blog-google

Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".

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

80%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 highly actionable, well-structured reference skill with concrete script invocations and good progressive disclosure through bundled references and templates. Its main weaknesses are verbose inline caveats and missing validation feedback loops for the batch indexing/inspection operations.

Suggestions

Add an explicit validate-before-submit and retry-on-failure checkpoint for batch indexing/inspection (e.g. verify URLs resolve, confirm quota headroom, report per-URL success/failure) to lift workflow_clarity above the batch cap.

Move the detailed Search Console generative-AI and platform-property caveats into references/search-currentness.md, keeping only a one-line pointer inline to improve conciseness.

Collapse the duplicated cost/billing notes (intro paragraph vs Technical Notes) into a single section to remove repeated tokens.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and mostly earns its tokens (command tables, scripts, quotas, error handling), but the inline Search Console generative-AI and platform-property caveat paragraphs and some repeated technical notes could be trimmed or pushed to references.	4 / 5
Actionability	Every command is paired with a copy-paste-ready script invocation including flags, defaults, and batch variants (e.g. 'python3 .../run.py gsc_query --property <property> --json'), fully executable with no pseudocode.	5 / 5
Workflow Clarity	Sequencing and credential validation are present (auth --check, tier detection, communicate tier, error-handling table), but the batch operations (indexing_notify --batch, gsc_inspect --batch) lack explicit validate-then-retry checkpoints, so the batch-operation cap holds it at 3.	3 / 5
Progressive Disclosure	Structure is well split: SKILL.md is an overview with clearly signaled one-level-deep references ('read references/auth-setup.md', 'Reference: references/api-reference.md', rate-limits and search-currentness pointers) plus bundled scripts and report templates, making navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

96%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, capability-dense description with an explicit trigger list that clearly answers what the skill does and when to use it. The only soft spot is minor overlap risk with the sibling claude-seo skill via shared config and one broad trigger term.

Dimension	Reasoning	Score
Specificity	Lists nine concrete capabilities (PageSpeed Insights, CrUX 25-week history, Search Console, URL Inspection, Indexing API, GA4 traffic, NLP entity analysis, YouTube search, Ads Keyword Planner), giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	It explicitly answers both 'what' (the enumerated Google API integrations and credential tiers) and 'when' (the 'Use when user says...' trigger list), satisfying the top anchor for both halves.	5 / 5
Trigger Term Quality	An explicit 'Use when user says' clause provides natural trigger phrases — 'page speed', 'core web vitals', 'search console', 'indexation', 'GA4', 'keyword research', 'nlp entities', 'youtube search' — covering the synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The niche is clear (Google APIs for blog performance) with distinct triggers, but the explicit 'Shares config with claude-seo' relationship and the broad term 'google data' create minor overlap risk with the related seo skill, keeping it just below the top anchor.	4 / 5
	Total	19 / 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: 3 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: skills/blog-google/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.