Yao Deepseek Crawler
Use when a user provides DeepSeek web AI-search keywords, repeat count, target entity...
Install
npx skills add yaojingang/yao-geo-skills --skill yao-deepseek-crawler -g -a claude-code -y- Repository
- yaojingang/yao-geo-skills912
- Category
- Marketing
- Updated
- 1mo ago
- License
- MIT
- Context cost
- Lightabout 539 tokens
- Runs scripts
- Yes, review before use
What it does
Use when a user provides DeepSeek web AI-search keywords, repeat count, target entity, and entity type, then needs repeated fresh-window crawls aggregated into JSON plus a Kami HTML GEO report. Not for generic website crawling, DeepSeek API chat, SEO writing, or one-off answer generation.
Yao DeepSeek Crawler
Inputs
Standard inputs: keywords/questions, repeat count, target entity, entity type (人/person, 公司/company, 产品/product), browser profile, and optional output directory. Competitors must match the target type. Reports default to Simplified Chinese with an English summary toggle.
Workflow
- Read
references/user-setup-and-usage.mdfor install, prerequisites, and user-facing steps. - Read
references/deepseek-crawl-workflow.mdfor crawler setup, preflight, delay, resume, and batch rules. - Read
references/report-contract.mdfor JSON schema, metrics, target/competitor recognition, and report rules. - Run
node scripts/preflight.mjs --profile <profile>before fresh crawling. - Stage 1: run
scripts/deepseek_batch_crawl.mjswith questions, repeat, profile, target entity/type,--safe-random-delay, and output dir. - Stage 2: run
scripts/analyze_deepseek_results.pyon any crawl JSON with target entity/type, optional brands file, report output dir, and semantic review mode. Use--semantic-review autoby default; use--semantic-review requiredfor formal delivery when AI review must pass. - Return the raw crawl JSON, structured Markdown, structured Excel workbook, HTML report, summary JSON, semantic-review cache when present, and failed logs. Reports include AI semantic labels for entity recognition, target-vs-best-3 radar, click-to-reveal bubbles, Chinese source names, clickable citations, title intent, compact treemap, and GEO actions.
