patent-pipeline

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Patent Pipeline: From Invention to Filing

专利撰写流程:从发明到申请

Draft a complete patent application based on: $ARGUMENTS
基于**$ARGUMENTS**撰写完整的专利申请文件。

Overview

概述

This skill orchestrates the full patent drafting lifecycle -- from prior art search through jurisdiction-formatted filing documents. It chains sub-skills into a patent-specific pipeline:
/prior-art-search → /patent-novelty-check → /invention-structuring → /claims-drafting → /specification-writing → /patent-review → /jurisdiction-format
     (search)           (verify)              (structure)             (claims)            (description)          (examiner)         (compile)
                                                                                              ├── /figure-description
                                                                                              └── /embodiment-description
This is a parallel branch, not part of the linear research pipeline. After
/idea-discovery
produces validated ideas, the user can either:
  • Go to
    /experiment-bridge
    /auto-review-loop
    /paper-writing
    (publish track)
  • Go to
    /grant-proposal
    (funding track)
  • Go to
    /patent-pipeline
    (patent track) <-- this skill
                    ┌→ /experiment-bridge → /auto-review-loop → /paper-writing  (publish track)
/idea-discovery ────┤
                    ├→ /grant-proposal → [get funded] → ...  (funding track)
                    └→ /patent-pipeline → [file patent]       (patent track)
Patents are about protecting inventions (legal scope), not publishing results (academic contribution). This skill handles the unique requirements of patent drafting: prior art analysis, claims hierarchy design, specification writing with enablement support, embodiment descriptions, and jurisdiction-specific formatting.
该Skill编排完整的专利撰写生命周期——从现有技术检索到生成符合管辖地区格式的申请文件。它将多个子Skill串联成专利专属流程:
/prior-art-search → /patent-novelty-check → /invention-structuring → /claims-drafting → /specification-writing → /patent-review → /jurisdiction-format
     (检索)           (验证)              (结构化)             (权利要求)            (说明书)          (审查)         (格式转换)
                                                                                              ├── /figure-description
                                                                                              └── /embodiment-description
这是一个并行分支,不属于线性研究流程。
/idea-discovery
产出经过验证的创意后,用户可选择以下任一路径:
  • 进入
    /experiment-bridge
    /auto-review-loop
    /paper-writing
    (发表路径)
  • 进入
    /grant-proposal
    (资助路径)
  • 进入
    /patent-pipeline
    (专利路径)<-- 本Skill
                    ┌→ /experiment-bridge → /auto-review-loop → /paper-writing  (发表路径)
/idea-discovery ────┤
                    ├→ /grant-proposal → [获得资助] → ...  (资助路径)
                    └→ /patent-pipeline → [提交专利申请]       (专利路径)
专利的核心是保护发明(法律范围),而非发布研究成果(学术贡献)。本Skill处理专利撰写的独特需求:现有技术分析、权利要求层级设计、具备充分公开支持的说明书撰写、实施例描述,以及符合管辖地区要求的格式调整。

