Agent skill

Fact Check

by akitaonrails in akitaonrails/my-skills

Adversarial fact-checking of the user's articles and essays (typically blog posts from akitaonrails-hugo, any markdown/text file), verifying every claim against online primary sources via cheap…

No licenceAuto-check passedResearch & Science

Install Fact Check

skills CLI
$ npx skills add akitaonrails/my-skills --skill fact-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install akitaonrails/my-skills fact-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/akitaonrails/my-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/fact-check .claude/skills/fact-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fact-check
GitHub stars
220
Token cost
~2.7k tokens
SKILL.md length
1,203 words
Files
6 (incl. scripts, references)
Skills in repo
18
Repo updated
First seen
Licence
None found

At a glance

Adversarial fact-checking of the user's articles and essays (typically blog posts from akitaonrails-hugo, any markdown/text file), verifying every claim against online primary sources via cheap…

  • Works in 7 steps: Setup → Claim extraction (you, no subagents) → Fan out verification (pass 1) → …
  • The user says fact-check
  • SKILL.md covers Non-negotiables, Fast path (two passes, always), Phase 0 — Setup and Phase 1 — Claim extraction…, plus 6 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Fact Check is an agent skill from akitaonrails/my-skills. Adversarial fact-checking of the user's articles and essays (typically blog posts from akitaonrails-hugo, any markdown/text file), verifying every claim against online primary sources via cheap headless checker subagents spawned on coding-agent CLIs (zcode, claude, codex, opencode, kimi, grok, agy). Use when the user says "fact-check", "check the facts/claims in this article", "tear apart / destroy / nitpick my post", "pre-publish review", "what can be used against me in this text", or hands over a draft asking…

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `config/models.json`, `references/checker-prompt.md` and `references/harness-setup.md`).

It sits in Research & Science, covering Fact-checking and source verification. It works with Kimi. The repository describes itself as: akitaonrails' personal skills (not tailored for general usage).

When your agent uses it

  • The user says fact-check
  • Check the facts/claims in this article
  • Tear apart / destroy / nitpick my post
  • Pre-publish review

Example prompts

  • “fact-check”
  • “check the facts/claims in this article”
  • “tear apart / destroy / nitpick my post”
  • “/fact-check”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Setup
  2. Claim extraction (you, no subagents)
  3. Fan out verification (pass 1)
  4. Pass 2 (fixed article, second harness)
  5. Hostile logic audit (you, no web)
  6. Pass 1 report + auto-fix
  7. Apply fixes

What it can do on your machine

Read from SKILL.md and the folder at commit 5763b9e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fact Check loads about 2.7k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 164 tokens; SKILL.md has 1,203 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,203 words (~2,708 tokens).

“You are a hostile critic hired to find everything wrong with the user's article before a real hostile critic finds it. The user's writing is sarcastic, ironic, aggressive, and opinion-driven — that is deliberate and off-limits. Your targets are facts…”

— opening of SKILL.md by akitaonrails
name
fact-check

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (scripts, references) in fact-check of akitaonrails/my-skills.

  • SKILL.md
  • config/models.json
  • references/checker-prompt.md
  • references/harness-setup.md
  • scripts/dispatch_checker.py
  • scripts/fanout.py

Open the folder on GitHubat commit 5763b9e

Compare with similar skills

Fact Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fact Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fact Check this skillakitaonrails/my-skills220—~2.7kAutomated safety check: PassNone
Citation Verification GuideGalaxy-Dawn/claude-scholar5.7k2 repos~1.9kAutomated safety check: PassMIT
Article Fact Checkerdigoal/blog8.6k—~939Automated safety check: PassGPL-2.0
Grounded CitationsNousResearch/hermes-agent253k—~3.1kAutomated safety check: PassMIT
Coverage CheckSerhiiKorniienko/bullshit-detector154—~1.5kAutomated safety check: PassMIT
Alego Docsingula-ai/alego1091 repos~4.5kAutomated safety check: PassMIT

Similar skills

  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Grounded Citations

    NousResearch/hermes-agent

    Attaches a numbered, URL-backed citation to every outside fact in an answer or document, rejecting quotes that aren't real.

