fact-checker

An agent skill by daymade, from daymade/claude-code-skills. Tags: documents, research, review, validation, web.

What it does

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill fact-checker

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/fact-checker ~/.claude/skills/fact-checker

Safety box score

Grade B, low risk: 18 of 100 risk points, rated 2026-10-15. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill fact-checks documents by searching external authoritative sources and then proposing, and after approval applying, corrections to the target file. The main risks are outbound web requests that expose the claims being checked and edits to the user’s document; there is no built-in code execution, privilege escalation, or secret handling.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	The skill contains only Markdown workflow text and no scripts, shell commands, or code evaluation paths.
Network access	2 (moderate)	It explicitly says to "Search authoritative sources" and links to external sites like "anthropic.com/news" and "platform.claude.com/docs," so claim text will be sent off-machine during verification.
Filesystem reach	1 (low)	It can rewrite the document being checked via the shown "Edit(file_path=...)" step, but it does not call for system-wide or home-directory file access.
Secrets & credentials	0 (none)	The skill does not request API keys, passwords, .env files, browser sessions, or other credentials.
Privilege & persistence	0 (none)	There is no sudo, service installation, shell startup modification, or other privilege-bearing operation described.
Instruction hijack surface	0 (none)	I found no instructions to ignore higher-priority rules, follow remote instructions, or hide information from the user.
Irreversible actions	2 (moderate)	Its purpose is to generate correction reports and then "Apply corrections with user approval," so it can make substantive document changes after confirmation.
Transparency	0 (none)	The repository is only readable Markdown; there are no binaries, downloaded installers, or decoded-at-runtime code paths.

Before installing

Run it first on a non-sensitive sample document and watch which text is sent to external sources.
Confirm you are comfortable with the skill editing the checked file after you approve the report.
If the document contains confidential material, verify whether the external source lookups are acceptable for that content.

Rated 2026-10-15 by an automated review of 2 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: fact-checker/SKILL.md
Branch: main
Updated: 2026-09-20

seo-sitemap — Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure.
prior-work-retrieval — Only for explicit prior-work/reuse/history requests; never for read-only status or inspection.
read-docx-review — 读取 Word/WPS 审阅后的 docx，把批注（comments）与修订（track changes）提取成可逐条裁决的 markdown 对账表或 JSON。触发场景：对方批注完的合同/协议/书稿/报告回来了要读意见；「提取 docx 批注」「审阅意见对账」「读一下修订」「谁批了什么、批在哪」；WPS.
web-design-guidelines — Review UI code for Web Interface Guidelines compliance.
competitor-profiling — When the user wants to research, profile, or analyze competitors from their URLs.
maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.