CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A well-structured, actionable reference for twelve commands across eight Google APIs, with excellent progressive disclosure to verified bundle files. The main gap is the absence of explicit validation checkpoints for the batch operation modes.

Suggestions

For batch modes (gsc_inspect --batch, indexing_notify --batch), add an explicit validation checkpoint: verify the batch input file exists and is well-formed before sending, and report a per-URL success/failure summary after the run.

Add a short feedback loop for the Indexing API batch (e.g. stop or warn on the first 429/quota-exceeded response rather than firing the whole batch) since the 200-publish/day quota is easily exhausted.

Surface the credential-tier check as an explicit numbered first step in each command's workflow so the validation checkpoint is unmissable rather than stated once in Prerequisites.

DimensionReasoningScore

Conciseness

The body is lean: tables and one-line script invocations per command, with prose reserved for domain-specific caveats Claude would not reliably know (e.g. INP replacing FID, canonicalization re-evaluation window, generative-AI report rollouts). It assumes Claude's competence and avoids explaining basic concepts.

3 / 3

Actionability

Every command ships a concrete, copy-paste-ready invocation such as `python3 skills/blog-google/scripts/run.py pagespeed_check <url> --json`, with flags, defaults, and batch variants specified.

3 / 3

Workflow Clarity

A clear sequence exists (credential check → tier detection → command) with an error-handling table, but the batch modes (`gsc_inspect --batch`, `indexing_notify --batch`) lack explicit validation/verification checkpoints, which caps workflow clarity per the batch-operation guideline.

2 / 3

Progressive Disclosure

The body is an overview pointing to real, one-level-deep reference files (auth-setup.md, api-reference.md, rate-limits-quotas.md, search-currentness.md — all present in the bundle) plus assets/templates, with clearly signaled navigation and inline content appropriately limited to per-command essentials.

3 / 3

Total

11

/

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.

A dense, specific description that names every concrete capability, provides natural trigger phrases, and explicitly signals when to use the skill. Third-person voice is maintained throughout with no over-claims.

DimensionReasoningScore

Specificity

Lists many concrete actions — "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 ... Google Ads Keyword Planner" — each a specific capability rather than vague language.

3 / 3

Completeness

Explicitly answers both what (the enumerated API integrations and progressive credential tiers) and when (a dedicated "Use when user says ..." trigger clause), satisfying the both-what-and-when requirement.

3 / 3

Trigger Term Quality

The "Use when user says" clause gives natural phrases users would actually say — "google data", "page speed", "core web vitals", "search console", "GA4", "keyword research", "youtube search" — with broad coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly scoped to Google SEO APIs for blog performance, with distinct triggers and an explicit note that it "Shares config with claude-seo", making overlap with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
AgriciDaniel/claude-blog
Reviewed

Table of Contents

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.