Borrowing it
Nothing to install: this file belongs to trsoliu/mini-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/trsoliu/mini-wiki/main/.agents/skills/patent-disclosure-skill/SKILL.mdgit clone --depth 1 https://github.com/trsoliu/mini-wikiWrote 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/trsoliu/mini-wiki/patent-disclosure-skill)<a href="https://agentmods.dev/skills/trsoliu/mini-wiki/patent-disclosure-skill"><img src="https://agentmods.dev/badge/skills/trsoliu/mini-wiki/patent-disclosure-skill/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/trsoliu/mini-wiki/patent-disclosure-skill"><img src="https://agentmods.dev/badge/skills/trsoliu/mini-wiki/patent-disclosure-skill.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 | $0.00106 | $0.03475 |
| Opus 5 | $0.00053 | $0.01737 |
| Sonnet 5 | $0.00021 | $0.00695 |
| Haiku 4.5 | $0.00011 | $0.00347 |
Grade A, and why
patent-disclosure-skill 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 11d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中国专利 · 交底书编写与通俗解读
本技能支持两种用法；分步指令在 prompts/，执行前须 Read 对应文件。
| 模式 | 何时用 | 主入口 |
|---|---|---|
| A · 交底书编写 | 从项目材料挖专利点 → 查新 → 成稿 .md/.docx → 迭代 |
下文「交底书主流程」 |
| B · 专利通俗解读 | 已有公开号 / PDF / 全文，原文抽象难读，要通俗叙事 + 图谱 | 下文「专利通俗解读」+ patent_plain_reader.md |
提供专利号或专利全文/PDF且意图为「读懂」时 → 优先模式 B，不默认跑交底书 Step 1–8。
环境与约定
- 语言：默认与用户语种一致；专利与法律术语用行业常用表述。
- 交底书图示（Step 7）：3.2/3.4 用 fenced mermaid；见工具表与
tools/README.md。 - 解读 + Obsidian：强烈推荐配置库（
PATENT_READER_OBSIDIAN_VAULT），以完整体验索引、Canvas 知识图谱、术语网、关系图配色与公开线索旁注；无库可降级outputs/patent_reader/。入库时自动 bootstrap（CSS / Bases / 关系图），勿再引导用户手动装 CSS。用户侧 Obsidian 安装与可选社区插件见docs/obsidian-setup-guide.md。
触发条件
- 交底书：专利挖掘、专利点、技术交底书、交底书、查新、现有技术对比；
/patent-disclosure-skill、/交底书等。 - 通俗解读：专利解读、读专利、看懂专利、反向专利、专利翻译成通俗；
/patent-read、/读专利；或用户给出公开号 / 专利 PDF / 全文且目标为理解而非写交底书。 - 交底书迭代（意图识别）：在已有交底书上补材料、改章节、纠错等——无需固定「迭代」一词，也不必先问是否迭代。
Readiteration_context.md，再merger.md（扩合并）或correction_handler.md（纠错）；另存{案件名}_{YYYYMMDDHHmmss}.md/.docx，不覆盖旧稿（除非用户明确要求）。禁止迭代意图成立时默认回到 Step 3–4 重挖专利点。对话中已有交底书路径/附件时优先按迭代处理。
工具与数据来源
按任务选用；工具名以当前 Agent 环境为准。扫描含 .docx/.pptx 时，Step 2 阅读前须先 docx_to_md.py / pptx_to_md.py（pip install -r requirements.txt）。
常见任务与建议方式
| 任务 | 建议方式 |
|---|---|
| 加载分步指令 | Read → ${CLAUDE_SKILL_DIR}/prompts/*.md |
| 读代码、设计文档、PDF、图片 | 文件读取；大仓库先检索再精读 |
| Word / PPT → Markdown | docx_to_md.py / pptx_to_md.py（见上） |
| 联网查新（交底书 Step 5） | Read prior_art_search.md。优先 cnipa_epub_search.py：先归纳 2～8 语义块，每次工具调用仅一词，自行按 pub_number 合并 EPUB_HITS_JSON；需 tools/requirements-cnipa.txt + Playwright Chromium。abstract 必用。异常或无果再 WebSearch |
| 交底书定稿（.md + .docx） | 3.2/3.4 用 mermaid；mermaid_render.py → PNG 并默认出 docx。见 tools/README.md |
| 交底书落盘 | 建议 ./outputs/{案件标识}/；文件名 {案件名}_{YYYYMMDDHHmmss}（§7.3 第 5 点，含首次与迭代） |
| 迭代对话留档 | 案件目录追加 交底书修订对话记录.md（iteration_dialog_log.py） |
| 专利通俗解读 | Read patent_plain_reader.md。先 check_obsidian_env.py（强烈推荐有库；未检测到则询问并用 --set；用户明确不要库才跳过）。仅公开号时用 fetch_patent_pdf.py（源表 references/patent_pdf_sources.yaml；禁止会话内现写下载脚本）→ extract → 叙事/权要可视化 → 公开线索由 Agent 读 URL 写 summary → write_patent_obsidian_note（入库自动 bootstrap；线索脚本抓取仅 --fetch-clues-fallback）。交付后可选社区插件引导；库内 ≥2 篇须反问关联，同意后 link_patent_notes.py |
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.
