Agent skill

Patent Disclosure Skill

by qzzqzzb in qzzqzzb/OpenClaudeScience

通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.

MITAuto-check: notesLegal & Compliance

Install Patent Disclosure Skill

skills CLI
$ npx skills add qzzqzzb/OpenClaudeScience --skill patent-disclosure-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qzzqzzb/OpenClaudeScience patent-disclosure-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qzzqzzb/OpenClaudeScience.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/patent-disclosure-skill .claude/skills/patent-disclosure-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
patent-disclosure-skill
GitHub stars
106
Token cost
~1.6k tokens
SKILL.md length
332 words
Files
57
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.

  • Works in 7 steps: Read intake.md → 执行 Step 1 → Read project_scan.md → 执行 Step 2 → Read patent_points_analyzer.md → 执行 Step… → …
  • Tasks that involve Intellectual property
  • SKILL.md covers 环境与约定, 触发条件, 工具与数据来源 and Prompt 文件映射, plus 3 more sections
  • Calls pip, python3 and python

What it does

Patent Disclosure Skill is an agent skill from qzzqzzb/OpenClaudeScience. 通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 61 other files (for example `INSTALL.md`, `README.md` and `docs/PRD.md`).

It sits in Legal & Compliance, covering Intellectual property. It works with Microsoft PowerPoint, Microsoft Word and Bash. The repository describes itself as: Bringing the Claude Science experience to the open-source world. The licence is MIT.

When your agent uses it

  • Tasks that involve Intellectual property

Example prompts

  • “/patent-disclosure-skill”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, WebSearch, Bash

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read intake.md → 执行 Step 1
  2. Read project_scan.md → 执行 Step 2
  3. Read patent_points_analyzer.md → 执行 Step 3–4
  4. Read prior_art_search.md → 执行 Step 5
  5. Read disclosure_preview.md → 执行 Step 6;用户可跳过
  6. Read disclosure_builder.md 与 Read template_reference.md → 执行 Step 7(首次交付的 .md/.docx 亦须 {案件名}_{YYYYMMDDHHmmss},§7.3 第 5 点);交付对话中须按…
  7. Read disclosure_self_check.md → 内部执行 Step 8,修订后交付

What it can do on your machine

Read from SKILL.md and the folder at commit 4a5f2ab. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • WebSearch
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip
    • python3
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Patent Disclosure Skill loads about 1.6k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 332 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Grep, Glob, WebSearch, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from qzzqzzb/OpenClaudeScience at commit 4a5f2ab, republished under its MIT licence (© qzzqzzb). 332 words, ~1,594 tokens.

Download SKILL.mdSave it as .claude/skills/patent-disclosure-skill/SKILL.md (or your agent's skills folder). This skill also uses 56 other files; get the full folder from GitHub.
name
patent-disclosure-skill
description
通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.
allowed-tools
Read, Write, Edit, Grep, Glob, WebSearch, Bash
version
1.8.9
user-invocable
true
argument-hint
[可选:项目路径或技术主题关键词]

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 Read prompts/iteration_context.md,再 Read prompts/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

Prompt 文件映射

步骤文件用途
Step 1prompts/intake.md边界与输入问题
Step 2prompts/project_scan.md项目文档扫描;须对 .docx/.pptx 先转换再读(见该文件「Office 文档」节);独立图片目录可跳过
Step 3–4prompts/patent_points_analyzer.md候选专利点、融合与选定
Step 5prompts/prior_art_search.md联网查新与分析要求
Step 6prompts/disclosure_preview.md全文前的摘要预览
Step 7prompts/disclosure_builder.md + prompts/template_reference.md交底书结构、脱敏、**符号与公式体例(§7.7)**与图示规范;mermaid 与 3.4.1 符号/公式范例在 template_reference
Step 8prompts/disclosure_self_check.md内部自检,不写入正文
迭代prompts/iteration_context.md迭代意图、落盘命名、修订对话记录 md(含对话/记录时间)
迭代prompts/merger.md新材料增量合并;文首含门禁;输出 {案件名}_{时间戳}.md/.docx
迭代prompts/correction_handler.md对话纠正;文首含门禁;输出 {案件名}_{时间戳}.md/.docx

主流程(执行顺序)

