Fact checker

Skill the-hugin/RSIm/skills/fact-checker

Systematic fact-verification framework for identifying misinformation. Evaluates claims against credible sources, rates accuracy with confidence levels, and exposes manipulation tactics (cherry-picking, false equivalences, logical fallacies).From its SKILL.md

Install

npx -y skills add the-hugin/RSIm --skill fact-checker

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.7 KB, 722 tokens by cl100k_base, as published. Nobody here has run it

Fact Checker

Systematic evidence-based fact verification. Prioritizes transparent reasoning over definitive pronouncements.

When to Apply

Verifying specific claims or statistics
Evaluating source credibility
Identifying misinformation or manipulation
Separating fact from opinion or spin

Verification Process

Identify the claim — Extract the specific, falsifiable statement
Determine evidence criteria — What would prove or disprove it?
Evaluate sources — Find credible evidence, apply source hierarchy
Rate accuracy — Assign verdict with confidence level
Provide context — Explain nuances, missing context, why misconceptions persist

Verdict Scale

Verdict	Meaning
TRUE	Supported by reliable evidence
MOSTLY TRUE	Correct but missing context or minor inaccuracies
MIXED	Contains both accurate and inaccurate elements
MOSTLY FALSE	Misleading framing with a grain of truth
FALSE	Contradicted by reliable evidence
UNVERIFIABLE	Cannot be confirmed or denied with available evidence

Source Hierarchy (credibility ranking)

Peer-reviewed scientific studies (highest)
Official government/institutional data
Reputable journalism with named sources
Expert consensus statements
Corporate/organizational statements (potential bias)
Social media, blogs (lowest — require independent verification)

Manipulation Tactics to Watch

Statistical cherry-picking — correct number, misleading timeframe or subset
Context removal — true statement, false implication without context
False equivalence — comparing non-comparable things
Logical fallacies — ad hominem, straw man, appeal to authority
Misleading framing — technically true but designed to mislead
Outdated data — presenting old statistics as current

Output Format

## Claim
[Exact statement being verified]

## Verdict: [TRUE / MOSTLY TRUE / MIXED / MOSTLY FALSE / FALSE / UNVERIFIABLE]

**Confidence:** [High / Medium / Low]

## Analysis
[2–4 paragraphs: what the evidence shows, key data points, source quality]

## Context
[Missing context, why the misconception persists, broader picture]

## Corrected Statement (if needed)
[More accurate version of the claim]

## Sources
1. [Source with credibility level]
2. [Source with credibility level]

Example

Claim: "Humans only use 10% of their brain."

Verdict: FALSE (High confidence)

Analysis: Brain imaging (fMRI/PET) shows activity throughout the entire brain, with different regions active for different tasks. Over a 24-hour period, virtually all brain regions show activity. There is no "dormant 90%."

Context: The myth likely originates from misquotations of early 20th-century psychologists and self-help books. It persists because it's an appealing idea (implying unused potential). The misconception is also reinforced by films like Lucy (2014).

Sources:

Boyd, R. (2008). Scientific American — "Do people only use 10 percent of their brains?" (High credibility)
Radford, B. (2010). Live Science — fMRI evidence review (High credibility)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most quality gates skills give in 722 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07

Read the output and check the exit codein 54 of 1195, across 14 files
Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
Identify the verification command proving the claimin 51 of 1195, across 12 files
Run the full verification commandin 50 of 1195, across 11 files
Verify output confirms the claimin 49 of 1195, across 12 files
Check version control diff after agent delegationin 46 of 1195, across 6 files
State claim with evidencein 44 of 1195, across 4 files
Run the test suitein 33 of 1195, across 26 files
Keep state in memory by defaultin 27 of 1195, across 6 files
Make prototype runnable with one commandin 26 of 1195, across 5 files
Produce a verification reportin 25 of 1195, across 14 files
Detect the package manager from lockfilesin 24 of 1195, across 5 files

Said here and by no other author read

extract specific falsifiable statements
determine evidence criteria
apply source hierarchy
explain nuances and missing context

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.