approval.
Install
npx skills add https://github.com/daymade/claude-code-skills --skill fact-checkerWhat is this skill?
- 5-step fact-checking checklist from claim ID through user-approved corrections
- Targets specs, versions, stats, API limits, and benchmark figures; skips pure opinion and tutorial steps
- Searches authoritative sources and produces a correction report before editing files
- Covers AI model specs, technical documentation, and general factual statements
- 5-step fact-checking workflow checklist
Adoption & trust: 604 installs on skills.sh; 1.2k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your docs or posts cite model specs, dates, or metrics that might be wrong or outdated, and you need evidence before changing files.
Who is it for?
Builders maintaining technical docs, AI capability tables, or launch copy where factual drift is costly.
Skip if: Pure opinion pieces, internal brainstorming with no verifiable claims, or security/code review where logic bugs matter more than external facts.
When should I use this skill?
User asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents.
What do I get? / Deliverables
You get a correction report tied to authoritative sources and optional file updates only after you confirm each change.
- Correction report with source comparisons
- User-approved document edits
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ship/review is the canonical shelf because the workflow is about validating accuracy before you publish, ship docs, or sign off on technical content. Review matches compare-against-sources, correction reports, and user-approved edits—not initial drafting.
Where it fits
Verify API limit tables in a README before merging the docs PR.
Run the five-step checklist on launch notes so pricing and feature claims match vendor pages.
Refresh benchmark scores in a blog post after a new model release.
Cross-check competitor capability claims in a one-pager before you commit to positioning.
How it compares
Use instead of asking the model to 'fix' a doc without citations—this skill separates search, report, and gated apply steps.
Common Questions / FAQ
Who is fact-checker for?
Solo builders and indie teams who publish technical or AI documentation and need verified claims before ship or distribution.
When should I use fact-checker?
In Ship/review before publishing; in Build/docs when validating README or API docs; in Grow/content when refreshing statistics in articles or changelogs.
Is fact-checker safe to install?
The skill enables web search and document edits with your approval—review the Security Audits panel on this page and restrict network use in sensitive repos.
SKILL.md
READMESKILL.md - Fact Checker
# Fact Checker Verify factual claims in documents and propose corrections backed by authoritative sources. ## When to use Trigger when users request: - "Fact-check this document" - "Verify these AI model specifications" - "Check if this information is still accurate" - "Update outdated data in this file" - "Validate the claims in this section" ## Workflow Copy this checklist to track progress: ``` Fact-checking Progress: - [ ] Step 1: Identify factual claims - [ ] Step 2: Search authoritative sources - [ ] Step 3: Compare claims against sources - [ ] Step 4: Generate correction report - [ ] Step 5: Apply corrections with user approval ``` ### Step 1: Identify factual claims Scan the document for verifiable statements: **Target claim types:** - Technical specifications (context windows, pricing, features) - Version numbers and release dates - Statistical data and metrics - API capabilities and limitations - Benchmark scores and performance data **Skip subjective content:** - Opinions and recommendations - Explanatory prose - Tutorial instructions - Architectural discussions ### Step 2: Search authoritative sources For each claim, search official sources: **AI models:** - Official announcement pages (anthropic.com/news, openai.com/index, blog.google) - API documentation (platform.claude.com/docs, platform.openai.com/docs) - Developer guides and release notes **Technical libraries:** - Official documentation sites - GitHub repositories (releases, README) - Package registries (npm, PyPI, crates.io) **General claims:** - Academic papers and research - Government statistics - Industry standards bodies **Search strategy:** - Use model names + specification (e.g., "Claude Opus 4.5 context window") - Include current year for recent information - Verify from multiple sources when possible ### Step 3: Compare claims against sources Create a comparison table: | Claim in Document | Source Information | Status | Authoritative Source | |-------------------|-------------------|--------|---------------------| | Claude 3.5 Sonnet: 200K tokens | Claude Sonnet 4.5: 200K tokens | ❌ Outdated model name | platform.claude.com/docs | | GPT-4o: 128K tokens | GPT-5.2: 400K tokens | ❌ Incorrect version & spec | openai.com/index/gpt-5-2 | **Status codes:** - ✅ Accurate - claim matches sources - ❌ Incorrect - claim contradicts sources - ⚠️ Outdated - claim was true but superseded - ❓ Unverifiable - no authoritative source found ### Step 4: Generate correction report Present findings in structured format: ```markdown ## Fact-Check Report ### Summary - Total claims checked: X - Accurate: Y - Issues found: Z ### Issues Requiring Correction #### Issue 1: Outdated AI Model Reference **Location:** Line 77-80 in docs/file.md **Current claim:** "Claude 3.5 Sonnet: 200K tokens" **Correction:** "Claude Sonnet 4.5: 200K tokens" **Source:** https://platform.claude.com/docs/en/build-with-claude/context-windows **Rationale:** Claude 3.5 Sonnet has been superseded by Claude Sonnet 4.5 (released Sept 2025) #### Issue 2: Incorrect Context Window **Location:** Line 79 in docs/file.md **Current claim:** "GPT-4o: 128K tokens" **Correction:** "GPT-5.2: 400K tokens" **Source:** https://openai.com/index/introducing-gpt-5-2/ **Rationale:** 128K was output limit; context window is 400K. Model also updated to GPT-5.2 ``` ### Step 5: Apply corrections with user approval **Before making changes:** 1. Show the correction report to the user 2. Wait for explicit approval: "Should I apply these corrections?" 3. Only proceed after confirmation **When applying correctio