- .gitignore 575 B
- assets/obsidian/_专利解读索引.template.md 1.8 KB
- assets/obsidian/glossary.base 542 B
- assets/obsidian/graph_color_groups.json 784 B
- assets/obsidian/patent-reader.css 1.5 KB
- assets/obsidian/patents.base 1.9 KB
- assets/patent_note_template.md 3.5 KB
- docs/obsidian-setup-guide.md 4.4 KB
- docs/thanks.jpg 143 KB
- docs/效果例-obs图谱.jpg 118 KB
- docs/效果例-初版生成.jpg 228 KB
- docs/效果例-解读.jpg 392 KB
- docs/效果例-迭代更新.jpg 54 KB
- examples/example_batch_job_scheduler/knowledge/docs/architecture.md 2.1 KB
- examples/example_batch_job_scheduler/knowledge/docs/README.md 1.1 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/README.md 577 B
- examples/example_patent_reader/README.md 1.7 KB
- examples/README.md 3.4 KB
- INSTALL.md 5.3 KB
- LICENSE 1.0 KB
- prompts/correction_handler.md 2.8 KB
- prompts/disclosure_builder.md 12 KB
- prompts/disclosure_preview.md 917 B
- prompts/disclosure_self_check.md 5.9 KB
- prompts/intake.md 943 B
- prompts/iteration_context.md 4.3 KB
- prompts/merger.md 3.3 KB
- prompts/obsidian_ofm_companion.md 2.3 KB
- prompts/obsidian_plugin_guide.md 1.6 KB
- prompts/patent_plain_reader.md 18 KB
- prompts/patent_points_analyzer.md 951 B
- prompts/patent_reader_self_check.md 1.3 KB
- prompts/prior_art_search.md 10 KB
- prompts/project_scan.md 4.2 KB
- prompts/template_reference.md 8.6 KB
- README.md 12 KB
- references/ipc_application_hints.yaml 3.5 KB
- references/patent_domain_rules.yaml 1.0 KB
- references/patent_obsidian_format.md 7.9 KB
- references/patent_pdf_sources.yaml 2.6 KB
- requirements.txt 485 B
- tests/fixtures/patent_reader_sample.txt 801 B
- tests/test_cnipa_epub_chain.py 1.4 KB runs code
- tests/test_cnipa_epub_crawler.py 1.7 KB runs code
- tests/test_desc_paragraphs.py 4.1 KB runs code
- tests/test_extract_patent_text.py 1.2 KB runs code
- tests/test_fetch_patent_pdf.py 3.3 KB runs code
- tests/test_math_render.py 1.9 KB runs code
- tests/test_md_to_docx_table.py 1.1 KB runs code
- tests/test_note_cites.py 4.3 KB runs code
- tests/test_patent_reader_debt_fixes.py 37 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.
- 11d ago First seen · 148 lines · 106 tokens per session scan A 6323b7ea177f
patent-disclosure-skill is a skill published in the GitHub repository trsoliu/mini-wiki (116 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 3,475 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 2026-08-30.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…