Constants

常量配置

  • JURISDICTION =
    CN
    — Target patent jurisdiction. Options:
    CN
    (CNIPA),
    US
    (USPTO),
    EP
    (EPO),
    ALL
    (generate all three). Override via argument (e.g.,
    /patent-pipeline "invention — US"
    ).
  • PATENT_TYPE =
    invention
    invention
    (发明专利, 20 year protection) or
    utility_model
    (实用新型, CN only, 10 year protection, apparatus claims only). Override via argument.
  • REVIEWER_MODEL =
    gpt-5.4
    — Model used via Codex MCP for examiner-style review.
  • MAX_REVIEW_ROUNDS = 2 — Maximum review-revision cycles.
  • AUTO_PROCEED = false — At each checkpoint, always wait for explicit user confirmation. Patent applications require inventor judgment at every stage. Set
    true
    only if user explicitly requests autonomous mode.
  • LANGUAGE =
    auto
    — Output language. Auto-detected from jurisdiction: CN->Chinese, US->English, EP->English. Override explicitly if needed.
  • OUTPUT_DIR =
    patent/
    — Directory for generated patent files.
  • OUTPUT_FORMAT =
    markdown
    — Draft format.
    markdown
    for review,
    docx
    for filing-ready.
Override defaults via arguments:
/patent-pipeline "invention — US, utility model"
or
/patent-pipeline "invention — ALL, language: Chinese"
.
  • JURISDICTION =
    CN
    — 目标专利管辖地区。可选值:
    CN
    (CNIPA)、
    US
    (USPTO)、
    EP
    (EPO)、
    ALL
    (生成全部三种格式)。可通过参数覆盖(例如:
    /patent-pipeline "invention — US"
    )。
  • PATENT_TYPE =
    invention
    — 专利类型:
    invention
    (发明专利,20年保护期限)或
    utility_model
    (实用新型,仅限中国地区,10年保护期限,仅支持装置类权利要求)。可通过参数覆盖。
  • REVIEWER_MODEL =
    gpt-5.4
    — 通过Codex MCP使用的审查员风格审查模型。
  • MAX_REVIEW_ROUNDS = 2 — 最大审查-修订循环次数。
  • AUTO_PROCEED = false — 在每个检查点,始终等待用户明确确认。专利申请的每个阶段都需要发明人的判断。仅当用户明确请求自主模式时设置为
    true
  • LANGUAGE =
    auto
    — 输出语言。根据管辖地区自动检测:CN→中文,US→英文,EP→英文。可根据需要手动覆盖。
  • OUTPUT_DIR =
    patent/
    — 生成专利文件的存储目录。
  • OUTPUT_FORMAT =
    markdown
    — 草稿格式。
    markdown
    用于审查,
    docx
    用于可直接提交的版本。
通过参数覆盖默认配置:
/patent-pipeline "invention — US, utility model"
/patent-pipeline "invention — ALL, language: Chinese"

Patent Type Specifications

专利类型说明

Invention Patent (发明专利)

发明专利 (发明专利)

FieldDetail
Protection20 years from filing date
Subject matterMethods, systems, products, compositions, processes
ExaminationSubstantive examination required
Inventive stepHigh (must involve an inventive step / 创造性)
Timeline2-4 years to grant (CN); 2-3 years (US); 3-5 years (EP)
ClaimsMethod + system + product claims allowed
字段详情
保护期限自申请日起20年
保护客体方法、系统、产品、组合物、工艺
审查方式需要实质审查
创造性要求高(需具备创造性 / 创造性)
时间线授权需2-4年(中国);2-3年(美国);3-5年(欧洲)
权利要求类型允许方法+系统+产品类权利要求

Utility Model (实用新型) — CN Only

实用新型专利 (实用新型) — 仅限中国地区

FieldDetail
Protection10 years from filing date
Subject matterProduct shape, structure, or combination thereof only
ExaminationFormal examination only (no substantive examination)
Inventive stepLower than invention patent
Timeline6-8 months to grant
ClaimsApparatus/device claims only. NO method claims.
RestrictionCN jurisdiction only
字段详情
保护期限自申请日起10年
保护客体仅产品的形状、结构或其结合
审查方式仅形式审查(无实质审查)
创造性要求低于发明专利
时间线授权需6-8个月
权利要求类型仅支持装置/设备类权利要求。不允许方法类权利要求
限制仅限中国管辖地区

State Persistence (Compact Recovery)

状态持久化(快速恢复)

