Back to Details

patent

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Patent — Prior-Art + Landscape Intelligence

专利——现有技术+态势智能

Portability: Requires 
web_fetch
(Google Patents, Espacenet, USPTO), 
WebSearch
(adjacent academic art), Node.js with 
docx
package, and optionally Lens.org API key for citation-graph signals. Works in Claude Code CLI natively. In Claude.ai with web tools + Code Execution + BYOK Lens.org, the workflow is supported.
Out of scope: trademark, copyright, trade-secret. These are flagged at intake. Use a different skill or qualified counsel.
Legal disclaimer: This skill produces search signal, not legal advice. Verdicts are technical assessments. Always consult a patent attorney before filing or licensing decisions.
可移植性: 需要
web_fetch
（Google Patents、Espacenet、USPTO）、
WebSearch
（相关学术文献）、带有
docx
包的Node.js，若要获取引用图谱信号还可选择配置Lens.org API密钥。原生支持Claude Code CLI。在配备Web工具+代码执行+BYOK Lens.org的Claude.ai环境中，该工作流同样受支持。
服务范围外: 商标、版权、商业秘密相关内容。这些会在引导阶段被标记，请使用其他Skill或咨询合格法律顾问。
法律声明: 本Skill仅提供检索信号，不构成法律建议。结论仅为技术评估。在提交专利申请或做出许可决策前，请务必咨询专利律师。

Non-Generic Framing — The Differentiator

非通用定位——核心差异化

This skill is prior-art + landscape intelligence. It refuses to be a bucket. Every invocation commits to one of five sub-use-cases via the grill-me intake before any search runs. The chosen sub-use-case dictates the entire search strategy, ranking heuristics, and DOCX emphasis.
Sub-use-caseSearch strategyDOCX emphasis
Novelty searchNarrow + claims-text focused; pre-filing date irrelevantClosest art + claim-differentiation
Freedom-to-operateBroad + active patents only; jurisdiction-filteredFTO flags + claim-by-claim risk
Competitive landscapeBreadth + filer tally + CPC trendsFiler map + investment hotspots
Acquisition diligenceSpecific assignee + portfolio scope + assignment chainPortfolio table + ownership verification
Litigation prior-artSpecific target patent + adjacent art before priority dateKnock-out candidates ranked by relevance
See 
references/sub_use_case_routing.md
 for the canon.
本Skill聚焦现有技术+态势智能，拒绝成为通用工具。每次调用都会通过“追问引导”流程让用户选定五个子用例之一，之后才会启动检索。选定的子用例将决定整个检索策略、排序规则以及DOCX文档的重点内容。
子用例检索策略DOCX文档重点
新颖性检索精准聚焦+权利要求文本导向；不考虑申请日期最相关现有技术+权利要求差异化分析
自由实施分析（FTO）广泛检索+仅包含有效专利；按司法辖区过滤FTO风险标记+逐条权利要求风险分析
竞争态势分析全面覆盖+申请人统计+CPC趋势分析申请人分布图+投资热点区域
收购尽职调查特定权利人检索+专利组合范围+转让链核查专利组合表格+所有权验证
诉讼现有技术检索特定目标专利检索+优先权日前的相关技术按相关性排序的无效候选专利
详见
references/sub_use_case_routing.md
中的规范说明。

Agent Integrity Rules (Research-Pack Convention)

Agent合规规则（研究包约定）

Locked verbatim per PR #657 audit.
  • Execution discipline. Sequential search calls only. 1 query/sec rate limit. Confirm response received before next call.
  • Source discipline. Cite only patents returned by THIS session's tool calls. Training knowledge labeled 
    [Not from search — reference information]
    and excluded from counts.
  • Three-count tracking. Queries sent / patents received (shown) / patents cited. Surfaced in audit log.
  • Retry policy. On failure → wait 3s → retry once → log. After 3 consecutive failures across tools: stop, alert user, explain what's missing.
  • Plan-tier detection. Lens.org free tier = 1000 queries/month. Google Patents has no auth but rate-limits per IP. Detect and surface caps.
严格遵循PR #657审核后的内容。
  • 执行规范: 仅允许顺序调用检索接口。速率限制：1次查询/秒。确认收到响应后再发起下一次查询。
  • 来源规范: 仅引用本次会话中工具调用返回的专利。训练知识库内容需标记
    [Not from search — reference information]
    ，且不计入统计。
  • 三项计数跟踪: 已发送查询数/已接收专利数（显示）/已引用专利数。在审计日志中展示。
  • 重试策略: 调用失败→等待3秒→重试1次→记录日志。若跨工具连续3次失败：停止操作，提醒用户，说明缺失内容。
  • 套餐层级检测: Lens.org免费套餐=每月1000次查询。Google Patents无需授权但按IP限制速率。需检测并告知用户限额情况。

Phase 1: Grill-Me Intake (6 forcing questions, one at a time)

阶段1：追问引导（6个强制问题，逐一提问）

Q1 (root) — Invention description

Q1（核心）——发明描述

Describe the invention in 2–3 sentences. What does it do, and what's new about it?
Why I'm asking: Concept and keyword extraction depends entirely on a precise description. Vague descriptions ("AI for healthcare", "a better widget") will be rejected — push back and ask the user to specify what the invention does and what differentiates it from existing approaches.
Refuse mush. If answer is generic, ask once more: "What does it do that existing systems don't?" Then commit (with caveat in DOCX).
用2-3句话描述发明内容。它的功能是什么，创新点在哪里？
提问原因: 概念提取和关键词生成完全依赖精准描述。模糊描述（如“医疗AI”“更好的小部件”）会被拒绝——需追问用户，让其明确发明功能及与现有方案的差异。
拒绝模糊表述。若回答过于通用，再次追问：“它能实现哪些现有系统无法做到的功能？”之后记录（并在DOCX中注明说明）。

Q2 (depends on Q1) — Sub-use-case commitment

Q2（基于Q1）——子用例确认

What's the purpose of this search? Pick one:
  1. Novelty search (am I novel enough to file)
  2. Freedom-to-operate (will I get sued if I ship)
  3. Competitive landscape (who else plays here)
  4. Acquisition diligence (does target really own X)
  5. Litigation prior-art hunting (kill a specific patent)
Why I'm asking: Each path uses a fundamentally different search strategy. I'll refuse to start without you picking one.
Forcing format. If user says "all of them", push for the primary purpose — secondary purposes can run as follow-up searches.
本次检索的目的是什么？请选择一项：
  1. 新颖性检索（是否具备申请专利的新颖性）
  2. 自由实施分析（产品上市是否会侵权）
  3. 竞争态势分析（领域内其他参与者情况）
  4. 收购尽职调查（目标方是否真的拥有某项专利）
  5. 诉讼现有技术检索（无效特定专利）
提问原因: 每个子用例对应完全不同的检索策略。未选定子用例前，将拒绝启动检索。
强制选择格式。若用户表示“全部都要”，请其优先选择核心目的——次要目的可作为后续检索任务。

Q3 (asked only if Q2 ∈ {FTO, landscape, diligence}) — Jurisdictions

Q3（仅当Q2为{FTO、态势分析、尽职调查}时提问）——司法辖区

Which jurisdictions matter? Pick all that apply: US / EP / CN / JP / KR / PCT / worldwide.
Why I'm asking: FTO only matters where you'll sell. Landscape changes radically by region. Diligence requires checking all jurisdictions where the target operates.
Skip for novelty (priority date is jurisdictionally portable) and litigation (jurisdiction is set by the target patent).
哪些司法辖区是重点？可多选：美国/欧盟/中国/日本/韩国/PCT/全球。
提问原因: FTO风险仅与产品销售区域相关。不同区域的专利态势差异极大。尽职调查需核查目标方运营的所有司法辖区。
新颖性检索（优先权日具有跨辖区效力）和诉讼检索（司法辖区由目标专利决定）跳过此问题。

Q4 (depends on Q1) — Known prior art

Q4（基于Q1）——已知现有技术

Have you already seen prior art close to this? Cite a patent number or paper.
Why I'm asking: If you know one piece of art, I can search adjacent to it — much more precise than starting cold. If you don't, that's fine — just confirm.
Anchoring. Accept "none" but ask if the user has seen any related work even informally.
您是否已了解与该发明相关的现有技术？请提供专利号或论文信息。
提问原因: 若您已知某项相关技术，可围绕其进行精准检索——比从零开始检索效率更高。若没有相关信息，确认即可。
锚定检索。接受“无”的回答，但需询问用户是否见过任何相关研究（即使是非正式的）。

Q5 (depends on Q2) — Risk tolerance

Q5（基于Q2）——风险容忍度

Risk tolerance for this search: strict (one close hit means abandon the path) or signal-gathering (you want the lay of the land regardless)?
Why I'm asking: Strict mode ranks aggressively and surfaces verdict-grade hits; signal mode prioritizes breadth and visualizations.
Asked for novelty and FTO; skipped for pure landscape (always signal-gathering by definition).
本次检索的风险容忍度：严格（只要有一个高度相关结果就放弃该方向）还是信号收集（无论如何都要了解整体态势）？
提问原因: 严格模式会优先排序高相关度结果并给出明确结论；信号收集模式则优先覆盖范围和可视化展示。
仅针对新颖性检索和FTO分析提问；纯态势分析默认始终为信号收集模式，跳过此问题。

Q6 (asked only if Q2 ∈ {novelty, FTO}) — Attorney status

Q6（仅当Q2为{新颖性检索、FTO分析}时提问）——律师咨询状态

Have you spoken to a patent attorney? This skill produces search signal, not legal advice. Confirm you understand this is for technical assessment only.
Why I'm asking: Novelty and FTO have legal consequences. The skill's verdict is signal-grade; legal positions require qualified counsel.
Triggers the legal-disclaimer footer in the DOCX. Skipped for landscape and diligence (lower legal exposure).
Stop condition: After Q6 (or earlier if dependency skips applied), commit and start Phase 2. Never re-open intake after Phase 2 begins.
您是否已咨询过专利律师？本Skill仅提供检索信号，不构成法律建议。请确认您理解本结果仅用于技术评估。
提问原因: 新颖性和FTO分析涉及法律后果。Skill的结论仅为参考信号，法律立场需由合格法律顾问确定。
将在DOCX文档底部添加法律声明。态势分析和尽职调查（法律风险较低）跳过此问题。
停止条件: 完成Q6后（或因依赖关系提前结束），确认并启动阶段2。阶段2启动后不得重新开启引导流程。

Phase 2: Search Strategy Selection

阶段2：检索策略选择

Deterministic from intake answers. Use 
scripts/sub_use_case_router.py
:
bash
python ../scripts/sub_use_case_router.py \
  --sub-use-case novelty \
  --jurisdictions "" \
  --risk strict \
  --known-art "US10000000B2"
Returns: query plan (5-8 queries) + ranking heuristic + DOCX emphasis flags.
根据引导阶段的答案确定检索策略。使用
scripts/sub_use_case_router.py
脚本：
bash
python ../scripts/sub_use_case_router.py \
  --sub-use-case novelty \
  --jurisdictions "" \
  --risk strict \
  --known-art "US10000000B2"
返回结果：查询计划（5-8个查询）+排序规则+DOCX文档重点标记。

Phase 3: Multi-Source Search (Sequential)

阶段3：多源检索（顺序执行）

Source priority

来源优先级

  1. Google Patents (https://patents.google.com) — workhorse, no auth required, broad coverage
  2. Espacenet (https://worldwide.espacenet.com) — global coverage, good for non-US art
  3. USPTO PPS (https://ppubs.uspto.gov) — US deep dive
  4. Lens.org (https://www.lens.org) — citation graph, BYOK API key required
  1. Google Patents（https://patents.google.com）——核心工具，无需授权，覆盖范围广
  2. Espacenet（https://worldwide.espacenet.com）——全球覆盖，适合非美国专利检索
  3. USPTO PPS（https://ppubs.uspto.gov）——美国专利深度检索
  4. Lens.org（https://www.lens.org）——引用图谱，需自备API密钥（BYOK）

Per-sub-use-case query patterns

各子用例查询模式

Novelty:
  • 3 narrow queries on invention-specific terminology (Google Patents)
  • 2 broad concept queries with synonyms (Google Patents + Espacenet)
  • 1 CPC-class-restricted query if class identified from initial hits
FTO:
  • Jurisdiction-filtered: only active patents (not expired, not abandoned)
  • Date filter: priority < today
  • Active-claim text extraction for each hit
Competitive landscape:
  • Broader queries on the technology space
  • CPC class identification → tally top filers in that class
  • 10-year filing trend by year per top-5 filer
Acquisition diligence:
  • Specific assignee searches (target company + subsidiaries + named inventors)
  • Assignment chain check (USPTO assignment recordation)
  • Family resolution for deduplication
Litigation prior-art:
  • Target patent input required (number)
  • Priority date extraction
  • Search for art before priority date in same CPC classes
  • Adjacent-claim-language search
新颖性检索:
  • 3个基于发明特定术语的精准查询（Google Patents）
  • 2个包含同义词的宽泛概念查询（Google Patents + Espacenet）
  • 若从初始结果中识别出CPC分类，执行1次分类限制查询
FTO分析:
  • 按司法辖区过滤：仅包含有效专利（未过期、未放弃）
  • 日期过滤：优先权日<当前日期
  • 提取每个结果的有效权利要求文本
竞争态势分析:
  • 针对技术领域的宽泛查询
  • 识别CPC分类→统计该分类下的主要申请人
  • 前5位申请人的10年申请趋势
收购尽职调查:
  • 特定权利人检索（目标公司+子公司+指定发明人）
  • 转让链核查（USPTO转让记录）
  • 同族专利去重
诉讼现有技术检索:
  • 需输入目标专利号
  • 提取优先权日
  • 检索优先权日前同一CPC分类下的相关技术
  • 相关权利要求语言检索

