Fact Verification
- 18 installs
- 869 repo stars
- Updated June 8, 2026
- beita6969/scienceclaw
fact-verification is a Claude skill that systematically verifies scientific, political, and environmental claims against evidence using retrieval and source evaluation.
About
This skill verifies factual claims (scientific, political, environmental, and health) against evidence through retrieval, source evaluation, and logical reasoning. A developer or researcher uses it to decompose a claim into atomic statements, gather supporting or refuting evidence, and assign a verdict on a defined scale. It references labeled datasets like PolitiFact and Climate-FEVER.
- Verifies scientific, political, and environmental claims against evidence
- Uses a 5-step protocol from claim decomposition to verdict synthesis
- References labeled datasets (PolitiFact, Climate-FEVER)
Fact Verification by the numbers
- 18 all-time installs (skills.sh)
- Ranked #1,276 of 2,065 Data Science & ML skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
fact-verification capabilities & compatibility
Free; relies on external evidence sources and reasoning.
- Capabilities
- fact verification
- Use cases
- research · web search · data analysis
- Pricing
- Free
What fact-verification says it does
Systematically verify factual claims using evidence retrieval, source evaluation, and logical reasoning.
npx skills add https://github.com/beita6969/scienceclaw --skill fact-verificationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 18 |
|---|---|
| repo stars | ★ 869 |
| Last updated | June 8, 2026 |
| Repository | beita6969/scienceclaw ↗ |
What it does
Use it to fact-check claims by decomposing them, retrieving evidence, and assigning a verdict on a defined truth scale.
Who is it for?
Fact-checking claims by decomposing them and aligning evidence to a verdict scale.
Skip if: Generating original claims or content rather than verifying existing ones.
When should I use this skill?
The user needs to verify scientific claims, political statements, or environmental assertions against evidence.
What you get
Produces an evidence-cited verdict for each claim on a defined truth scale.
- Per-claim verdict with cited evidence
- Decomposed sub-claim assessments
By the numbers
- 5-step verification protocol
- 6-level verdict scale
- 4 verification categories
Files
Fact Verification
Purpose
Systematically verify factual claims using evidence retrieval, source evaluation, and logical reasoning.
Key Datasets
- PolitiFact (Jinyan1/PolitiFact): Political statements rated on 6-level truth scale (True, Mostly True, Half True, Mostly False, False, Pants on Fire)
- Climate-FEVER (tdiggelm/climate_fever): Climate claims labeled SUPPORTS/REFUTES/NOT_ENOUGH_INFO with evidence sentences
Protocol
1. Claim decomposition — Break complex claims into atomic verifiable statements 2. Evidence retrieval — Search authoritative sources for each sub-claim 3. Source evaluation — Assess source credibility and potential bias 4. Evidence-claim alignment — Determine if evidence supports, refutes, or is insufficient 5. Verdict synthesis — Aggregate sub-verdicts into overall assessment
Verification Categories
- Scientific claims: Published findings, statistical assertions, causal claims
- Political statements: Policy claims, historical assertions, statistical citations
- Environmental claims: Climate data, pollution metrics, biodiversity assertions
- Health claims: Treatment efficacy, risk factors, epidemiological data
Verdict Scale
- VERIFIED: Multiple independent high-quality sources confirm
- LIKELY TRUE: Evidence supports but limited independent confirmation
- MIXED: Partially true with important caveats or context
- LIKELY FALSE: Evidence contradicts but some ambiguity remains
- FALSE: Clear evidence contradicts the claim
- UNVERIFIABLE: Insufficient evidence to determine
Rules
- Always cite specific evidence for each verdict
- Distinguish between factual errors and misleading framing
- Check for cherry-picked statistics or out-of-context quotes
- Consider temporal context (claim may have been true when made)
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511FAQ
What is the verification protocol?
Claim decomposition, evidence retrieval, source evaluation, evidence-claim alignment, and verdict synthesis.
What verdict scale does it use?
VERIFIED, LIKELY TRUE, MIXED, LIKELY FALSE, FALSE, and UNVERIFIABLE.