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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/handsomestWei/patent-disclosure-skillnpx agentmods add skills/handsomestwei/patent-disclosure-skill/patent-disclosureWrote 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-disclosure)<a href="https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-disclosure"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-disclosure/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-disclosure"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-disclosure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 24 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00049 | $0.01245 |
| Opus 5.5 | $0.00020 | $0.00498 |
| Sonnet 5.5 | $0.00010 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
patent-disclosure 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 26d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交底书编写
用途
挖专利点、轻量查新、写成发明 / 实用新型 / 外观设计交底书；首篇定稿后可走保护型 1+N 围栏。发明 / 实用新型 / 外观是包内三个目录，不是三个可触发技能。分步指令在本包 prompts/。
何时用
用户说专利挖掘、交底书、查新、实用新型、外观设计，或 /patent-disclosure、/交底书。未显式指定类型时默认发明。
「专利布局 / 专利围栏 / 族树 / 做围栏」走本包旁路（首篇已定稿；用户点名可强开）。不要因写申请、读专利、对照表自动进入。
输入
发明人材料、项目目录、可选 .tex；类型与联系人在 prompts/intake.md 收敛，不全可推断并注明假设。--type 与 intake 一致。线稿、CAD、公式、Word 出图、PDF 转 md 用本包 tools/。
步骤
| 步骤 | 文件 |
|---|---|
| Step 1 | prompts/intake.md |
| Step 2 | prompts/project_scan.md；有 .tex 再 Read prompts/tex_scan.md |
| Step 3–4 | prompts/invention/ · utility_model/ · design/ 挖点 |
| 填表 / 线稿 | prompts/fill_*、image_gen.md、*_lineart_*.md；外观视图口径 references/design_view_cnipa.md；外观成文前 tools/check_design_views.py；结构案成文前 tools/check_source_parts.py |
| Step 5 | prompts/prior_art_search.md（轻量查新：3～4 个手段短语，公布模式每页 10 条，LLM 摘要精排） |
| Step 5.5 | 同文件「D1 锁定与区别特征 Fk」：主比对钉一篇最接近 + 逐特征表（可 D2 补行）+ 三态门禁，落 查新与区别定位_*.md。三态都进 Step 6；不过仍成文但创造性降级 |
| Step 6 | prompts/disclosure_preview.md |
| Step 7 | 对应类型 disclosure_builder.md + template_reference.md |
| Step 8 | prompts/disclosure_self_check.md |
| 迭代 | iteration_context.md / merger.md / correction_handler.md |
| 旁路 · 保护型 1+N | 首篇定稿后 prompts/fence/guardrails.md；用户同意则 decompose.md → design_around.md → matrix.md → plan.md（family.yaml + 专利布局.md）→ score.md（立项后弱校验）→ 确认后 dispatch.md |
| 交付对话 | 定稿回复末块 prompts/delivery_confirm.md（标题固定 交付后请确认） |
查新：prompts/prior_art_search.md，脚本 tools/crawl/cnipa_epub_search.py（整仓路径 skills/patent-disclosure/tools/crawl/cnipa_epub_search.py）。
围栏：Step 8 之后只在交付回复 ## 交付后请确认 第 3 条询问。口径见 prompts/fence/guardrails.md。立项说明直接写 outputs/{案件}/fence/专利布局.md（章节见 prompts/fence/plan.md），family.yaml 只供校验和分件。弱校验表 references/scorecards/gbt42748_fence.yaml。口头确认「按 C1、P1 写」后再分件。
python skills/patent-disclosure/tools/fence/check_layout.py --decompose outputs/{案件}/fence/decompose.yaml
python skills/patent-disclosure/tools/fence/check_layout.py --family outputs/{案件}/fence/family.yaml --matrix outputs/{案件}/fence/matrix.yaml
python skills/patent-disclosure/tools/fence/check_scorecard.py -i outputs/{案件}/fence/scorecard.yaml --case-dir outputs/{案件}
What ships with it
60 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.
