fact-checking skills

424 tagged fact-checking, measured the same way as everything else here.

Browse within: academic-writing 34data-journalism 34journalism 27investigations 25open-source 25osint 25aeo 22claude-plugin 22content-marketing 22content-pipeline 22editorial 22seo 22techshu 22Hallucination Detection 15

dev-toolkit

07

jamditis/claude-skills-journalism

Plugin Claude Code

Thirteen development skills for newsroom and research dev teams: accessibility, context management, directed multi-agent execution, Electron, mobile debugging, Python pipelines, test-first bug fixing, ethical scraping, no-build frontends, web UI craft, and CLAUDE.md maintenance.

384 +6 4d ago A tokens not measured original MIT

web-scraping

09

jamditis/claude-skills-journalism

Skill Claude CodeCodex

Authorized web scraping with fallback cascades and access-failure handling. Use for social media, yt-dlp, CAPTCHA or 403 blocks.

384 +6 4d ago A 33 tokens original MIT

journalism-core

10

jamditis/claude-skills-journalism

Plugin Claude Code

Fifteen core journalism skills for reporting, verification, publishing, and digital investigations: AP-style writing, AI-slop detox, source verification, FOIA/OPRA and Brazilian LAI requests, fact-checking, interview prep and transcription, story pitches, editorial workflow, crisis comms, newsletter publishing, data…

384 +6 4d ago A tokens not measured original MIT

foia-requests

11

jamditis/claude-skills-journalism

Skill Claude CodeCodex

FOIA and public records workflows. Use when drafting requests, tracking submissions, checking exemptions, or appealing denials.

384 +6 4d ago A 28 tokens original MIT

FirstData AGENTS.md

13

MLT-OSS/FirstData

Instructions file CodexOpenCode

Instructions for MLT-OSS/FirstData, covering agents.md, what this repo is, validation, install dependencies (first time only) and run all validation checks.

182 16d ago A 1,716 tokens original MIT

FirstData CLAUDE.md

14

MLT-OSS/FirstData

Instructions file

Instructions for MLT-OSS/FirstData, covering claude.md, project overview, validation, install dependencies (first time only) and run all validation checks.

182 16d ago A 1,912 tokens original MIT

firstdata

15

MLT-OSS/FirstData

Skill Claude CodeCodex

Find official portals, APIs, and download paths for authoritative primary data sources (governments, international organizations, research institutions, etc.). Use when users need to know "where to find this data from an official source", "which source is more authoritative", or "how to cite primary data". Covers…

182 16d ago A 78 tokens original MIT

firstdata

16

MLT-OSS/FirstData

MCP server Claude CodeCodexCursor +2

Hosted MCP server for finding authoritative primary data sources and official portals. Remote server at firstdata.deepminer.com.cn.

182 16d ago A tokens not measured original MIT

bullshit-detector

17

SerhiiKorniienko/bullshit-detector

Plugin Claude Code

Fact-check the internet with your agent — fetch any YouTube video, article, tweet, or PDF, verify its claims against independent sources, and get a BS score instead of hype.

139 +1 16d ago A tokens not measured original MIT

SerhiiKorniienko/bullshit-detector

Instructions file CodexOpenCode

Instructions for SerhiiKorniienko/bullshit-detector, a project described as: Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF.

139 +1 16d ago A 4 tokens copy · 100% MIT

claim-extractor

20

SerhiiKorniienko/bullshit-detector

Agent

Extract and classify claims from a chunk of transcript or article text for fact-checking. Used by the bullshit-detector skill to fan out extraction over long content — spawn one per chunk, in parallel. Mechanical work; runs on a fast model.

139 +1 16d ago A 53 tokens original MIT

bullshit-detector

21

SerhiiKorniienko/bullshit-detector

Skill Claude CodeCodex

Fact-check and hype-audit content. Extracts the discrete claims from a video, article, tweet, or PDF, verifies each against independent sources via web search, and produces a report card with per-claim verdicts and an overall BS score (0-10). Use when the user asks to fact-check, verify, debunk, or evaluate…

139 +1 16d ago A 101 tokens original MIT

coverage-check

22

SerhiiKorniienko/bullshit-detector

Skill Claude CodeCodex

Count how many independent origins are behind news coverage of a claim, instead of counting URLs. Queries GDELT for matching articles, collapses reprints and wire copy into single origins, and flags publication bursts that indicate syndication. Use when a claim appears to be confirmed by many outlets and you need to…

139 +1 16d ago A 75 tokens original MIT

report-card

23

SerhiiKorniienko/bullshit-detector

Skill Claude CodeCodex

Render a finished BS report as a self-contained HTML page — score hero, filterable claims, readable on a phone, prints to a clean PDF. Use when the user wants to open, share, print, or show a report to someone who is not going to read a markdown table, or asks for "the HTML version", "something I can send", "a…

139 +1 16d ago A 87 tokens original MIT

At most 3 mods per repository are shown here — the rest are on their repository pages: