blog-factcheck

Verify statistics and claims in blog posts by fetching cited source URLs and checking if the claimed data actually appears on the page. Extracts all load-bearing claims (statistics, product or policy claims, ranking and comparative claims, named sources), validates cited URLs before fetching, and scores match confidence (exact match 1.0, paraphrase 0.7-0.9, not found 0.0). Flags uncited claims as UNVERIFIED. Use when user says "fact check", "verify statistics", "check sources", "validate claims", "factcheck", "source verification".

Quality

94%

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

88%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 well-structured, highly actionable instruction-only skill with explicit validation checkpoints and feedback loops for its batch URL-verification workflow. Its main weakness is mild redundancy of the echo-cluster/primary-source/stale-source concepts across sections and a lack of file-based progressive disclosure.

Suggestions

Consolidate the echo-cluster, primary-source, and stale-source guidance into a single section; currently these recur across Step 3, Source Tier and Echo Checks, Verification Scoring, and Integration.

Consider moving the detailed Claim Extraction Patterns or Source Tier tables into a reference file under references/ to improve progressive disclosure, since the body exceeds 50 lines.

The Step 3 sub-steps read as a numbered list within an ordered list; promote them to top-level workflow steps or a checklist so the validation sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	Content is dense and domain-specific with no basic-concept padding, but echo-cluster, primary-source, and stale-source concepts reappear across Step 3, Source Tiers, Scoring, and Integration, which could be trimmed. Fits the 4 anchor (efficient with minor over-explanation) rather than 5.	4 / 5
Actionability	Concrete URL-rejection rules ('reject localhost, loopback, private... reject javascript:, data:, and file:'), an explicit scoring table, and worked examples ('43%' vs 'nearly half' scores 0.8; 2024/2023 stale caps at 0.5) cover the common cases. As an instruction-only skill, the absence of code is not penalized given the highly actionable guidance.	5 / 5
Workflow Clarity	Five sequenced steps with explicit validation checkpoints (URL validation before fetch, source-tier classification, context/timeframe matching) and feedback loops (resumable output, rate limiting) for a batch operation, satisfying the 5 anchor and the batch-validation requirement.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Workflow, Claim Extraction Patterns, Source Tiers, Scoring, Output Format, Limitations) with no nested references, but all content is inline with no bundle files; at ~170 lines the under-50-line exception does not apply, so it fits the 4 anchor rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

100%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 concretely states multiple capabilities and pairs them with explicit natural-language triggers. It fully answers both what the skill does and when to invoke it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Verify statistics and claims', 'Extracts all load-bearing claims (statistics, product or policy claims, ranking and comparative claims, named sources)', 'validates cited URLs before fetching', 'scores match confidence', 'Flags uncited claims' — giving comprehensive coverage, matching the 5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (verify, extract, validate, score, flag) and 'when' ('Use when user says...') with concrete trigger phrases, satisfying the 5 anchor.	5 / 5
Trigger Term Quality	Provides natural trigger phrases users would actually say — 'fact check', 'verify statistics', 'check sources', 'validate claims', 'factcheck', 'source verification' — including synonyms (fact check/factcheck), matching the comprehensive 5 anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear blog-factchecking niche with distinct triggers ('fact check', 'source verification') and minimal overlap risk with other skills, matching the 5 anchor.	5 / 5
	Total	20 / 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: AgriciDaniel/claude-blog
Path: brain/.raw/sources/claude-blog-skill/skills/blog-factcheck/SKILL.md
Commit: 84f7abf

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.