blog-audit

Full-site blog health assessment scanning all blog files for quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness. Runs canonical batch analysis before site-wide checks. Produces per-post scores and a prioritized action queue. Use when user says "audit blog", "blog audit", "site audit", "blog health", "audit all posts", "check all blogs".

Quality

82%

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

65%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 thorough, well-structured audit procedure with concrete specifics, but it is a monolithic file with no progressive disclosure to bundle references and lacks explicit validation checkpoints for its batch operation.

Suggestions

Add explicit validation/verification checkpoints to the batch workflow — e.g. 'Verify analyze_blog.py JSON is well-formed and non-empty before layering site-wide checks' and 'Confirm the saved report file exists before informing the user' — to lift workflow clarity above the batch-operation cap of 3.

Move the detailed per-layer checklists (Content Quality, SEO, Schema, Link, Freshness, AI Readiness) and the report table templates into reference files under references/ with clearly signaled one-level-deep links, so SKILL.md stays a lean overview.

Either bundle scripts/analyze_blog.py so the referenced command is real and executable, or rephrase the Step 2 invocation to describe the expected JSON contract without implying a script that is absent from the bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense with specific thresholds and field names and avoids explaining concepts Claude already knows, but the ~240 lines include several repeated placeholder table templates that could be trimmed.	4 / 5
Actionability	It gives one executable command plus exact field names, thresholds, globs, and output schemas, but the graph-building and clustering steps are described concretely rather than as copy-paste code, leaving minor gaps.	4 / 5
Workflow Clarity	Steps 1–7 are clearly sequenced, but this batch operation over all blog files lacks explicit validate→fix→retry checkpoints (e.g. verify analyzer JSON before layering checks), which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections are well-organized, but everything is inlined into one ~240-line file with no bundle references — the referenced scripts/analyze_blog.py does not exist in the bundle — so content that could live in separate files is inline.	3 / 5
	Total	14 / 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, well-constructed description: concrete capabilities, six natural trigger phrases, explicit what-and-when, and a distinct niche in third-person voice. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — scanning for 'quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness', running 'canonical batch analysis', and producing 'per-post scores and a prioritized action queue' — giving comprehensive, non-generic coverage.	5 / 5
Completeness	It explicitly answers both 'what' (the full-site assessment and its outputs) and 'when' (concrete trigger phrases via the 'Use when user says' clause), matching the anchor example closely.	5 / 5
Trigger Term Quality	The 'Use when user says' clause lists six natural user utterances ('audit blog', 'blog audit', 'site audit', 'blog health', 'audit all posts', 'check all blogs') with synonyms and phrasing variations a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The full-site blog-health-audit niche with dedicated audit triggers is clearly distinguishable from sibling blog skills, uses third-person voice, and carries minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: brain/.raw/sources/claude-blog-skill/skills/blog-audit/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.