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 Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents.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.
90
88%
Does it follow best practices?
Impact
93%
1.10xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It clearly articulates specific capabilities (verification via web search, proposing corrections), includes an explicit 'Use when...' clause with natural trigger terms, and defines its scope with supported content types. The description is distinctive enough to avoid conflicts with related skills like general document editing or web search.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Verifies factual claims', 'using web search and official sources', 'proposes corrections with user confirmation'. Also specifies supported content types: 'AI model specs, technical documentation, statistics, and general factual statements'. | 3 / 3 |
Completeness | Clearly answers both what (verifies claims using web search/official sources, proposes corrections) and when (explicit 'Use when...' clause with multiple trigger scenarios). The scope is also defined with supported document types. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'fact-check', 'verify information', 'validate claims', 'check accuracy', 'update outdated information'. These are all phrases users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on fact-checking and verification with distinct triggers like 'fact-check', 'validate claims', 'check accuracy'. Unlikely to conflict with general document editing or web search skills due to the specific verification focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with excellent workflow clarity and explicit validation checkpoints. The main weaknesses are moderate verbosity (explaining concepts Claude already knows) and the monolithic structure that could benefit from progressive disclosure to separate reference files. The concrete examples, templates, and explicit user approval requirements are strong points.
Suggestions
Remove or significantly trim the 'Limitations' section - Claude already understands it cannot verify opinions or access paywalled content
Move 'Search best practices' and 'Special considerations' sections to a separate REFERENCE.md file, keeping only essential guidance in the main skill
Condense the 'Skip subjective content' list - Claude knows what constitutes subjective vs factual content
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content like explaining what types of claims to skip (Claude knows what's subjective), and the 'Limitations' section states obvious things Claude already understands. The examples section could be more compact. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific search query examples, exact Edit tool syntax, structured report templates, and clear comparison table formats. The workflow steps are copy-paste ready with real examples. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit checkpoints: progress checklist at the start, clear validation step (Step 5 requires user approval before changes), verification after corrections, and quality checklist at the end. The feedback loop for handling ambiguity is well-defined. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is quite long (~250 lines) and could benefit from splitting detailed content (like search best practices, special considerations) into separate reference files. Currently a monolithic document that could overwhelm. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- daymade/claude-code-skills
- Commit
392d34c
- Reviewed
Table of Contents
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.