Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Fact Check

ASecurity

Fact-check articles and posts: claims, lychee link checks, primary sources.

10 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgobashgitdocumentation

Works with

cli

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add fmind/dot --skill fact-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fact Check?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Fact Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fmind-fact-check/badge)](https://www.skillsdirectory.com/skills/fmind-fact-check)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: fact-check
description: "Fact-check articles and posts: claims, lychee link checks, primary sources."
license: MIT
metadata:
  kind: task
  author: Médéric HURIER (Fmind)
  source: github.com/fmind/dot/tree/main/skills/fact-check
  created: "2026-10-04"
  updated: "2026-10-05"
---

# Fact-Check

Verify every material claim and link in a draft article, post, talk, or README section, and add primary sources where a claim needs one. Report findings with narrowed wording that would be true today; rewrite only when asked. [technical-publishing](../technical-publishing/SKILL.md) owns the publication pipeline, and a publishing project's local review skill (for example `review-content`) takes precedence for its own packages.

## Workflow

1. **Scope the source**: read the whole file and the author's raw notes when they exist; record the revision checked (`git log -1 --format=%h -- <file>` plus `git status --short <file>`). Published copy is immutable: report findings for an erratum instead of editing it.
1. **Build the claim ledger**: one row per material assertion: versions, defaults, numbers, dates, comparisons, quotations, attributions, availability ("open source", "GA", "free"), and personal results. Skip opinions, but check the facts an opinion rests on.

   | # | Claim (exact quote) | Kind | Support | Verdict | Fix |
   | - | ------------------- | ---- | ------- | ------- | --- |

1. **Verify, do not recognize**: confirm each row against a primary source opened in this session: the vendor's documentation or changelog, the repository, the lockfile or installed version, the paper, the official announcement. Prefer the canonical page over an aggregator, blog summary, or model memory. Personal facts trace only to the author's notes or explicit input; never supply them.
1. **Check links**: run lychee on the file, then open each cited page and confirm it says what the sentence claims; a resolving link that does not support its claim is the worse failure. A bare `--include-fragments` checks `#anchor` fragments only; use `--include-fragments=full` when the draft cites text fragments (`#:~:text=`).

   ```bash
   lychee --no-progress --include-fragments --max-retries 2 --format detailed <file>
   ```

1. **Add sources**: for an unsupported but true claim, propose the primary link at the claim, not a generic homepage; keep the existing link style (inline, reference, footnote). For an outdated or inflated claim, propose the smaller true form. Never invent a URL; name the missing source instead.
1. **Report**: verdict counts first (`supported`, `outdated`, `unsupported`, `wrong`, `broken link`), then the ledger rows that need action, ranked by reader impact. Include the date checked: versions, prices, and availability drift.

## Gotchas

- **Watch for quiet failures**: an intention in notes promoted to a present-tense fact, a number found in no source, a pin true when drafted but drifted since, someone else's result stated as the author's, and a "we" that claims a team that does not exist.
- **Verify comparison conditions**: check the baseline, equivalent task, outcome quality, and measurement limits; a token or time reduction alone does not prove productivity or cost.
- **Link checkers lie both ways**: bot-blocking sites return 403 or 429 to lychee yet work in a browser, and soft-404 pages return 200. Confirm suspicious results by opening the page; report login walls as unverifiable.
- **Treat remembered facts as hypotheses**: a fact you remember is a hypothesis; a fact you opened today is evidence. Say "unverified" rather than guessing.

## Documentation

- [lychee](https://lychee.cli.rs/) · [releases](https://github.com/lycheeverse/lychee/releases)
- Companion skills: [technical-publishing](../technical-publishing/SKILL.md) (publication), [social-post](../social-post/SKILL.md) (channel copy), [repository-docs](../repository-docs/SKILL.md) (README and docs accuracy).

Attribution

fmindfmind
View sourceSee grades on GitHubMore from fmind →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →