Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides a framework for Generative Engine Optimization (GEO), helping strategists analyze how AI search engines perceive specific entities. It transforms raw crawl data into structured reports to identify gaps between target entities and their competitors.
By focusing on semantic density and source-bound evidence, the tools allow for the systematic rewriting of articles to improve their friendliness toward AI search algorithms.
WHO IT'S FOR
GEO / AI-search strategists
optimizing content for AI search visibility
Market intelligence analysts
conducting target-vs-competitor AI search diagnosis
AI automation engineers
building automated AI-search data pipelines
Content marketers
improving article citation-readiness for AI engines
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Existing article text or a readable local .md, .txt, .html, .htm, .docx, or .pdf path
Any source material available to support the article's claims
Make sure yao-geo-article-friendly is installed in your agent before trying this task.
Use the yao-geo-article-friendly skill at standard depth to improve the GEO and AI-search readiness of the article at [local article path], or of the article text pasted below. Preserve its meaning, facts, examples, title, and tone. Return the optimized article, GEO score report, change notes, requested supplements, and risk notes in one structured Markdown response. Mark unsupported additions as suggestions rather than inventing evidence.
Relevant competitors, scenarios, constraints, and business materials if available
Make sure yao-geo-intent-miner is installed in your agent before trying this task.
Use the yao-geo-intent-miner skill to expand [seed terms] for [brand or product] into a focused AI-search question set for [target audience and region]. Include intent clusters, follow-up chains, query rewrites, and initial content or FAQ mappings. Clearly identify the real-data mode and list data gaps instead of inventing platform answers, search volume, or conversion data.
Available browser interaction and screenshot-saving capability
Make sure yao-geo-baidu-keywords is installed in your agent before trying this task.
Use the yao-geo-baidu-keywords skill to collect Baidu autocomplete and first-page “related searches” for [target keyword]. Use [industry] and [conversion goal] as the commercial-value scoring context. Capture genuine browser screenshots, preserve displayed order and source details, and deliver the resulting Excel, JSON, and evidence screenshot directory. Report blocked, empty, or unavailable results honestly.
Codex
DeepSeek