Individual skill

yao-doubao-crawler

Use when a user needs repeated Doubao AI-search collection from web or Android Appium into compatible JSON plus Markdown/Excel/HTML GEO reports. Requires keywords/questions and repeat count; target entity/type are required only for target-vs-competitor diagnosis. Not for generic scraping, Doubao API chat, hidden API extraction, SEO writing, high-frequency automation, or one-off answers.

skills/yao-doubao-crawler/SKILL.md

Read pinned source

Source commit d21bfc1a7729a4b1baee896bdc51aab1caaf602a

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 10, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 915
Repository last updated: Oct 1, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

ai-agent Repository topic
automation Repository topic
cli Repository topic
codex Repository topic
geoflow Repository topic
skills Repository topic
workflow Repository topic
marketing Derived category
writing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.gitignoreasset · 122 bytes
.skillignoreasset · 122 bytes
README.mddoc · 9,365 bytes
SKILL.mdcore · 1,900 bytes
agents/interface.yamlasset · 1,775 bytes
evals/expected_artifacts.jsonasset · 1,220 bytes
evals/trigger_cases.jsonasset · 1,210 bytes
examples/README.mddoc · 405 bytes
fixtures/sample-doubao-crawl.jsonasset · 7,611 bytes
fixtures/sample-doubao-mobile-crawl.jsonasset · 8,614 bytes
manifest.jsonasset · 3,307 bytes
references/doubao-crawl-workflow.mddoc · 5,772 bytes
references/mobile-appium-workflow.mddoc · 8,667 bytes
references/report-contract.mddoc · 18,062 bytes
references/user-setup-and-usage.mddoc · 13,728 bytes
reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/report.htmlasset · 110,392 bytes
reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/structured-data.mddoc · 100,446 bytes
reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/structured-data.xlsxasset · 58,484 bytes
reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/summary.jsonasset · 351,334 bytes
requirements-mobile.txtdoc · 28 bytes
scripts/analyze_doubao_results.pyruns · 212,395 bytes
scripts/doubao_batch_crawl.mjsruns · 20,168 bytes
scripts/doubao_browser_crawl.mjsruns · 14,821 bytes
scripts/doubao_mobile_crawl.pyruns · 88,484 bytes
scripts/preflight.mjsruns · 11,903 bytes
scripts/run-tests.shruns · 927 bytes
scripts/test_doubao_browser_crawl.mjsruns · 5,816 bytes
scripts/test_entity_recognition.pyruns · 5,863 bytes
scripts/test_mobile_extraction.pyruns · 14,976 bytes
templates/brief-template.mddoc · 491 bytes

Read excerpt


# 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

1. Read `references/user-setup-and-usage.md`, `references/doubao-crawl-workflow.md`, and `references/report-contract.md`.
2. For Android/Appium, also read `references/mobile-appium-workflow.md` and run `python3 scripts/doubao_mobile_crawl.py preflight ...`.
3. Stage 1 web: run `scripts/doubao_batch_crawl.mjs`.
4. Stage 1 mobile: run `scripts/doubao_mobile_crawl.py batch`; use `--fresh-chat --require-fresh-chat` when samples must start in separate Doubao app conversations.
5. Stage 2: run `scripts/analyze_doubao_results.py` on the compatible crawl JSON.
6. Use `evals/` and `templates/` for packaging checks and collection briefs.