Patent drafting is a long task that may trigger context compaction. Persist state to
patent/PATENT_STATE.json
after each phase:
json
{
  "phase": 3,
  "jurisdiction": "CN",
  "patent_type": "invention",
  "language": "Chinese",
  "codex_thread_id": "019cfcf4-...",
  "invention_title": "...",
  "claims_count": 15,
  "status": "in_progress",
  "timestamp": "2026-04-10T15:00:00"
}
Write this file at the end of every phase. On invocation, check for this file:
  • If absent or
    status: "completed"
    -> fresh start
  • If
    status: "in_progress"
    and within 24h -> resume from saved phase (read output files to restore context)
  • If older than 24h -> fresh start (stale state)
On completion, set
"status": "completed"
.
专利撰写是一项耗时任务,可能触发上下文压缩。在每个阶段结束后,将状态保存至
patent/PATENT_STATE.json
json
{
  "phase": 3,
  "jurisdiction": "CN",
  "patent_type": "invention",
  "language": "Chinese",
  "codex_thread_id": "019cfcf4-...",
  "invention_title": "...",
  "claims_count": 15,
  "status": "in_progress",
  "timestamp": "2026-04-10T15:00:00"
}
在每个阶段结束时写入该文件。 调用本Skill时,检查该文件:
  • 若文件不存在或
    status: "completed"
    → 全新开始
  • status: "in_progress"
    且时间在24小时内 → 从保存的阶段恢复(读取输出文件以还原上下文)
  • 若超过24小时 → 全新开始(状态过期)
完成后,设置
"status": "completed"

Workflow

工作流程

Phase 0: Input Parsing & Context Gathering

阶段0:输入解析与上下文收集

Parse
$ARGUMENTS
to extract:
  1. Invention description — may be structured (references INVENTION_BRIEF.md), conversational with figures, or output from IDEA_REPORT.md
  2. Jurisdiction — detect from keywords (e.g., "CN" or "中国" -> CN, "US" or "USPTO" -> US, "EP" or "EPO" -> EP, "ALL")
  3. Patent type — detect from keywords (e.g., "utility model" or "实用新型" -> utility_model, default -> invention)
  4. Overrides — language, output format, review rounds
Then gather context from the project directory:
  1. Read
    INVENTION_BRIEF.md
    if it exists (user filled in the template)
  2. Read
    IDEA_REPORT.md
    if it exists (from
    /idea-discovery
    -- can extract invention from research results)
  3. Read
    refine-logs/FINAL_PROPOSAL.md
    if it exists
  4. Read
    NARRATIVE_REPORT.md
    if it exists (research results that may be patentable)
  5. Search for user-provided figures (PNG, JPG, SVG, PDF) in the project directory
  6. Check for
    patent/PATENT_STATE.json
    (resume from prior interrupted run)
If insufficient context exists:
  • No invention description at all -> suggest user describe the invention or fill in
    INVENTION_BRIEF.md
  • Has IDEA_REPORT.md -> extract patentable aspects from the research
  • Has figures -> reference them in the invention brief
  • No figures -> note that figures will be needed and plan what drawings are required
If the input is conversational (not a structured brief), parse the description into the invention brief structure and write
patent/INVENTION_BRIEF.md
for downstream phases.
解析
$ARGUMENTS
以提取:
  1. 发明描述 — 可能是结构化内容(参考INVENTION_BRIEF.md)、带附图的对话式描述,或IDEA_REPORT.md的输出内容
  2. 管辖地区 — 从关键词检测(例如:"CN"或"中国"→CN,"US"或"USPTO"→US,"EP"或"EPO"→EP,"ALL")
  3. 专利类型 — 从关键词检测(例如:"utility model"或"实用新型"→utility_model,默认→invention)
  4. 覆盖配置 — 语言、输出格式、审查轮次
然后从项目目录收集上下文:
  1. 若存在
    INVENTION_BRIEF.md
    则读取(用户已填写模板)
  2. 若存在
    IDEA_REPORT.md
    则读取(来自
    /idea-discovery
    ——可从研究成果中提取发明内容)
  3. 若存在
    refine-logs/FINAL_PROPOSAL.md
    则读取
  4. 若存在
    NARRATIVE_REPORT.md
    则读取(可能具备专利性的研究成果)
  5. 在项目目录中搜索用户提供的附图(PNG、JPG、SVG、PDF格式)
  6. 检查是否存在
    patent/PATENT_STATE.json
    (从之前中断的运行中恢复)
若上下文不足:
  • 完全没有发明描述 → 建议用户描述发明或填写
    INVENTION_BRIEF.md
  • 存在IDEA_REPORT.md → 从研究成果中提取具备专利性的内容
  • 存在附图 → 在发明摘要中引用这些附图
  • 无附图 → 记录需要附图,并规划所需的绘图内容
若输入为对话式内容(非结构化摘要),将描述解析为发明摘要结构,并写入
patent/INVENTION_BRIEF.md
供后续阶段使用。

