Agent skill

Gsc SEO Optimizer

by davepoon in davepoon/buildwithclaude

Analyze Google Search Console exports or authorized API data to prioritize page improvements.

MITAuto-check passedMarketing & SEO

Install Gsc SEO Optimizer

skills CLI
$ npx skills add davepoon/buildwithclaude --skill gsc-seo-optimizer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davepoon/buildwithclaude gsc-seo-optimizer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/all-skills/skills/gsc-seo-optimizer .claude/skills/gsc-seo-optimizer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gsc-seo-optimizer
GitHub stars
3.6k
Token cost
~1.9k tokens
SKILL.md length
949 words
Files
13 (incl. scripts, references)
Skills in repo
247
Repo updated
First seen
Licence
MIT

At a glance

Analyze Google Search Console exports or authorized API data to prioritize page improvements.

  • Works in 4 steps: Supplied exports: CSV or ZIP can be… → Existing Google API access: prefer it… → Connected tools: inspect their actual… → …
  • Traffic changes
  • SKILL.md covers Establish scope and data route, Validate before interpreting, Prioritize and Deliver and optionally execute, plus 2 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Gsc SEO Optimizer is an agent skill from davepoon/buildwithclaude. Analyze Google Search Console exports or authorized API data to prioritize page improvements. Use for traffic changes, page/query opportunities, indexing evidence, and deciding when to leave recently edited or weakly supported pages alone.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including scripts and reference files (for example `references/data-access.md`, `references/data-quality.md` and `references/report-template.md`).

It sits in Marketing & SEO. It works with Google Search Console. The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.

When your agent uses it

  • Traffic changes
  • Page/query opportunities
  • Indexing evidence
  • Deciding when to leave recently edited

Example prompts

  • “/gsc-seo-optimizer”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Supplied exports: CSV or ZIP can be analyzed without credentials. Read references/data-access.md for the bundled local importer and export…
  2. Existing Google API access: prefer it for reproducible filtering and comparison. The same reference documents the bundled read-only…
  3. Connected tools: inspect their actual capabilities and verify property, scope, freshness, authorization and any cost before use.
  4. Available browser: use the user's available authorized browser integration for UI-only evidence or missing API access. On login, account…

What it can do on your machine

Read from SKILL.md and the folder at commit 616deb5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gsc SEO Optimizer loads about 1.9k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 949 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 616deb5, republished under its MIT licence (© davepoon). 949 words, ~1,890 tokens.

Download SKILL.mdSave it as .claude/skills/gsc-seo-optimizer/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
gsc-seo-optimizer
description
Analyze Google Search Console exports or authorized API data to prioritize page improvements. Use for traffic changes, page/query opportunities, indexing evidence, and deciding when to leave recently edited or weakly supported pages alone.
category
analytics
license
MIT

GSC SEO Optimizer

Turn the user's own search evidence into a small, justified optimization batch. Default to read-only diagnosis. Execute changes only within the user's explicit authorization; existing approval for a concrete batch remains valid. An analysis request never authorizes publishing or spending.

Establish scope and data route

Confirm the exact GSC property (domain property or URL prefix), target market, Web/other search type, and requested period. Verify the property returned by a connector matches the requested site before using any numbers. Do not choose the first accessible property. Infer from the user's site and supplied context when unambiguous; ask if multiple properties or markets remain plausible.

For ranking analysis use the user's target market, not a universal US default. Global performance totals may be useful separately; label them and never mix scopes in comparisons. If no market can be established, label aggregate findings and defer market-specific ranking claims.

Use the least-friction route already available:

  1. Supplied exports: CSV or ZIP can be analyzed without credentials. Read references/data-access.md for the bundled local importer and export requirements.
  2. Existing Google API access: prefer it for reproducible filtering and comparison. The same reference documents the bundled read-only fetcher, authentication, and URL Inspection.
  3. Connected tools: inspect their actual capabilities and verify property, scope, freshness, authorization and any cost before use.
  4. Available browser: use the user's available authorized browser integration for UI-only evidence or missing API access. On login, account selection, 2FA, or permission screens, let the user complete the interaction. Never extract cookies, browser profile data, or passwords. If browser access is unavailable, request exports and continue with available evidence rather than blocking all analysis.

Do not install packages/connectors or start OAuth unless needed and within the user's request. The CSV importer uses Python's standard library. API dependencies are optional and separate.

Validate before interpreting

Read references/data-quality.md before drawing conclusions. Every run must record property, date range, search type, country/device/page filters, data source, and completeness limitations.

