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.

The body is a well-structured, actionable instruction skill with a clear validated workflow and concrete scoring rules. Its main weakness is that all reference material lives inline in a single file rather than being split into one-level-deep bundle references.

Suggestions

Move the Source Tier table and Verification Scoring rubric into a references/ file (e.g. references/scoring.md) and link to it from the body to improve progressive disclosure and reduce baseline token load.

Tighten the Cross-reference section's provenance explanation to a brief pointer to flow-framework.md rather than restating the evidence-discipline rationale.

Consider extracting the Claim Extraction Patterns list into a reference file so the main SKILL.md stays a concise overview of the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — skill-specific tables (claim types, source tiers, scoring rubric) earn their tokens rather than restating general knowledge — but a few passages (e.g. the Cross-reference provenance explanation) could be tightened, so it sits above the score-3 anchor but not fully lean at 5.	4 / 5
Actionability	Provides concrete executable guidance: specific URL-validation rules (allow http/https only, reject localhost/loopback/private IPs, reject javascript:/data:/file:, cap size and timeout), explicit scoring examples ('43%' vs 'nearly half' = 0.8), and a copy-paste output template — fully actionable for an instruction-only skill.	5 / 5
Workflow Clarity	A clear 5-step sequence carries explicit validation checkpoints (pre-fetch URL validation, source-tier and echo-cluster classification, context/geography/timeframe matching) plus batch feedback loops (resumable output, rate limiting, user cutoff handling), matching the score-5 anchor.	5 / 5
Progressive Disclosure	Content is well-organized with clear section headers and a clearly-signaled one-level external reference (skills/blog-flow/references/flow-framework.md), but with no bundle files present everything is inlined in one ~175-line file where some material (source tiers, scoring rubric) could be split out, leaving it just short of the score-5 ideal.	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.

The description is specific, complete, and well-triggered: it states concrete actions, includes natural trigger phrases with synonyms, and clearly distinguishes the skill's niche. It uses correct third-person voice and answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fetching cited source URLs', 'Extracts all load-bearing claims', 'validates cited URLs before fetching', 'scores match confidence', 'Flags uncited claims as UNVERIFIED' — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Clearly answers both 'what' (verify claims by fetching sources, extract load-bearing claims, score confidence, flag uncited) and 'when' with concrete trigger phrases, and uses third-person voice throughout.	5 / 5
Trigger Term Quality	Provides natural trigger phrases users would say — 'fact check', 'verify statistics', 'check sources', 'validate claims', 'factcheck', 'source verification' — including synonyms and a variant spelling, matching the comprehensive score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (blog post source verification) with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche score-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: 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.