中国专利.skill is a Chinese-language agent skill for finding patentable ideas, writing patent disclosure documents, explaining published patents, tracking examination policies, and helping prepare examination responses. It is for developers and researchers working with Chinese invention, utility-model, and design patents, with workflows that can store related research in Obsidian.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add handsomestWei/patent-disclosure-skill --skill patent-applicationgit clone --depth 1 https://github.com/handsomestWei/patent-disclosure-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-application)<a href="https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-application"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-application/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-application"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-application.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.00635 |
| Opus 5 | $0.00048 | $0.00318 |
| Sonnet 5 | $0.00019 | $0.00127 |
| Haiku 4.5 | $0.00010 | $0.00064 |
Grade A, and why
patent-application scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
申请文件
须用户点名（申请文件 / 申请底稿 / 申报材料 / 权利要求书 / /申请底稿 / /patent-apply），并指定交底材料目录。案卷会稿（patent-docket）调度本包时视为已点名，仍须有交底目录。
缺交底书 / schema / 线稿则终止，引导先用交底技能补齐。内容歧义不阻塞：先出主文件，缺口写入 问题清单.md。发明人/申请人未填只记清单，不终止、不挡案卷轮次。交付后对话末尾须给出该文件路径并摘要条目（见 issues.md）。
主交付是四件套（Markdown + Word + 黑白图）。
Readprompts/guardrails.md→intake.md- 已有申请产出上改稿（未要求整案重写）：
Readiteration_context.md→iteration.md（新时间戳目录、出 Word、问题清单），然后结束，不要再走第 3–5 步 - 跑
tools/material_gate.py --case-dir <交底目录>；退出码 2 则停 - 发明 / 实用新型：
claim_strategy.md→claims_builder.md→figures.md→specification_builder.md→numeral_register.md→consistency.md - 外观：先
Readreferences/design_view_cnipa.md（或交底包同文），只走design_application.md；不跑compose_application_figure.py - 本包
tools/emit_application_docx.py出 Word；Readissues.md，写问题清单.md（不入正式文件），并在同一条交付回复末尾给出路径、摘要条目、请用户先看清单
整仓路径：python skills/patent-application/tools/…。
产出：outputs/patent-application/{案件标识}_{时间戳}/。禁止跨包调用其他子技能 tools/。不做 TIFF，不做请求书 / 费减 / CPCNS。
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- prompts/claim_strategy.md 1.8 KB
- prompts/claims_builder.md 1.9 KB
- prompts/consistency.md 1.7 KB
- prompts/design_application.md 2.0 KB
- prompts/figures.md 3.1 KB
- prompts/guardrails.md 3.5 KB
- prompts/intake.md 929 B
- prompts/issues.md 1.8 KB
- prompts/iteration_context.md 663 B
- prompts/iteration.md 2.0 KB
- prompts/material_gate.md 740 B
- prompts/numeral_register.md 875 B
- prompts/self_check.md 2.0 KB
- prompts/specification_builder.md 5.5 KB
- README.md 1.3 KB
- references/design_view_cnipa.md 2.8 KB
- references/disclosure_to_spec_map.md 1.9 KB
- references/promo_terms.yaml 2.4 KB
- references/schemas/application_plan.schema.yaml 1.9 KB
- references/schemas/invention_figures.schema.yaml 1.9 KB
- references/schemas/numeral_register.schema.yaml 859 B
- references/schemas/README.md 533 B
- tests/test_audit_claims.py 3.0 KB runs code
- tests/test_invention_figures.py 8.6 KB runs code
- tests/test_lexicon.py 1.4 KB runs code
- tests/test_material_gate.py 4.2 KB runs code
- tests/test_math_to_omml.py 748 B runs code
- tests/test_numeral_register.py 2.8 KB runs code
- tests/test_support_and_antecedent.py 3.9 KB runs code
- tools/__init__.py 72 B runs code
- tools/audit_claims.py 7.8 KB runs code
- tools/check_numeral_register.py 11 KB runs code
- tools/check_support.py 8.7 KB runs code
- tools/compose_application_figure.py 4.8 KB runs code
- tools/emit_application_docx.py 1.9 KB runs code
- tools/iteration_dialog_log.py 2.6 KB runs code
- tools/lexicon.py 1.1 KB runs code
- tools/material_gate.py 10 KB runs code
- tools/math_to_omml.py 9.4 KB runs code
- tools/md_to_docx.py 44 KB runs code
- tools/README.md 1.7 KB
- tools/render_invention_figures.py 23 KB runs code
- tools/stdio_utf8.py 1.4 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed 1409e87ae871
- 3d ago First seen · 23 lines · 95 tokens per session scan A 105a47bb7f6b
patent-application is a skill published in the GitHub repository handsomestWei/patent-disclosure-skill (9,078 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 635 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
software-certificate-skill
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.
law-to-markdown
A legal-document conversion skill for turning PDF, Word, or plain-text regulations into structured Markdown. Markdown is a text format that uses simple symbols for headings and lists.
analyze-document
Forensically analyse a family court document using the 13-point protocol. Use when the user says "analyse this document", "review this affidavit", "what does this report say", "break down this letter", uploads a court document, affidavit, family report, solicitor letter, or any legal document related to their family…
case-setup
Set up a new family court case vault from scratch. Use when the user says "set up my case", "start my case vault", "I need to organise my family court case", "help me build a case", "create my evidence vault", or is beginning a new family court matter and needs structure.
法律文件脱敏处理
A browser-based and Python tool for removing sensitive details from legal Word documents and restoring them later. It can replace information such as names, dates, prices, bank accounts and case numbers while preserving document formatting.