SKILL.md
Yao Doubao Crawler
Inputs
Collect with keywords/questions, repeat count, backend (web or mobile), connection fields, and output dir. Add target entity + entity type for standard diagnosis. Without a target, generate exploratory output and label inferred candidates as heuristic.
Workflow
- Read
references/user-setup-and-usage.md, references/doubao-crawl-workflow.md, and references/report-contract.md.
- For Android/Appium, also read
references/mobile-appium-workflow.md and run python3 scripts/doubaomobilecrawl.py preflight ....
- Stage 1 web: run
scripts/doubaobatchcrawl.mjs.
- Stage 1 mobile: run
scripts/doubaomobilecrawl.py batch; use --fresh-chat --require-fresh-chat when samples must start in separate Doubao app conversations.
- Stage 2: run
scripts/analyzedoubaoresults.py on the compatible crawl JSON.
- Use
evals/ and templates/ for packaging checks and collection briefs.
- Return crawl JSON,
summary.json, structured Markdown/Excel, HTML report, screenshots/XML for mobile, failed logs, and mobile search-material evidence when present.
Honest Boundaries
- Do not bypass login, CAPTCHA, risk controls, hidden APIs, network traffic, or app storage.
- Android/Appium is low-frequency visible UI evidence capture.
- Probability and competitor metrics are repeated-sample estimates; review aliases before external use.
- Preserve raw answers, references, URLs, screenshots/XML, and logs.