  • Default to the most recent 28 complete GSC days, compared with the preceding non-overlapping 28 days when assessing change. Use 90 days for sparse sites and 7-day windows for recent releases, without treating short-term movement as causality.
  • Dates use GSC's Pacific-time calendar. Inclusive 28-day windows start 27 days before the end. Prefer finalized data and label the latest available date; a missing day is not proof of zero traffic or of ingestion completeness.
  • Get overall totals independently from page/query detail. Check row caps, pagination, anonymized queries, filter scope, and aggregation before reporting changes.
  • Separate brand, non-brand, and ambiguous terms using user-confirmed brand spellings/aliases. Inspect page-specific queries before calling a low-CTR page an opportunity; branded sitelinks are a common false signal.
  • Compare the same query and page when interpreting rank movement. An aggregate average can improve because lower-ranking queries disappeared.
  • Do not join separately exported page and query tables to invent query-to-page relationships. Without that evidence, offer page-level findings and state what targeted export is needed.
  • Impressions are not an indexing verdict. For indexing conclusions use URL Inspection or explicit UI evidence. Sitemap counts do not establish the indexed count of the whole site.

If query evidence is absent or too sparse, try a targeted page export/query or available UI. UI may also omit anonymized queries. If no stronger evidence is available, lower confidence and continue only with supported findings; never conclude that the page has no keywords.

Show full SKILL.md (388 more words)Show less

Prioritize

Read references/roi-rubric.md when ranking opportunities. Prefer relevant business intent, a plausible small intervention, and adequate evidence. Call this an opportunity assessment, not measured ROI unless conversion and cost data are supplied.

Distinguish ranking gaps, snippet/intent mismatch, missing query coverage, and confirmed technical problems. Do not diagnose intent mismatch from CTR alone. Two pages appearing for a query do not by themselves prove cannibalization.

Check recent edits in supplied change notes or repository history. Usually observe for at least 7–14 complete post-change days before another overlapping edit; larger ranking effects may take longer. Do not promise a time-to-impact.

Recommend only as many pages as the evidence supports, often 1–5 and sometimes none. For each include URL, scope, clicks/impressions/CTR/position, supporting queries, diagnosis, proposed action, business relevance, confidence, and review interval. Explain important skips. Keep broad informational, irrelevant report, and very sparse pages out of the batch unless a strategic reason is explicit.

Deliver and optionally execute

Lead with what changed and what to do next. State limitations that would change the decision. Use references/report-template.md to save a baseline when useful; analysis artifacts belong in the workspace and are not committed by default. Preserve private search data locally unless the user authorizes an external destination.

For approved edits, inspect the project's own instructions and content storage first. Follow existing code/CMS patterns and limit changes to approved pages. Back up changed CMS rows. Align copy with the page's actual functionality; add FAQ/schema only for visible supported content. Avoid mass year updates, keyword stuffing, speculative canonicals, or replacing useful conversion copy with generic SEO prose.

Verify the relevant rendered title, description, canonical, robots, schema, links, and visible content. Run the project's checks appropriate to the changes. Deploy only if authorized. Record changed URLs, edit/deployment dates, baseline, expected mechanism, and review interval. A later comparison can show association, not isolate the edit's causal effect.

Bundled tools and validation

Use scripts/import_gsc.py for local CSV/ZIP exports. The optional scripts/gsc_fetch.py requires scripts/requirements-api.txt and authorized Google access; setup is in the data-access reference. Python 3.9 or newer is required.

Run python3 -m unittest discover -s tests -v from this skill directory. tests/test_gsc.py checks parsing, scope, date windows, pagination and read-only request construction using synthetic fixtures. API responses are mocked; these tests do not prove live authorization or host compatibility.

Provenance

Adapted from Tracetify Skills, MIT. See LICENSE.

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references) in plugins/all-skills/skills/gsc-seo-optimizer of davepoon/buildwithclaude.

  • SKILL.md
  • LICENSE
  • references/data-access.md
  • references/data-quality.md
  • references/report-template.md
  • references/roi-rubric.md
  • scripts/gsc_fetch.py
  • scripts/import_gsc.py
  • scripts/requirements-api.txt
  • tests/fixtures/Filters.csv
  • tests/fixtures/Pages.csv
  • tests/fixtures/Queries.csv
  • tests/test_gsc.py

Open the folder on GitHubat commit 616deb5

Compare with similar skills

Gsc SEO Optimizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gsc SEO Optimizer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gsc SEO Optimizer this skilldavepoon/buildwithclaude3.6k—~1.9kAutomated safety check: PassMIT
Google SEO APIsAgriciDaniel/claude-seo19k1 repos~4.2kAutomated safety check: PassMIT
Blog GoogleAgriciDaniel/claude-blog2.3k1 repos~3.3kAutomated safety check: NotesMIT
SEO GodAKCodez/seo-god113—~2.2kAutomated safety check: PassMIT
SEO Coachakseolabs-seo/seo-coach146—~2.8kAutomated safety check: PassNone
SEO Setupalisamadiii/Portfolio180—~1.7kAutomated safety check: PassNone

Similar skills

  • Google SEO APIs

    AgriciDaniel/claude-seo

    Pulls real Google data for SEO work: Search Console, PageSpeed Insights, CrUX field data, the Indexing API and GA4 organic traffic, through /seo google commands.

