fact-checker

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 Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents.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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body has an excellent, well-validated five-step workflow with concrete templates and an explicit approval gate, but it is monolithic: ~290 lines with search best practices, source-evaluation guidance, and worked examples that belong in separate reference files, plus several padded sections and inline time-sensitive version examples.

Suggestions

Move 'Search best practices', 'Special considerations', and the 'Examples' section into reference files (e.g., references/search-strategies.md, references/examples.md), keeping only a one-line pointer in SKILL.md.

Trim sections that restate what Step 2 already covers or what Claude already knows — the good/poor query lists and the source-evaluation preference hierarchy can be condensed to a few bullet rules.

Remove or generalize hardcoded time-sensitive details (specific model versions, 'released Sept 2025', the Chinese-language file path in the Edit example) so the skill doesn't age or read as project-specific.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded in places: the good/poor query lists, source-evaluation hierarchies, and a three-example Examples section restate what Step 2 already covers or what Claude already knows. Time-sensitive version references (e.g., 'GPT-5.2', 'released Sept 2025') appear outside any old-patterns section, further costing conciseness. Not a 2 because there is no conceptual filler explaining basics.	3 / 5
Actionability	Provides a concrete comparison-table format, status codes, a fill-in correction report template, specific search query examples, and an Edit-tool call. Not a 5 because the Edit example is illustrative (hardcoded Chinese file path, comment-style invocation) rather than copy-paste ready.	4 / 5
Workflow Clarity	Five explicitly numbered steps, a copyable progress checklist, an explicit user-approval gate ('Wait for explicit approval... Only proceed after confirmation'), post-edit verification, and a final quality checklist. Validation checkpoints are present, so the batch/destructive cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist and everything — search best practices, source evaluation, and three worked examples — is inlined in a single ~290-line file. Structure is clear via headers, but content that belongs in separate reference files is inline with no references at all, matching the anchor-3 pattern.	3 / 5
	Total	15 / 20 Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, explicit what and when, natural trigger phrases, and concrete actions. Only minor room for improvement in the breadth of concrete actions and slight overlap risk with generic document-update skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Verifies factual claims in documents using web search and official sources', 'proposes corrections with user confirmation') plus a coverage list of supported content types. It stops just short of the comprehensive multi-action coverage of the anchor-5 example.	4 / 5
Completeness	Explicitly answers both what ('Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation') and when ('Use when the user asks to fact-check...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes five natural phrases users would actually say — 'fact-check, verify information, validate claims, check accuracy, or update outdated information' — covering the common synonyms for this domain with no obvious variation missing.	5 / 5
Distinctiveness Conflict Risk	The fact-checking niche is distinct with clear triggers, though 'update outdated information in documents' has minor overlap risk with general document-update or editing skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: daymade/claude-code-skills
Path: fact-checker/SKILL.md
Commit: bb6ad55

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.