gsc
The gsc skill queries Google Search Console to retrieve SEO performance data including search queries, top pages, click-through rates, and indexing status. Use it to analyze search visibility, identify optimization opportunities for high-impression low-CTR pages, inspect URL indexing status, and verify sitemap health across specified time periods and dimensions like device type or country.
git clone --depth 1 https://github.com/jdrhyne/agent-skills /tmp/gsc && cp -r /tmp/gsc/skills/gsc ~/.claude/skills/gscSKILL.md
# Google Search Console Skill Query GSC for search analytics, indexing status, and SEO insights. ## Setup 1. **Credentials**: Uses same OAuth credentials as GA4 skill (stored in `.env`) 2. **Scopes**: Requires `webmasters.readonly` scope on your Google Cloud OAuth consent screen 3. **Access**: Your Google account must have access to the Search Console properties 4. **Run location**: Commands below use relative paths — run them from this skill's directory (`cd` into it first) ## Commands ### List Available Sites ```bash source .env && \ python3 scripts/gsc_query.py sites ``` ### Top Search Queries ```bash source .env && \ python3 scripts/gsc_query.py top-queries \ --site "https://www.nutrient.io" \ --days 28 \ --limit 20 ``` ### Top Pages by Traffic ```bash source .env && \ python3 scripts/gsc_query.py top-pages \ --site "https://www.nutrient.io" \ --days 28 \ --limit 20 ``` ### Find Low-CTR Opportunities High impressions but low click-through rate = optimization opportunities: ```bash source .env && \ python3 scripts/gsc_query.py opportunities \ --site "https://www.nutrient.io" \ --days 28 \ --min-impressions 100 ``` ### Inspect URL Indexing Status ```bash source .env && \ python3 scripts/gsc_query.py inspect-url \ --site "https://www.nutrient.io" \ --url "/sdk/web" ``` ### List Sitemaps ```bash source .env && \ python3 scripts/gsc_query.py sitemaps \ --site "https://www.nutrient.io" ``` ### Raw Search Analytics (JSON) ```bash source .env && \ python3 scripts/gsc_query.py search-analytics \ --site "https://www.nutrient.io" \ --days 28 \ --dimensions query page \ --limit 100 ``` ## Available Dimensions - `query` - Search query - `page` - Landing page URL - `country` - Country code - `device` - DESKTOP, MOBILE, TABLET - `date` - Date ## Metrics Returned - **clicks** - Number of clicks from search - **impressions** - Number of times shown in search - **ctr** - Click-through rate (clicks/impressions) - **position** - Average ranking position ## SEO Use Cases 1. **Content Optimization**: Find high-impression/low-CTR pages → improve titles & descriptions 2. **Keyword Research**: See what queries bring traffic → create more content around them 3. **Technical SEO**: Check indexing status, find crawl issues 4. **Ranking Tracking**: Monitor position changes over time 5. **Sitemap Health**: Verify sitemaps are submitted and error-free ## Notes - Data has ~3 day delay (GSC limitation) - Credentials shared with GA4 skill - URL inspection requires the page to be in the property
Automatically update OpenClaw and selected skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Check for new OpenClaw releases and notify once per new version.
OpenClaw documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all OpenClaw features
Bulk download images from login-protected gallery websites using an attached browser session. Use when asked to scrape, download, or save images from authenticated gallery pages, extract full-size images from thumbnails, or batch download from multi-page galleries.
Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.
Persistent TODO scratch pad for tracking tasks across sessions. Use when user says "add to TODO", "what's on the TODO", "mark X done", "show TODO list", "remove from TODO", or asks about pending tasks. Also triggers on heartbeat to remind about stale items.