Phase 1: Prior Art Search & Novelty Assessment

阶段1:现有技术检索与新颖性评估

1.1 Prior Art Search

1.1 现有技术检索

Invoke
/prior-art-search
:
/prior-art-search "patent/INVENTION_BRIEF.md"
This searches patent databases (Google Patents, Espacenet) and academic literature for relevant prior art.
调用
/prior-art-search
/prior-art-search "patent/INVENTION_BRIEF.md"
该步骤检索专利数据库(Google Patents、Espacenet)和学术文献,查找相关现有技术。

1.2 Novelty Check

1.2 新颖性检查

Invoke
/patent-novelty-check
:
/patent-novelty-check "patent/INVENTION_BRIEF.md"
This assesses novelty and non-obviousness against the prior art found in step 1.1.
🚦 Checkpoint: Present the prior art landscape and novelty assessment:
Prior art search complete:
- [X] patent references found
- [Y] non-patent literature references found
- Closest prior art: [reference] -- [why it's closest]
- Novelty assessment: [PATENTABLE / PATENTABLE WITH AMENDMENTS / NOT PATENTABLE]
- Key risk areas: [list]

Ready to proceed with invention structuring?
⛔ STOP HERE and wait for user response. Do NOT auto-proceed unless AUTO_PROCEED=true.
Options:
  • Reply "go" -> proceed to Phase 2
  • Reply with adjustments -> refine the invention scope and re-check novelty
  • Reply "stop" -> save progress to
    patent/DRAFT_NOTES.md
State: Write
PATENT_STATE.json
with
phase: 1
.
调用
/patent-novelty-check
/patent-novelty-check "patent/INVENTION_BRIEF.md"
该步骤针对1.1中找到的现有技术,评估发明的新颖性和非显而易见性。
🚦 检查点: 呈现现有技术概况和新颖性评估结果:
现有技术检索完成:
- [X] 找到专利参考文献
- [Y] 找到非专利文献参考文献
- 最接近的现有技术:[参考文献] -- [为何最接近]
- 新颖性评估:[具备专利性 / 修改后具备专利性 / 不具备专利性]
- 关键风险点:[列表]

是否准备进入发明结构化阶段?
⛔ 在此处停止并等待用户回复。 除非AUTO_PROCEED=true,否则请勿自动继续。
选项:
  • 回复**"go"** → 进入阶段2
  • 回复调整意见 → 调整发明范围并重新检查新颖性
  • 回复**"stop"** → 将进度保存至
    patent/DRAFT_NOTES.md
状态: 写入
PATENT_STATE.json
,设置
phase: 1

Phase 2: Invention Structuring & Claims Design

阶段2:发明结构化与权利要求设计

2.1 Structure the Invention

2.1 发明结构化

Invoke
/invention-structuring
:
/invention-structuring "patent/INVENTION_BRIEF.md"
This decomposes the invention into core inventive concept, supporting features, and optional features. Produces
patent/INVENTION_DISCLOSURE.md
.
调用
/invention-structuring
/invention-structuring "patent/INVENTION_BRIEF.md"
该步骤将发明分解为核心发明构思、支持性特征和可选特征,生成
patent/INVENTION_DISCLOSURE.md

