ai-claim-checker

Evaluate factual claims in AI-generated text and teach a lightweight verification habit. Use when a learner wants to fact-check an AI answer, identify uncertainty, choose appropriate independent sources, or practise critical AI literacy.

Quality

85%

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

82%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.

A tight, well-structured instruction-only skill with a concrete workflow, status vocabulary, and output template that make it highly actionable. The main gap is the absence of an explicit validate-fix-retry feedback loop in the workflow.

Suggestions

Add an explicit feedback loop after the comparison step (e.g. 'If a source contradicts the claim, re-extract the corrected claim and re-record its status before producing output') to strengthen workflow validation.

Tighten the parenthetical clarifications in 'Workflow' and 'Source selection examples' so each remaining sentence is irreducible guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and instruction-focused with no padding about what AI or fact-checking is, but a few clarifying sentences (e.g. 'An official site can be authoritative for policy or public guidance without being a peer-reviewed publication') could be trimmed without losing guidance value.	4 / 5
Actionability	Provides concrete, executable guidance: a 7-step process, an explicit record schema (exact claim, why check, evidence, source type), five named verification statuses, source-type examples by domain, and a copy-paste-ready output template with defined fields.	5 / 5
Workflow Clarity	The 7-step workflow is clearly sequenced with an explicit fallback ('If live verification is unavailable, do not simulate it... mark the claim not verified') and a status-comparison step, but error-recovery feedback loops are only implicit rather than a structured validate-fix-retry cycle.	4 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (Safety boundary, Workflow, Optional learner exercise, Source selection examples, Output, Limitations) with no nested or broken references and no bundle files to misnavigate, though the skill is self-contained rather than pointing to one-level-deep detail files.	4 / 5
	Total	17 / 20 Passed

Description

83%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, third-person description that clearly states both capability and trigger conditions with natural keywords. It is comprehensive on completeness and only marginally short on action specificity and trigger synonym coverage.

Suggestions

Swap 'teach a lightweight verification habit' for a more concrete action verb phrase (e.g. 'walk a learner through a verification check') to lift specificity.

Add one or two colloquial trigger synonyms such as 'check if an AI answer is accurate' or 'is this true' to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Evaluate factual claims', 'fact-check an AI answer', 'identify uncertainty', 'choose appropriate independent sources'), but 'teach a lightweight verification habit' and 'practise critical AI literacy' lean slightly abstract, leaving minor coverage gaps versus a fully comprehensive list.	4 / 5
Completeness	Explicitly answers both what ('Evaluate factual claims in AI-generated text and teach a lightweight verification habit') and when ('Use when a learner wants to fact-check an AI answer, identify uncertainty, choose appropriate independent sources, or practise critical AI literacy') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('fact-check an AI answer', 'identify uncertainty', 'independent sources') with the synonym 'verify' implied, but a few common variations (e.g. 'check if this is true', 'is this accurate') are missing.	4 / 5
Distinctiveness Conflict Risk	The AI-claim-checking niche is clear and distinct, but 'critical AI literacy' and general fact-checking could produce minor overlap with broader media-literacy or research skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: iflytek/skillhub
Path: builtin-skills/skills/ai-claim-checker/SKILL.md
Commit: 7352597

Reviewed: 4 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.