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-readergit 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-reader)<a href="https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-reader"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-reader/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-reader"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00536 |
| Opus 5.5 | $0.00012 | $0.00214 |
| Sonnet 5.5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
patent-reader 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 24d 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
专利通俗解读
用途
把公开号 / PDF / 全文读成通俗笔记、图谱，并可写入 Obsidian。独权拆成稳定特征行（claim_features.json），说明书段落可机读（description_paragraphs.json），给对照表当输入。
何时用
用户说读专利、给出公开号或 PDF 且目标是「读懂」，或 /patent-read、/读专利。对照表派工缺 claim_features.json 或 description_paragraphs.json 时由对照表点名进入。对照表只要这两份文件，不写笔记、不入库。
输入
公开号、专利 PDF、或粘贴的权利要求/说明书。对照表派工时默认把从属权也拆进 claim_features.json，并保留 description_paragraphs.json。
步骤
Readprompts/patent_plain_reader.md。对照表派工只做到该文件「对照表派工」段，不写笔记- 用户要读懂、且为实用新型或外观：
Readprompts/type_hooks.md+prompts/fill_* - 笔记 / 自检：
obsidian_ofm_companion.md、patent_reader_self_check.md
工具在本包 tools/（extract/ · analyze/ · vault/）。PDF：tools/extract/fetch_patent_pdf.py；入库：tools/vault/write_patent_obsidian_note.py。特征行校验：tools/analyze/validate_claim_features.py。
护栏
- 笔记、PDF 与特征行只用本包
tools/。
产出物
工作区 outputs/patent_reader/：通俗笔记、图谱中间产物、claim_features.json、description_paragraphs.json（含 source_url）。有库则另写入 Obsidian。对话给出笔记路径。
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.
- assets/obsidian/_专利解读索引.template.md 1.8 KB
- assets/obsidian/glossary.base.yaml 542 B
- assets/obsidian/graph_color_groups.json 800 B
- assets/obsidian/patent-reader.css 1.5 KB
- assets/obsidian/patents.base.yaml 2.5 KB
- assets/obsidian/README.md 578 B
- assets/patent_note_template.md 3.8 KB
- docs/obsidian-setup-guide.md 4.7 KB
- examples/example_patent_reader/README.md 2.8 KB
- prompts/fill_appearance_schema.md 1.7 KB
- prompts/fill_structure_schema.md 1.6 KB
- prompts/obsidian_ofm_companion.md 2.3 KB
- prompts/obsidian_plugin_guide.md 1.6 KB
- prompts/patent_plain_reader.md 24 KB
- prompts/patent_reader_self_check.md 1.7 KB
- prompts/type_hooks.md 1.9 KB
- README.md 1.5 KB
- references/ipc_application_hints.yaml 3.5 KB
- references/patent_domain_rules.yaml 1.0 KB
- references/patent_obsidian_format.md 8.6 KB
- references/patent_pdf_sources.yaml 4.2 KB
- references/schemas/appearance.schema.yaml 1.9 KB
- references/schemas/claim_features.schema.yaml 897 B
- references/schemas/structure.schema.yaml 1.4 KB
- references/tech_effect_hints.yaml 700 B
- tests/__init__.py 4 B runs code
- tests/fixtures/patent_reader_sample.txt 1.1 KB
- tests/test_biblio_extract.py 1.0 KB runs code
- tests/test_claim_features.py 3.4 KB runs code
- tests/test_desc_paragraphs.py 4.8 KB runs code
- tests/test_extract_patent_text.py 1.6 KB runs code
- tests/test_fetch_patent_pdf.py 5.9 KB runs code
- tests/test_note_cites.py 4.3 KB runs code
- tests/test_patent_reader_debt_fixes.py 39 KB runs code
- tests/test_patent_reader_links.py 5.4 KB runs code
- tests/test_patent_reader_p0_p2.py 4.7 KB runs code
- tests/test_patent_reader_pipeline.py 8.2 KB runs code
- tests/test_schema_vault.py 3.0 KB runs code
- tools/__init__.py 235 B runs code
- tools/analyze/__init__.py 28 B runs code
- tools/analyze/build_claim_mermaid.py 1.6 KB runs code
- tools/analyze/build_context_anchor.py 8.2 KB runs code
- tools/analyze/claim_features.py 7.2 KB runs code
- tools/analyze/lint_patent_note.py 9.8 KB runs code
- tools/analyze/validate_claim_features.py 2.7 KB runs code
- tools/analyze/validate_claim_tree.py 3.9 KB runs code
- tools/analyze/validate_public_clues.py 6.1 KB runs code
- tools/browser.py 6.3 KB runs code
- tools/crawl/cnipa_epub_crawler.py 18 KB runs code
- tools/crawl/cnipa_epub_parse.py 19 KB runs code
- tools/crawl/requirements-cnipa.txt 248 B
- tools/extract/__init__.py 28 B runs code
- tools/extract/extract_patent_figures.py 2.9 KB runs code
- tools/extract/extract_patent_text.py 14 KB runs code
- tools/extract/fetch_design_views.py 15 KB runs code
- tools/extract/fetch_patent_pdf.py 16 KB runs code
- tools/extract/figure_extract.py 18 KB runs code
- tools/patent_type.py 9.1 KB runs code
- tools/README.md 4.7 KB
- tools/requirements.txt 68 B
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.
- 24d ago Changed · +19 lines 1862e514a2f4
- 1mo ago First seen · 17 lines · 31 tokens per session scan A 40103db2dbee
patent-reader is a skill published in the GitHub repository handsomestWei/patent-disclosure-skill (12,184 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 536 once invoked, about $0.0001 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
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.
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.
pdf-courseware-to-obsidian
A workflow that turns local PDF or PowerPoint course materials into structured Chinese study notes in an Obsidian vault. Obsidian is a note-taking app that stores linked Markdown files and related images.
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.