2.2 Draft Claims

2.2 撰写权利要求

Invoke
/claims-drafting
:
/claims-drafting "patent/INVENTION_DISCLOSURE.md"
This drafts the claims hierarchy -- the most critical part of the patent. Produces
patent/CLAIMS.md
.
🚦 Checkpoint: Present the invention structure and claims:
Invention structured:
- Core inventive concept: [summary]
- Claim categories: [method, system, etc.]
- Claims drafted: [X] independent + [Y] dependent = [Z] total
- Independent claim 1 (broadest): [first 50 words of claim 1]
- Examiner review score: [X]/10

The claims define the legal scope of protection. Please review before proceeding to specification.
⛔ STOP HERE and wait for user response. Do NOT auto-proceed unless AUTO_PROCEED=true.
Options:
  • Reply "go" -> proceed to Phase 3
  • Reply with adjustments (e.g., "broaden claim 1", "add more dependent claims") -> revise claims
  • Reply "stop" -> save progress
State: Write
PATENT_STATE.json
with
phase: 2
.
调用
/claims-drafting
/claims-drafting "patent/INVENTION_DISCLOSURE.md"
该步骤撰写权利要求层级——这是专利最关键的部分,生成
patent/CLAIMS.md
🚦 检查点: 呈现发明结构和权利要求内容:
发明已完成结构化:
- 核心发明构思:[摘要]
- 权利要求类别:[方法、系统等]
- 已撰写权利要求:[X]项独立权利要求 + [Y]项从属权利要求 = [Z]项总计
- 独立权利要求1(最宽泛):[权利要求1的前50个单词]
- 审查员评分:[X]/10

权利要求定义了专利的法律保护范围,请在进入说明书撰写前进行审核。
⛔ 在此处停止并等待用户回复。 除非AUTO_PROCEED=true,否则请勿自动继续。
选项:
  • 回复**"go"** → 进入阶段3
  • 回复调整意见(例如:"拓宽权利要求1"、"添加更多从属权利要求")→ 修改权利要求
  • 回复**"stop"** → 保存进度
状态: 写入
PATENT_STATE.json
,设置
phase: 2

Phase 3: Specification Writing

阶段3:说明书撰写

Invoke
/specification-writing
:
/specification-writing "patent/CLAIMS.md"
This writes the full specification section by section. Internally invokes
/figure-description
(if user-provided figures exist) and
/embodiment-description
for the detailed description. The specification-writing skill handles figure processing and embodiment writing as sub-skills.
🚦 Checkpoint: Present the specification overview:
Specification written:
- Title: [title]
- Sections: Technical Field, Background, Summary, Drawings Description, Detailed Description, Abstract
- Embodiments: [X]
- Reference numerals: [Y] components mapped
- Abstract length: [Z] words (limit: [jurisdiction limit])
- Claim support: [all elements covered / X elements missing]

Ready to proceed to review?
⛔ STOP HERE and wait for user response.
State: Write
PATENT_STATE.json
with
phase: 3
.
调用
/specification-writing
/specification-writing "patent/CLAIMS.md"
该步骤逐节撰写完整的说明书,内部会调用
/figure-description
(若用户提供了附图)和
/embodiment-description
来撰写详细描述部分。说明书撰写Skill会将附图处理和实施例撰写作为子Skill进行处理。
🚦 检查点: 呈现说明书概述:
说明书撰写完成:
- 标题:[标题]
- 章节:技术领域、背景技术、发明内容、附图说明、具体实施方式、摘要
- 实施例数量:[X]
- 引用编号:[Y]个组件已映射
- 摘要长度:[Z]字(限制:[管辖地区限制])
- 权利要求支持:[所有要素已覆盖 / X个要素缺失]