Sequential discipline

顺序执行规范

1 q/sec across ALL sources combined. Tracked via 
scripts/citation_tracker.py
with timestamp-enforced gap.
所有来源合并执行速率限制：1次查询/秒。通过
scripts/citation_tracker.py
脚本跟踪，强制执行时间间隔。

Phase 4: Claim Extraction + Relevance Scoring

阶段4：权利要求提取+相关性评分

For each closest-art hit:
  • Pull independent claim 1 (the broadest claim — primary anticipation/obviousness vehicle)
  • Pull key dependent claims (claims that add the inventive step)
  • Score relevance against invention description (overlap of claim language with Q1 terminology)
Rank by score. Verdict per sub-use-case (NOVEL / POTENTIALLY NOVEL / NOT NOVEL for novelty; CLEAR / FLAGGED / HIGH RISK per jurisdiction for FTO).
针对每个高相关结果：
  • 提取独立权利要求1（最宽泛的权利要求——判断侵权/显而易见性的核心依据）
  • 提取关键从属权利要求（包含创新点的权利要求）
  • 根据发明描述（Q1中的术语）对相关性进行评分
按评分排序。根据子用例给出结论（新颖性检索：新颖/可能新颖/不新颖；FTO分析：无风险/标记风险/高风险，按司法辖区划分）。

Phase 5: Citation Graph + Family Resolution

阶段5：引用图谱+同族专利去重

Citation graph (Lens.org BYOK)

引用图谱（Lens.org BYOK）

If user provides Lens.org API key:
  • Foundational-patent identification (cited-by count > threshold, typically 50+)
  • Recent high-cite signals (citations in last 24 months as proxy for current activity)
  • Forward citations from target patent (litigation prior-art) or from closest art (novelty)
If no Lens.org key: skip; note in audit log; recommend manual citation review on Google Patents.
若用户提供Lens.org API密钥：
  • 识别基础专利（引用数>阈值，通常为50+）
  • 近期高引用信号（过去24个月的引用数作为当前活跃度指标）
  • 目标专利（诉讼检索）或最相关技术（新颖性检索）的后续引用
若无Lens.org密钥：跳过此步骤，在审计日志中注明；建议在Google Patents上手动查看引用关系。

Family resolution

同族专利去重

Same invention often filed in multiple jurisdictions (US + EP + JP + CN). Group by family ID or priority number to avoid double-counting. Use 
scripts/family_resolver.py
:
bash
python ../scripts/family_resolver.py --hits-file hits.json
同一发明通常会在多个司法辖区申请（美国+欧盟+日本+中国）。按同族ID或优先权号分组，避免重复统计。使用
scripts/family_resolver.py
脚本：
bash
python ../scripts/family_resolver.py --hits-file hits.json

Returns: deduplicated family list + family-member jurisdictions

返回结果：去重后的同族专利列表+同族专利所在司法辖区

undefined
undefined

CPC/IPC Classification Awareness

CPC/IPC分类感知

Critical: keyword search alone misses adjacent art. After initial search, extract the CPC/IPC classes from top 5 hits and run one class-restricted query. This consistently surfaces art that keyword search misses.
See 
references/cpc_classification_canon.md
 for the canon.
关键要点: 仅靠关键词检索会遗漏相关技术。初始检索后，从排名前5的结果中提取CPC/IPC分类，执行1次分类限制查询。这一操作能持续发现关键词检索遗漏的技术。
详见
references/cpc_classification_canon.md
中的规范说明。

Phase 6: DOCX Generation (8 Sections)