  1. Read intake.md → 执行 Step 1
  2. Read project_scan.md → 执行 Step 2
  3. Read patent_points_analyzer.md → 执行 Step 3–4
  4. Read prior_art_search.md → 执行 Step 5
  5. Read disclosure_preview.md → 执行 Step 6;用户可跳过
  6. Read disclosure_builder.md 与 Read template_reference.md → 执行 Step 7(首次交付的 .md/.docx 亦须 {案件名}_{YYYYMMDDHHmmss},§7.3 第 5 点);交付对话中须按 disclosure_builder.md §7.6 补充「权利要求偏向点」建议交互(仅对话,不入正文)
  7. Read disclosure_self_check.md → 内部执行 Step 8,修订后交付

禁止:交底书正文中包含「自检清单」章节;自检仅内部使用。


迭代模式(摘要)

启用方式:根据用户自然语言意图判断(见上文「触发条件」),不要求固定关键词,默认不为「是否迭代」打断用户。

  • 补充材料 / 扩展章节或 §7.6 第五章权利要求书式强化(用户已声明侧重点):Read → iteration_context.md → merger.md;合并结果另存为带时间戳的 .md/.docx(§7.3 第 5 点);追加 交底书修订对话记录.md(iteration_dialog_log.py 或手工);完成后必须输出「合并摘要」留档;若本轮亦为定稿交付,仍建议简短附带 §7.6 类引导
  • 指出错误 / 与事实或参数不符:Read → iteration_context.md → correction_handler.md;纠正结果另存为带时间戳的 .md/.docx;追加对话记录;完成后必须输出「纠正摘要」留档;定稿交付时还须按 disclosure_builder.md §7.6 附「权利要求偏向点」引导(见 correction_handler.md 末尾)

主流程 Step 7→8 的 disclosure_self_check.md 仍在新稿定稿路径上内部执行。


Agent 自用工作流检查清单

□ 已按步骤 Read 对应 prompts;Step 2 若目录含 Office,已执行 docx_to_md / pptx_to_md 并读了产出 `.md`
□ 识别到「在已有交底书上修改」类意图时,已 Read `iteration_context.md` 并选用 merger 或 correction_handler(而非从头跑扫描);交付为**新** `{案件名}_{时间戳}.md`/`.docx`,未无故覆盖旧稿
□ 执行 merger / correction_handler 后,已在对话中输出该文件要求的留档摘要(合并摘要 / 纠正摘要);案件目录已追加 **`交底书修订对话记录.md`**(或等价日志)
□ 查新完成且写入 1.1 与区别论述(符合 `prior_art_search.md`:**优先** `tools/cnipa_epub_search.py`,**国知局侧已分多次调用、每轮一词,并已自行合并** `EPUB_HITS_JSON`;**`abstract` 必用且已充分理解后再概括**;异常或无果再 **WebSearch**)
□ 除用户明确跳过外,完成摘要预览
□ 脱敏、mermaid(定稿均已渲染为 PNG)、章节引用符合 template_reference;含公式时 **3.4.1 符号表、§7.7 体例**(维度下标、无字母多义、LaTeX 分隔符统一)及 **3.5 符号列同形** 已满足;**已交付 .md 与 .docx**,且**文件名符合 §7.3 第 5 点**(**凡交付均含**时间戳后缀);**正文无**技能/示例仓库类文末脚注
□ 定稿类对话已含 **`disclosure_builder.md` §7.6**「权利要求偏向点」建议交互(**不入正文**、**不捏造**未在稿内出现的保护取向);迭代再走 merger 时见 **`iteration_context.md`** 表格补充行
□ 自检在后台完成,正文无自检清单章节;含公式时已按 **`disclosure_self_check.md` §8.2** 复核**公式正确性与公式逻辑**(有误已在 Step 8 直接改稿)

© qzzqzzb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 56 other files in skills/patent-disclosure-skill of qzzqzzb/OpenClaudeScience.