是否准备进入审查阶段?
⛔ 在此处停止并等待用户回复。
状态: 写入
PATENT_STATE.json
,设置
phase: 3

Phase 4: Patent Review

阶段4:专利审查

Invoke
/patent-review
:
/patent-review "patent/"
This runs 2 rounds of examiner-style review via GPT-5.4 xhigh. The examiner evaluates clarity, written description, enablement, novelty, non-obviousness, and claim scope.
State: Write
PATENT_STATE.json
with
phase: 4
and review score.
调用
/patent-review
/patent-review "patent/"
该步骤通过GPT-5.4 xhigh进行2轮审查员风格的审查。审查员会评估清晰度、书面描述充分性、充分公开性、新颖性、非显而易见性和权利要求范围。
状态: 写入
PATENT_STATE.json
,设置
phase: 4
并记录审查评分。

Phase 5: Jurisdiction Formatting & Output

阶段5:管辖地区格式转换与输出

Invoke
/jurisdiction-format
:
/jurisdiction-format "patent/"
This compiles the application into the target jurisdiction format(s).
调用
/jurisdiction-format
/jurisdiction-format "patent/"
该步骤将申请文件编译为目标管辖地区的格式。

Final Deliverables

最终交付物

OutputLocationDescription
CN: 权利要求书
patent/output/CN/
Claims in CNIPA format
CN: 说明书
patent/output/CN/
Description in CNIPA format
CN: 说明书摘要
patent/output/CN/
Abstract (CN)
US: Claims
patent/output/US/
Claims in USPTO format
US: Specification
patent/output/US/
Description in USPTO format
US: Abstract
patent/output/US/
Abstract (US)
EP: Claims
patent/output/EP/
Claims in EPO format
EP: Description
patent/output/EP/
Description in EPO format
EP: Abstract
patent/output/EP/
Abstract (EP)
输出内容存储位置描述
CN: 权利要求书
patent/output/CN/
符合CNIPA格式的权利要求书
CN: 说明书
patent/output/CN/
符合CNIPA格式的说明书
CN: 说明书摘要
patent/output/CN/
中文摘要
US: Claims
patent/output/US/
符合USPTO格式的权利要求书
US: Specification
patent/output/US/
符合USPTO格式的说明书
US: Abstract
patent/output/US/
英文摘要(美国)
EP: Claims
patent/output/EP/
符合EPO格式的权利要求书
EP: Description
patent/output/EP/
符合EPO格式的说明书
EP: Abstract
patent/output/EP/
英文摘要(欧洲)

Final Report

最终报告

markdown
undefined
markdown
undefined

Patent Pipeline Complete

专利撰写流程完成

Application Summary

申请摘要

  • Title: [invention title]
  • Jurisdiction: [CN/US/EP/ALL]
  • Patent Type: [Invention / Utility Model]
  • Language: [Chinese/English]
  • Total Claims: [X] independent + [Y] dependent
  • 标题:[发明标题]
  • 管辖地区:[CN/US/EP/ALL]
  • 专利类型:[发明专利 / 实用新型专利]
  • 语言:[中文/英文]
  • 权利要求总数:[X]项独立权利要求 + [Y]项从属权利要求

Pipeline Scores

流程评分

PhaseScore
Prior Art Search[completeness assessment]
Novelty Assessment[PATENTABLE/PATENTABLE WITH AMENDMENTS/NOT PATENTABLE]
Examiner Review Round 1[X]/10
Examiner Review Round 2[Y]/10
Final[Z]/10
阶段评分
现有技术检索[完整性评估]
新颖性评估[具备专利性/修改后具备专利性/不具备专利性]
审查员第一轮审查[X]/10
审查员第二轮审查[Y]/10
最终评分[Z]/10

Output Files

输出文件

[Table of all generated files with paths]
[所有生成文件的路径表格]

Next Steps

后续步骤

  • Have a patent attorney review the application
  • Conduct professional prior art search (this tool's search is preliminary)
  • Prepare formal drawings (if user figures need professional rendering)
  • File with the patent office
  • For utility model (CN): formal examination typically takes 6-8 months
  • For invention patent: substantive examination may take 2-4 years