    19k GitHub starsUsed in 1 repo~4.2k tokens
    Marketing & SEOAuto-check passed
  • Blog Google

    AgriciDaniel/claude-blog

    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…

    2.3k GitHub starsUsed in 1 repo~3.3k tokens
    Marketing & SEOAuto-check: notes
  • SEO God

    AKCodez/seo-god

    Agentic SEO operator for your own website: audits and fixes your site with OpenSEO, measures rankings + Google Search Console, works to get ChatGPT and other AI engines citing you, and schedules the…

    113 GitHub stars~2.2k tokensUpdated 2 mo ago
    Marketing & SEOAuto-check passed
  • SEO Coach

    akseolabs-seo/seo-coach

    Beginner-first SEO coaching for people who want to learn by doing one safe, verifiable step at a time.

    146 GitHub stars~2.8k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • SEO Setup

    alisamadiii/Portfolio

    Full SEO/metadata setup and audit for client websites (Astro, Next.js, any static site).

    180 GitHub stars~1.7k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • SEO Coach

    petera2c/simple-table

    Enter a friendly OpenSEO coach mode that explains workflows, recommends next steps, and helps users use agents, web search, scraping, and MCP data effectively.

    229 GitHub starsUsed in 2 repos~1.2k tokens
    Marketing & SEOAuto-check passed

More from davepoon/buildwithclaude

All 247 skills in this repo
  • iOS Hig Design Guide

    davepoon/buildwithclaude

    Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.

    3.6k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • Video Downloader

    davepoon/buildwithclaude

    Download YouTube videos with customizable quality and format options.

    3.6k GitHub starsUsed in 1 repo~871 tokens
    Auto-check passed
  • Qwen Vision

    davepoon/buildwithclaude

    A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…

    3.6k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Atlas Cloud Media

    davepoon/buildwithclaude

    Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.

    3.6k GitHub stars~852 tokensUpdated yesterday
    Auto-check passed
  • Browser Extension Launch

    davepoon/buildwithclaude

    面向没有编程经验的用户,把想法做成可试用的浏览器插件,并完成检查、商店材料、审核提交和上线验证;也用于继续已有插件、排错和发布新版。用户说“帮我做个插件”“把插件上架”“继续我的插件”时使用。普通网站开发、仅查询插件知识不触发。

    3.6k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Slack Gif Creator

    davepoon/buildwithclaude

    Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.

    3.6k GitHub starsUsed in 12 repos~4.3k tokens
    Auto-check passed

Categories

Questions about Gsc SEO Optimizer

What does Gsc SEO Optimizer do?

Analyze Google Search Console exports or authorized API data to prioritize page improvements. Gsc SEO Optimizer is an agent skill from davepoon/buildwithclaude. Analyze Google Search Console exports or authorized API data to prioritize page improvements.

When should I use Gsc SEO Optimizer?

Gsc SEO Optimizer fits situations like: traffic changes; page/query opportunities; indexing evidence; deciding when to leave recently edited.

How do I install Gsc SEO Optimizer in Claude Code?

Run `npx skills add davepoon/buildwithclaude --skill gsc-seo-optimizer -a claude-code`. Or copy the skill folder (plugins/all-skills/skills/gsc-seo-optimizer in davepoon/buildwithclaude) into .claude/skills/gsc-seo-optimizer in your project. Claude Code loads it when a task matches its description.

How do I install Gsc SEO Optimizer in Codex?

Run `npx skills add davepoon/buildwithclaude --skill gsc-seo-optimizer -a codex`. Or copy the skill folder (plugins/all-skills/skills/gsc-seo-optimizer in davepoon/buildwithclaude) into .agents/skills/gsc-seo-optimizer in your project. Codex loads it when a task matches its description.

Can I use Gsc SEO Optimizer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davepoon/buildwithclaude --skill gsc-seo-optimizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gsc-seo-optimizer, .gemini/skills/gsc-seo-optimizer, .github/skills/gsc-seo-optimizer and .opencode/skills/gsc-seo-optimizer in your project.

What does Gsc SEO Optimizer need to run?

Going by SKILL.md and its folder, Gsc SEO Optimizer needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Gsc SEO Optimizer access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Gsc SEO Optimizer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Gsc SEO Optimizer use?

Gsc SEO Optimizer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gsc SEO Optimizer use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Gsc SEO Optimizer?

Skills that share tags, products or a category with Gsc SEO Optimizer: Google SEO APIs (AgriciDaniel/claude-seo, 19k stars), Blog Google (AgriciDaniel/claude-blog, 2.3k stars), SEO God (AKCodez/seo-god, 113 stars) and SEO Coach (akseolabs-seo/seo-coach, 146 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gsc SEO Optimizer?

davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,610 GitHub stars. The repository holds 247 skills in this directory. The repository was last updated on October 9, 2026.

Source: davepoon/buildwithclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.