  • SKILL.md
  • .gitignore
  • INSTALL.md
  • LICENSE
  • README.md
  • docs/PRD.md
  • docs/skill-structure.md
  • docs/thanks.jpg
  • docs/效果例-初版生成.jpg
  • docs/效果例-迭代更新.jpg
  • examples/README.md
  • examples/example_batch_job_scheduler/README.md
  • examples/example_batch_job_scheduler/knowledge/docs/README.md
  • examples/example_batch_job_scheduler/knowledge/docs/architecture.md
  • examples/example_batch_job_scheduler/knowledge/docs/sample_architecture_review.docx
  • examples/example_batch_job_scheduler/knowledge/docs/sample_assets
  • … and 41 more

Open the folder on GitHubat commit 4a5f2ab

Compare with similar skills

Patent Disclosure Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Patent Disclosure Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Patent Disclosure Skill this skillqzzqzzb/OpenClaudeScience106—~1.6kAutomated safety check: NotesMIT
Patent Disclosure Skilltrsoliu/mini-wiki116—~1.7kAutomated safety check: NotesMIT
Paper to Chinese Patent DrafterYuan1z0825/nature-skills47k1 repos~1.1kAutomated safety check: PassApache-2.0
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1071 repos~959Automated safety check: PassNone
Markdown Exporterbowenliang123/markdown-exporter2721 repos~5.3kAutomated safety check: PassApache-2.0
Patentalirezarezvani/claude-skills28k—~4.1kAutomated safety check: PassMIT

Similar skills

  • Patent Disclosure Skill

    trsoliu/mini-wiki

    中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language…

    116 GitHub stars~1.7k tokensUpdated 6 days ago
    Legal & ComplianceAuto-check: notes
  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed
  • Paper To Cn Patent

    snipp-zha/Paper-to-patent-Skill

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.

    107 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed
  • Markdown Exporter

    bowenliang123/markdown-exporter

    Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.

    272 GitHub starsUsed in 1 repo~5.3k tokens
    Documents & OfficeAuto-check passed
  • Patent

    alirezarezvani/claude-skills

    Patent prior-art and landscape intelligence skill — not generic patent help.

    28k GitHub stars~4.1k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Research

    alirezarezvani/claude-skills

    Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants…

    28k GitHub stars~4.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

More from qzzqzzb/OpenClaudeScience

  • Skill Creator

    qzzqzzb/OpenClaudeScience

    Create or update InternAgent skills. An agent skill from qzzqzzb/OpenClaudeScience.

    106 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Local Release Test

    qzzqzzb/OpenClaudeScience

    Use the repository-local GitHub Actions release workflow to publish prerelease test builds from development branches without touching the official InternScience/InternAgents release repository.

    106 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check: notes

Questions about Patent Disclosure Skill

What does Patent Disclosure Skill do?

通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check. Patent Disclosure Skill is an agent skill from qzzqzzb/OpenClaudeScience. 通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.

When should I use Patent Disclosure Skill?

Patent Disclosure Skill fits situations like: tasks that involve Intellectual property.

How do I install Patent Disclosure Skill in Claude Code?

Run `npx skills add qzzqzzb/OpenClaudeScience --skill patent-disclosure-skill -a claude-code`. Or copy the skill folder (skills/patent-disclosure-skill in qzzqzzb/OpenClaudeScience) into .claude/skills/patent-disclosure-skill in your project. Claude Code loads it when a task matches its description.

How do I install Patent Disclosure Skill in Codex?

Run `npx skills add qzzqzzb/OpenClaudeScience --skill patent-disclosure-skill -a codex`. Or copy the skill folder (skills/patent-disclosure-skill in qzzqzzb/OpenClaudeScience) into .agents/skills/patent-disclosure-skill in your project. Codex loads it when a task matches its description.

Can I use Patent Disclosure Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qzzqzzb/OpenClaudeScience --skill patent-disclosure-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/patent-disclosure-skill, .gemini/skills/patent-disclosure-skill, .github/skills/patent-disclosure-skill and .opencode/skills/patent-disclosure-skill in your project.

What does Patent Disclosure Skill need to run?

Going by SKILL.md and its folder, Patent Disclosure Skill needs the command-line tools its instructions call (pip, python3 and python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, WebSearch, Bash.

Does Patent Disclosure Skill access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Patent Disclosure Skill safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Patent Disclosure Skill use?

Patent Disclosure Skill is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Patent Disclosure Skill use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Patent Disclosure Skill?

Skills that share tags, products or a category with Patent Disclosure Skill: Patent Disclosure Skill (trsoliu/mini-wiki, 116 stars), Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars) and Markdown Exporter (bowenliang123/markdown-exporter, 272 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Patent Disclosure Skill?

qzzqzzb (a GitHub user) maintains it in qzzqzzb/OpenClaudeScience, which has 106 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 13, 2026.

Source: qzzqzzb/OpenClaudeScience on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.