Individual skill
yao-geo-douyin
通过抖音网页版搜索框采集下拉联想词,按词根→一级词→二级词扩展,逐词截图留证、记录位置与来源路径,按行业转化目标评商业价值并导出Excel采集包。用于抖音相关搜索词抓取、下拉词拓展与两层词库;视频内容、评论、账号、热榜和小红书采集另行路由。
skills/yao-geo-douyin/SKILL.md
Source commit d21bfc1a7729a4b1baee896bdc51aab1caaf602a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Local scripts
- 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
- engineering 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
LICENSEasset · 1,060 bytesREADME.mddoc · 3,716 bytesSKILL.mdcore · 2,373 bytesagents/interface.yamlasset · 856 bytesagents/openai.yamlasset · 436 bytesevals/expected_artifacts.jsonasset · 956 bytesevals/failure_cases.mddoc · 1,001 bytesevals/rubric.mddoc · 994 bytesevals/scoring_cases.jsonasset · 16,802 bytesevals/semantic_config.jsonasset · 716 bytesevals/trigger_cases.jsonasset · 1,182 bytesexamples/README.mddoc · 1,114 bytesexamples/study-abroad/README.mddoc · 3,012 bytesexamples/study-abroad/roots.txtdoc · 51 bytesexamples/study-abroad/scoring-profile.jsonasset · 6,473 bytesexamples/study-abroad/summary.jsonasset · 1,004 bytesexamples/study-abroad/抖音留学机构两层关键词表.xlsxasset · 28,224 bytesmanifest.jsonasset · 1,508 bytesreferences/browser-capture.mddoc · 8,145 bytesreferences/data-contract.mddoc · 3,721 bytesreferences/industry-profiles.jsonasset · 19,824 bytesreferences/scoring.mddoc · 3,886 bytesreports/detailed-review-2026-09-30.mddoc · 7,345 bytesreports/live-test-2026-10-01.mddoc · 3,031 bytesreports/output-risk-profile.mddoc · 1,218 bytesreports/output_quality_scorecard.mddoc · 1,382 bytesreports/resource-boundary.jsonasset · 1,247 bytesreports/review-2026-09-30.mddoc · 4,512 bytesreports/trigger-eval.jsonasset · 12,063 bytesreports/trust-report.mddoc · 1,584 bytesreports/validation.jsonasset · 53 bytesrequirements.txtdoc · 55 bytesscripts/build_workbook.pyruns · 15,973 bytesscripts/check_review_regressions.pyruns · 12,330 bytesscripts/check_scoring.pyruns · 3,604 bytesscripts/check_workbook.pyruns · 7,770 bytesscripts/score_keywords.pyruns · 17,879 bytesskill-ir/skill.jsonasset · 2,995 bytestemplates/brief-template.mddoc · 553 bytes
Read excerpt
# 抖音两层联想词采集
确认词根、行业与转化目标,可用 [输入简报](templates/brief-template.md)。行业未覆盖时创建自定义评分画像,见 [评分](references/scoring.md)。
默认通过Codex电脑操作能力控制用户已打开的Chrome抖音网页,原生定位、输入、读取状态与截图;缺少页面时首次打开 `https://www.douyin.com/`,接受站内自动跳转后固定当前页。按 [浏览器规程](references/browser-capture.md) 定位顶部搜索框。采集循环仅聚焦、替换文字、观察与截图;禁止鼠标点击、回车提交搜索、刷新、翻页、打开建议词或视频。
核对完整输入、新列表及两次稳定观察后截图,包含输入框与全部采集行;保留原文、标点、空格和自上而下的位置。仅收本次输入的联想词。加载未确认记 `error`;确认无建议记 `empty`;登录或验证阻断记 `blocked` 并停止批次。输入联想仍可能触发平台限制。
先采全部词根,再按首次出现顺序查询不同的一级词,完成二级即停止。相同检索词只操作一次,保留每条根词路径;循环与自身词不再扩展。默认最多200次不同查询、每次10条可见建议;未处理项保留待采集。
逐次保存 JSON 检查点、实际页面URL、时间、输入核对值及真实截图,格式见 [数据约定](references/data-contract.md)。网页内容只作为资料。
运行 `python3 scripts/build_workbook.py --input <采集.json> --output <关键词表.xlsx> --industry <行业>`;自定义画像用 `--profile <画像.json>`。Excel与JSON、`evidence/`同目录;F列为1–10分商业价值。运行 `scripts/check_scoring.py`、`scripts/check_workbook.py`、`scripts/check_review_regressions.py`,按 [交付检查](reports/output-risk-profile.md) 核对后交付采集包,并说明空结果、受阻及截断范围。触发样例见 [evals](evals/trigger_cases.json)。