**State**: Write `PATENT_STATE.json` with `phase: 5, status: "completed"`.
  • 请专利律师审核申请文件
  • 进行专业的现有技术检索(本工具的检索为初步检索)
  • 准备正式附图(若用户提供的附图需要专业渲染)
  • 向专利局提交申请
  • 对于实用新型专利(中国):形式审查通常需要6-8个月
  • 对于发明专利:实质审查可能需要2-4年

**状态:** 写入`PATENT_STATE.json`,设置`phase: 5, status: "completed"`。

Key Rules

核心规则

  • Never fabricate prior art references, patent numbers, or citations.
  • Claims must be supported by the specification (written description requirement).
  • Each jurisdiction has strict format requirements -- do not mix formats.
  • Utility model (实用新型) applies ONLY to CN jurisdiction and ONLY covers apparatus/device claims.
  • AUTO_PROCEED defaults to false -- patent applications require human review at every phase. Sub-skills inherit this flag: when AUTO_PROCEED=false, sub-skills present results and wait at their own internal checkpoints too.
  • The patent pipeline produces drafts for attorney review, not final filing documents.
  • Large file handling: if a Write operation fails, retry with Bash
    cat <<'EOF'
    heredoc.
  • Never include experimental results or empirical evaluations in the specification.
  • Consistent terminology is mandatory -- same word for the same concept throughout.
  • If
    mcp__codex__codex
    is not available (no OpenAI API key), skip external cross-model review and note it in the output. The pipeline must not fail due to missing reviewer access.
  • 切勿编造现有技术参考文献、专利号或引用内容。
  • 权利要求必须得到说明书的支持(书面描述要求)。
  • 每个管辖地区都有严格的格式要求——请勿混合格式。
  • 实用新型专利(实用新型)仅适用于中国管辖地区,且仅覆盖装置/设备类权利要求。
  • AUTO_PROCEED默认值为false——专利申请的每个阶段都需要人工审核。子Skill会继承该标志:当AUTO_PROCEED=false时,子Skill也会在各自的内部检查点呈现结果并等待用户确认。
  • 专利撰写流程生成的是供律师审核的草稿,而非最终提交文件。
  • 大文件处理:若写入操作失败,使用Bash
    cat <<'EOF'
    heredoc重试。
  • 切勿在说明书中包含实验结果或实证评估内容。
  • 必须保持术语一致——同一概念在全文中使用相同表述。
  • mcp__codex__codex
    不可用(无OpenAI API密钥),跳过外部跨模型审查并在输出中注明。流程不得因缺少审查权限而失败。

Composing with Other Workflows

与其他工作流的组合

The patent pipeline can start from multiple entry points:
User describes invention directly ──→ /patent-pipeline

/idea-discovery produces IDEA_REPORT.md ──→ /patent-pipeline (extract patentable aspects)

/research-refine produces FINAL_PROPOSAL.md ──→ /patent-pipeline (from refined research idea)

/auto-review-loop produces strong results ──→ /patent-pipeline (patent the method)
专利撰写流程可从多个入口启动:
用户直接描述发明 ──→ /patent-pipeline

/idea-discovery生成IDEA_REPORT.md ──→ /patent-pipeline(提取具备专利性的内容)

/research-refine生成FINAL_PROPOSAL.md ──→ /patent-pipeline(基于优化后的研究创意)

/auto-review-loop产出优质成果 ──→ /patent-pipeline(为方法申请专利)

Acknowledgements

致谢

Built on the ARIS (Auto-claude-code-research-in-sleep) skill architecture. Patent writing principles adapted from MPEP (US), CN Patent Examination Guidelines (CN), and EPO Guidelines for Examination (EP).
基于ARIS(Auto-claude-code-research-in-sleep)Skill架构构建。专利撰写原则改编自MPEP(美国)、《中国专利审查指南》(中国)和EPO审查指南(欧洲)。