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 Raw1mage/patentmcp --skill patent-disclosure-skillgit clone --depth 1 https://github.com/Raw1mage/patentmcpWrote 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/raw1mage/patentmcp/patent-disclosure-skill)<a href="https://agentmods.dev/skills/raw1mage/patentmcp/patent-disclosure-skill"><img src="https://agentmods.dev/badge/skills/raw1mage/patentmcp/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/raw1mage/patentmcp/patent-disclosure-skill"><img src="https://agentmods.dev/badge/skills/raw1mage/patentmcp/patent-disclosure-skill.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 | $0.00087 | $0.03359 |
| Opus 5 | $0.00044 | $0.01680 |
| Sonnet 5 | $0.00017 | $0.00672 |
| Haiku 4.5 | $0.00009 | $0.00336 |
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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
专利挖掘与交底书生成
本技能覆盖 专利点挖掘 → 查新与差异化 → 交底书生成 → 自检完善 全流程；分步指令在 prompts/，每步执行前 Read 对应文件，与步骤的对照见「Prompt 文件映射」。
环境与约定
- 语言：默认与用户语种一致；专利与法律术语采用行业常用表述。
- 图示定稿（Step 7）：3.2/3.4 用 fenced mermaid；执行方式、
mmdc安装与降级规则见下表「交底书定稿交付」行及tools/README.md。
触发条件
在用户使用以下任一方式时启用本技能：
- 明确提及：专利挖掘、专利点、技术交底书、交底书、专利交底书、查新、现有技术对比等
- 斜杠或简短指令：如
/patent-disclosure-skill、/patent-disclosure、/交底书 - 迭代模式（按意图识别）：当用户意图明显是在已有交底书或上一轮输出上继续工作（如改章节、补实施例、补材料、修正参数/事实、调整表述等），无需用户写出「迭代」等固定词，也不必询问是否进入迭代——Agent 应
Readprompts/iteration_context.md，再Readprompts/merger.md（侧重新材料、扩展合并）或prompts/correction_handler.md（侧重纠错、与事实或风格不符），严格按该文件开头的「执行门禁」（优先执行，不可跳过）做完合并或纠正，另存为新文件：{案件名}_{YYYYMMDDHHmmss}.md与同名.docx（与首次定稿同一命名规则，见disclosure_builder.md§7.3 第 5 点），不覆盖旧稿（除非用户明确要求）。禁止在迭代意图已成立时默认回到 Step 3–4 专利点全文分析（除非用户明确要求重新挖掘专利点）。对话中已出现交底书路径、附件或上文刚交付的草稿时，优先按迭代处理。
工具与数据来源
按任务选用能力；具体工具名称以当前 Agent 环境为准。
若扫描范围内含 Word（.docx） 或 PowerPoint（.pptx），须在 Step 2 纳入阅读前用本仓库 docx_to_md.py / pptx_to_md.py 转为 Markdown；依赖 pip install -r requirements.txt，命令与说明见下表对应行。
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，见下表 |
| 读代码、设计文档、PDF、图片 | 文件读取工具；大仓库先用搜索/语义检索定位再精读 |
| Word（.docx）→ Markdown + 抽取图片（扫描前） | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/docx_to_md.py --input {path}.docx --output {dir}/{name}.md；图片默认写入与 .md 同级的 {name}_media/；需 pip install -r requirements.txt（含 mammoth）；复杂版式可改由所内导出 PDF/MD 再扫 |
| PowerPoint（.pptx）→ Markdown + 抽取图片（扫描前） | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/pptx_to_md.py --input {path}.pptx --output {dir}/{name}.md；默认 {name}_media/；需 pip install -r requirements.txt（含 python-pptx）；旧版 .ppt 不支持，请先另存为 .pptx；图表/SmartArt 等若未以图片形状嵌入则可能仅能从备注或另行导出补全 |
| 罗列目录、按名找文件 | 目录列举 / 按文件名搜索 |
| 联网查新（Step 5） | 执行前 Read prompts/prior_art_search.md。中国专利公布公告：优先 Bash 运行 cnipa_epub_search.py；须在生成命令前归纳 2～8 个相关度高的语义块；执行时须分多次调用，每次仅传一个词块，自行按 pub_number 合并多轮 EPUB_HITS_JSON（勿单次工具调用堆多个 argv，见该 prompt）。一步拉取+解析、不写 HTML 落盘；须 pip install -r tools/requirements-cnipa.txt 且 python -m playwright install chromium。abstract 规定必用同该 prompt。需整句一次 AND 或保存 HTML 时用 cnipa_epub_crawler.py；异常或无果再 WebSearch |
| 交底书定稿交付（须同时 .md + .docx） | 3.2 系统框图与 3.4 流程图均用 fenced mermaid，不要 ASCII 文字流程图/框图。定稿执行 tools/mermaid_render.py：mermaid 转 PNG（失败块保留围栏）后默认生成同名 .docx；若 Word 失败，按 stderr 提示手动运行 md_to_docx.py。详见 tools/README.md |
| 保存交底书路径 | 写入用户指定路径；未指定时可建议 ./outputs/{案件标识}/；凡交付的 .md / .docx 须为 {案件名}_{YYYYMMDDHHmmss}（§7.3 第 5 点，含首次定稿与迭代），勿默认覆盖旧稿；outputs/ 整目录默认由 .gitignore 忽略 |
| 迭代对话留档 | 每轮 merger / correction 交付后，在案件目录追加 交底书修订对话记录.md（tools/iteration_dialog_log.py 或等价手工），见 prompts/iteration_context.md |
What ships with it
50 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 256 B
- docs/PRD.md 3.1 KB
- docs/skill-structure.md 2.5 KB
- docs/thanks.jpg 143 KB
- docs/效果例-初版生成.jpg 228 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/README.md 3.0 KB
- INSTALL.md 3.9 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/patent_points_analyzer.md 951 B
- prompts/prior_art_search.md 10 KB
- prompts/project_scan.md 4.2 KB
- prompts/template_reference.md 8.6 KB
- README.md 8.8 KB
- requirements.txt 485 B
- tests/test_cnipa_epub_chain.py 1.4 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
- tools/cnipa_epub_crawler.py 11 KB runs code
- tools/cnipa_epub_parse.py 8.6 KB runs code
- tools/cnipa_epub_search.py 5.6 KB runs code
- tools/docx_to_md.py 3.7 KB runs code
- tools/iteration_dialog_log.py 3.2 KB runs code
- tools/math_render.py 13 KB runs code
- tools/md_to_docx.py 32 KB runs code
- tools/mermaid_render.py 16 KB runs code
- tools/package-lock.json 84 KB
- tools/package.json 269 B
- tools/pptx_to_md.py 4.9 KB runs code
- tools/README.md 15 KB
- tools/requirements-cnipa.txt 159 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.
- 12d ago First seen · 107 lines · 87 tokens per session scan A 5e4b8f3a9911
patent-disclosure-skill is a skill published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 3,359 once invoked, about $0.0004 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 2026-08-31.
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…