- examples/example_batch_job_scheduler/knowledge/docs/architecture.md 2.3 KB
- examples/example_batch_job_scheduler/knowledge/docs/README.md 1.2 KB
- examples/example_batch_job_scheduler/knowledge/docs/sample_architecture_review.docx 38 KB
- examples/example_batch_job_scheduler/knowledge/docs/sample_assets/sample_fig_modules.png 2.5 KB
- examples/example_batch_job_scheduler/knowledge/docs/sample_assets/sample_fig_queue.png 1.7 KB
- examples/example_batch_job_scheduler/knowledge/docs/sample_scheduler_deck.pptx 33 KB
- examples/example_batch_job_scheduler/knowledge/meeting_notes_intake_example.md 731 B
- examples/example_batch_job_scheduler/knowledge/pkg/scheduler/heartbeat.go 553 B
- examples/example_batch_job_scheduler/knowledge/pkg/scheduler/reorder.go 1.4 KB
- examples/example_batch_job_scheduler/knowledge/pkg/scheduler/scorer.go 497 B
- examples/example_batch_job_scheduler/knowledge/pkg/scheduler/types.go 866 B
- examples/example_batch_job_scheduler/knowledge/tex/macros.tex 158 B
- examples/example_batch_job_scheduler/knowledge/tex/main.tex 180 B
- examples/example_batch_job_scheduler/knowledge/tex/README.md 624 B
- examples/example_batch_job_scheduler/knowledge/tex/sections/method.tex 685 B
- examples/example_batch_job_scheduler/README.md 608 B
- examples/example_design_desk_lamp/knowledge/assets/mi_desk_lamp_pro.jpg 168 KB
- examples/example_design_desk_lamp/knowledge/assets/view_arm_detail.jpg 104 KB
- examples/example_design_desk_lamp/knowledge/assets/view_joint_detail.jpg 100 KB
- examples/example_design_desk_lamp/knowledge/assets/view_packaging.jpg 948 KB
- examples/example_design_desk_lamp/knowledge/assets/view_perspective.jpg 196 KB
- examples/example_design_desk_lamp/knowledge/assets/views_ortho.jpg 162 KB
- examples/example_design_desk_lamp/knowledge/docs/design_brief.md 785 B
- examples/example_design_desk_lamp/README.md 3.4 KB
- examples/example_utility_model_ev_powertrain/knowledge/assets/photo_motor_pcu.jpg 123 KB
- examples/example_utility_model_ev_powertrain/knowledge/docs/structure_brief.md 10 KB
- examples/example_utility_model_ev_powertrain/README.md 3.7 KB
- examples/README.md 668 B
- prompts/correction_handler.md 4.7 KB
- prompts/delivery_confirm.md 4.0 KB
- prompts/design_lineart_assist.md 5.7 KB
- prompts/design/disclosure_builder.md 5.2 KB
- prompts/design/patent_points.md 3.0 KB
- prompts/design/template_reference.md 2.0 KB
- prompts/disclosure_preview.md 3.3 KB
- prompts/disclosure_self_check.md 20 KB
- prompts/fence/decompose.md 1.2 KB
- prompts/fence/design_around.md 1.5 KB
- prompts/fence/dispatch.md 2.3 KB
- prompts/fence/guardrails.md 2.4 KB
- prompts/fence/matrix.md 1.5 KB
- prompts/fence/plan.md 5.3 KB
- prompts/fence/score.md 5.1 KB
- prompts/fill_appearance_schema.md 4.5 KB
- prompts/fill_structure_schema.md 4.4 KB
- prompts/image_gen.md 4.9 KB
- prompts/intake.md 3.0 KB
- prompts/invention/disclosure_builder.md 29 KB
- prompts/invention/patent_points_analyzer.md 1.8 KB
- prompts/invention/template_reference.md 17 KB
- prompts/iteration_context.md 6.1 KB
- prompts/merger.md 6.0 KB
- prompts/prior_art_search.md 23 KB
- prompts/project_scan.md 12 KB
- prompts/structure_lineart_assist.md 8.1 KB
- prompts/structure_lineart_compose.md 5.4 KB
- prompts/tex_scan.md 3.3 KB
- prompts/utility_model/disclosure_builder.md 6.3 KB
- prompts/utility_model/patent_points.md 4.0 KB
- prompts/utility_model/template_reference.md 2.9 KB
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.
- 26d ago Changed · +20 lines fe93aa6342f6
- 1mo ago Changed 0114a7690978
- 1mo ago Changed a8d0207533c9
- 1mo ago Changed · +1 lines 323e2d5697c4
- 1mo ago Changed · +1 lines 7989d97d578f
- 1mo ago Changed · +8 lines · +9 tokens per session f19364406243
- 1mo ago Changed 47bcb2611aec
- 1mo ago Changed · +1 lines da7d2bae1ceb
- 1mo ago First seen · 27 lines · 40 tokens per session scan A 49e4440a815b
patent-disclosure is a skill published in the GitHub repository handsomestWei/patent-disclosure-skill (12,313 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,245 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
clawhub-content-rights-correspondence
Use when drafting, sending, or preserving email correspondence for an existing ClawHub content rights case.
compliance-checker
Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…
yuwen-publish-precheck
A Chinese-language review workflow for checking content before publishing it on Douyin, Xiaohongshu, or WeChat Channels.
competitive-intelligence
Analyze competitor IP portfolios — comparative patent portfolio reports with strategy inference. Budget: 120 patent families, 15 claim parses, 40 web searches.
claim-analysis
Deep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.
appropriateness-bounding
Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.