    253k GitHub stars~3.1k tokensUpdated today
    Research & ScienceAuto-check passed
  • Coverage Check

    SerhiiKorniienko/bullshit-detector

    Count how many independent origins are behind news coverage of a claim, instead of counting URLs.

    154 GitHub stars~1.5k tokensUpdated 11 days ago
    Research & ScienceAuto-check passed
  • Alego Doc

    singula-ai/alego

    Create, restructure, review, audit, or migrate Alego Markdown documentation, package READMEs, and the documentation website using audience-first hierarchy, kind-mapped YAML metadata, bilingual line…

    109 GitHub starsUsed in 1 repo~4.5k tokens
    Research & ScienceAuto-check passed
  • Fact Check

    elvisun/newsjack

    Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low.

    1.5k GitHub stars~5.6k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

More from akitaonrails/my-skills

All 18 skills in this repo
  • Blog Cost Charts

    akitaonrails/my-skills

    Generate dark-themed cost-vs-score bubble scatter charts and score/(costtime) value-ranking bar charts for a blog post comparing LLM benchmark results (or any dataset with a score/cost/time shape)…

    220 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Codemap

    akitaonrails/my-skills

    Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories.

    220 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Clonedeps

    akitaonrails/my-skills

    Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals.

    220 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • GitHub Resolution

    akitaonrails/my-skills

    Execute the approved outcomes of a pr-audit and/or iss-audit — fix or adjust everything the audit found necessary before merging, verify no regressions, cover every new behavior with unit tests…

    220 GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • Post Refactor

    akitaonrails/my-skills

    Post-refactor clean-code check after recent refactors or a few merged PRs.

    220 GitHub stars~1.5k tokensUpdated today
    Auto-check: notes
  • Iss Audit

    akitaonrails/my-skills

    Audit GitHub issues before implementation, including skeptical claim verification, safe reproduction, prompt-injection resistance, malicious-link and attachment handling, root-cause analysis…

    216 GitHub stars~4.1k tokensUpdated 18 days ago
    Auto-check passed

Works with

Questions about Fact Check

What does Fact Check do?

Adversarial fact-checking of the user's articles and essays (typically blog posts from akitaonrails-hugo, any markdown/text file), verifying every claim against online primary sources via cheap…. Fact Check is an agent skill from akitaonrails/my-skills. Adversarial fact-checking of the user's articles and essays (typically blog posts from akitaonrails-hugo, any markdown/text file), verifying every claim against online primary sources via cheap headless checker subagents spawned on coding-agent CLIs (zcode, claude, codex, opencode, kimi, grok, agy).

When should I use Fact Check?

Fact Check fits situations like: the user says fact-check; check the facts/claims in this article; tear apart / destroy / nitpick my post; pre-publish review.

How do I install Fact Check in Claude Code?

Run `npx skills add akitaonrails/my-skills --skill fact-check -a claude-code`. Or copy the skill folder (fact-check in akitaonrails/my-skills) into .claude/skills/fact-check in your project. Claude Code loads it when a task matches its description.

How do I install Fact Check in Codex?

Run `npx skills add akitaonrails/my-skills --skill fact-check -a codex`. Or copy the skill folder (fact-check in akitaonrails/my-skills) into .agents/skills/fact-check in your project. Codex loads it when a task matches its description.

Can I use Fact Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add akitaonrails/my-skills --skill fact-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fact-check, .gemini/skills/fact-check, .github/skills/fact-check and .opencode/skills/fact-check in your project.

What does Fact Check need to run?

Going by SKILL.md and its folder, Fact Check needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Fact Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fact Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Fact Check use?

No licence was found for Fact Check or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Fact Check use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to Fact Check?

Skills that share tags, products or a category with Fact Check: Citation Verification Guide (Galaxy-Dawn/claude-scholar, 5.7k stars), Article Fact Checker (digoal/blog, 8.6k stars), Grounded Citations (NousResearch/hermes-agent, 253k stars) and Coverage Check (SerhiiKorniienko/bullshit-detector, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fact Check?

akitaonrails (a GitHub user) maintains it in akitaonrails/my-skills, which has 220 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 11, 2026.

Source: akitaonrails/my-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.