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

88%

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

77%

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

The body is actionable with a clear, validated workflow, but it is somewhat verbose and monolithic rather than progressively disclosed across reference files.

Suggestions

Tighten the Verification Scoring and Source Tier sections — collapse redundant guidance and worked examples to reduce token load on the score-3 conciseness anchor.

Move the Claim Extraction Patterns and Source Tier/Echo Checks material into separate reference files (e.g. references/claim-patterns.md, references/source-tiers.md) and link from the body to improve progressive disclosure.

Trim the verbose Step 3 sub-list into a tighter checklist so the workflow reads leaner while preserving the validation checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and avoids explaining concepts Claude already knows, but the ~175-line body is padded with extensive scoring-guidance examples and tier/echo detail that could be tightened; not quite the lean score-3 anchor.	2 / 3
Actionability	Provides concrete claim fields, a source-tier table, explicit scoring rules with worked examples ("43%" vs "nearly half" scores 0.8), and a complete output format — actionable, copy-ready guidance even for an instruction-only skill.	3 / 3
Workflow Clarity	A clear five-step sequence with sub-steps and explicit validation checkpoints (validate URL before fetching, assign source tier before scoring, re-validate on failure) plus batch/rate-limit/resume handling.	3 / 3
Progressive Disclosure	Single monolithic file with well-organized sections but no bundle files; for a skill this length, the claim-extraction patterns and source-tier material could be split into separate reference files rather than kept inline.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is specific, trigger-rich, and complete, with concrete actions and an explicit use-when clause in third person. It is clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "fetching cited source URLs", "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" — matching the score-3 anchor.	3 / 3
Completeness	Clearly answers both what (extract/validate/score/flag) and when, with an explicit "Use when user says..." trigger clause meeting the score-3 anchor.	3 / 3
Trigger Term Quality	"Use when user says 'fact check', 'verify statistics', 'check sources', 'validate claims', 'factcheck', 'source verification'" gives good coverage of natural phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche — verifying blog-post statistics against fetched cited URLs — is distinct with dedicated triggers, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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: aec971a

Reviewed: about 13 hours 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.