patent-search
Skill2 starsChanged 39 days agoMITView on GitHub
中国专利公布公告著录检索:发明人、申请人、分类号、名称、摘要;也可从单图或权利要求生成名称/摘要关键字后查询。
8 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- RobThePCGuy/Claude-Patent-Creatortheir own version, first seen Oct 13, 2026
- ZimoLiao/scholaraiotheir own version, first seen Oct 8, 2026
- handsomestWei/patent-disclosure-skilledited, first seen Oct 8, 2026
- Open2Loop/claude-patent-skillstheir own version, first seen Oct 8, 2026
- Madyleisured4213/patent-disclosure-skilledited, first seen Sep 3, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- handsomestWei/patent-disclosure-skill★ 13k45% same
- Madyleisured4213/patent-disclosure-skill★ 023% same
Wrote their own version · 6
- ZimoLiao/scholaraio★ 585same name
- RobThePCGuy/Claude-Patent-Creator★ 211same name
- MrEgg2021/patent-skills★ 8same name
- Open2Loop/claude-patent-skills★ 4same name
- Linearl/reasonix_skill_repo★ 3same name
- lengrufeng2008/dsh-skill-library★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository40 other files it gives its agents.
- admin-credential-bootstrapSkill
- ai-code-review-gateSkill
- ai-debt-ledgerSkill
- android-camera-devSkill
- android-device-debuggingSkill
- arch-dev-workflowSkill
- askills-syncSkill
- async-job-sse-upload-devSkill
- branching-workflowSkill
- disk-capacity-guardSkill
- edge-offline-pipeline-devSkill
- frontend-dev-workflowSkill
- github-ci-releaseSkill
- git-identitySkill
- installer-bundle-designSkill
- installer-preflightSkill
- installer-target-executionSkill
- mqtt-device-gateway-devSkill
- observability-designSkill
- ohos-media-devSkill
- onvif-rtsp-devSkill
- open-source-contributionSkill
- patent-applicationSkill
- patent-chartSkill
- patent-disclosureSkill
- patent-docketSkill
- patent-exam-policySkill
- patent-mapSkill
- patent-oaSkill
- patent-readerSkill
- project-brandingSkill
- redis-stream-rpcSkill
- robot-camerasSkill
- skill-distillationSkill
- skill-refreshSkill
- solution-racingSkill
- subagent-parallel-devSkill
- ui-responsive-listSkill
- user-facing-errorsSkill
- web-launch-dxSkill
The file
Files
著录检索
用途
公布站高级查询(发明人 / 申请人 / 分类号 / 名称 / 摘要等)。个人公开清单只是一种用法。单图或权要可先抽关键字再查。对照表派工时可按特征精排,另出覆盖旁路,不改列表报告。
何时用
用户要按著录字段查公布公告、个人公开清单、以图或权要生成检索式,或 /patent-search。对照表派工或用户点名「按特征精排」时再走 covers_rank.md。
输入
至少一项:发明人、申请人、分类号、名称、摘要/简要说明、申请号或公开号。单图必须 --type design|utility_model|invention,不能 all;用户没说类型时看图推断并加 --type-inferred。权要按文本选类型,可用 all。
步骤
先 Read prompts/patent_search.md。 用户给单图或权要时再 Read prompts/derived_query.md。对照表派工或用户点名「按特征精排」时再 Read prompts/covers_rank.md。翻页口径以该文件「默认少翻页 / 完整性门禁」为准。
填表语法跟公布站高级查询说明走,按字段区分,不要混用(细则见 prompts/patent_search.md)。
python patent-search/tools/cnipa_search.py --inventor "姓名" --applicant "单位"
python patent-search/tools/cnipa_search.py --title "数据处理" --abstract "吸附 and 再生" --class B01J20 --max-pages 2
python patent-search/tools/cnipa_search.py --abstract "折叠 and 杯盖" --type design --derived-from image --type-inferred --derived-note "折叠杯盖"
python patent-search/tools/cnipa_search.py --inventor "姓名" --complete单独拷走本包时:python tools/cnipa_search.py …。改版式只动 tools/emit_search_report.py。机读前缀:EPUB_SEARCH_MD: / EPUB_SEARCH_JSON: / EPUB_SEARCH_NOTE: / EPUB_SEARCH_INCOMPLETE:。对话里给出 Markdown 路径。
护栏
- 结果不得冒充交底查新。
- 本包只做公布站高级查询。单图或权要只生成公布站布尔式。覆盖精排是列表之后的可选旁路。
产出物
outputs/patent-search/SEARCH-YYYYMMDD-HHMMSS.md(及对应 json)。精排旁路另出 SEARCH-*.covers.md / .covers.json,不改列表报告。本包不设「交付后请确认」。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