阶段6：DOCX文档生成（8个章节）

Sub-use-case-dependent emphasis. Via Node.js + 
docx
library.
  1. Executive Summary + Verdict — Sub-use-case banner + one-line verdict (NOVEL / FLAGGED / etc.) + 3-4 key findings + legal disclaimer footer
  2. Closest Prior Art — 5-10 patents in ranked order. Per hit: hyperlinked title + assignee + filing/priority dates + independent claim 1 text (italicized) + relevance score + relevance rationale (1-2 sentences)
  3. Patent Landscape — Top filers table (top 10 by count) + 10-year filing trend description + CPC class distribution table. Only for landscape and diligence; abbreviated otherwise.
  4. Citation Graph Signals — Foundational patents (if Lens-enabled) + recent high-cite activity. If Lens unavailable, note "manual review recommended" and skip table.
  5. Geographic Coverage — Filings by jurisdiction for top 10 hits. Only for FTO, landscape, diligence; skipped for novelty and litigation.
  6. FTO Flags (FTO only) — Active patents posing infringement risk. Per flag: hyperlinked patent + jurisdiction + relevant claims + risk level (HIGH/MEDIUM/LOW) + mitigation note.
  7. Strategy + Recommendations — Sub-use-case-specific:
    • Novelty → claim differentiation suggestions
    • FTO → design-around hints + jurisdiction strategy
    • Landscape → who-to-watch list
    • Diligence → red flags in portfolio
    • Litigation → ranked knock-out candidates
    • Mandatory disclaimer to consult patent attorney for any filing/licensing decision.
  8. Audit Log — Searches table (#, query, source, results, status), counts (sent/shown/cited), tool constraints (plan-tier notes), failed steps, attorney-consultation reminder
根据子用例调整重点内容。通过Node.js + 
docx
库生成。
  1. 执行摘要+结论——子用例标题+一句话结论（新颖/标记风险等）+3-4个核心发现+底部法律声明
  2. 最相关现有技术——5-10个按相关性排序的专利。每个结果包含：超链接标题+权利人+申请/优先权日+独立权利要求1文本（斜体）+相关性评分+相关性说明（1-2句话）
  3. 专利态势——主要申请人表格（前10位）+10年申请趋势描述+CPC分类分布表格。仅在态势分析和尽职调查中完整展示；其他场景简化展示。
  4. 引用图谱信号——基础专利（若启用Lens）+近期高引用活动。若无Lens，注明“建议手动查看”并跳过表格。
  5. 地域覆盖——排名前10的结果按司法辖区分布。仅在FTO分析、态势分析、尽职调查中展示；新颖性检索和诉讼检索跳过此章节。
  6. FTO风险标记（仅FTO分析）——存在侵权风险的有效专利。每个标记包含：超链接专利+司法辖区+相关权利要求+风险等级（高/中/低）+缓解建议。
  7. 策略建议——针对子用例的特定建议：
    • 新颖性检索→权利要求差异化建议
    • FTO分析→规避设计提示+司法辖区策略
    • 态势分析→重点关注对象列表
    • 尽职调查→专利组合中的风险点
    • 诉讼检索→按相关性排序的无效候选专利
    • 强制声明：任何申请/许可决策前需咨询专利律师。
  8. 审计日志——检索表格（编号、查询内容、来源、结果数、状态）、计数（已发送/已显示/已引用）、工具限制（套餐层级说明）、失败步骤、律师咨询提醒

Styling

样式规范

Arial 12pt body, navy headings (#1a3a5c), light blue table headers (#e8f0f8), red FTO-flag callout. 
ExternalHyperlink
patterns:
  • Google Patents: 
    https://patents.google.com/patent/[number]
  • Espacenet: 
    https://worldwide.espacenet.com/patent/...
  • USPTO: 
    https://patents.uspto.gov/patent/...
正文为Arial 12号字体，标题为深蓝色（#1a3a5c），表格表头为浅蓝色（#e8f0f8），FTO风险标记为红色。
ExternalHyperlink
格式：
  • Google Patents: 
    https://patents.google.com/patent/[number]
  • Espacenet: 
    https://worldwide.espacenet.com/patent/...
  • USPTO: 
    https://patents.uspto.gov/patent/...

Date Discipline

日期规范

Distinguish at every hit:
  • Filing date — when the application was first submitted
  • Priority date — earliest claim of priority (often earlier than filing)
  • Publication date — when the application became public (typically 18 months after priority)
  • Grant date — when the patent was granted (later than publication)
Surface the legally-relevant date per sub-use-case:
  • Novelty → priority date (vs invention's anticipated filing date)
  • FTO → grant date + status (active vs expired)
  • Landscape → publication date (when public knowledge began)
  • Diligence → grant date + assignment date
  • Litigation → priority date of target patent (sets the prior-art cutoff)
针对每个结果需区分：
  • 申请日——首次提交申请的日期
  • 优先权日——最早主张优先权的日期（通常早于申请日）
  • 公开日——申请公开的日期（通常为优先权日后18个月）
  • 授权日——专利获得授权的日期（晚于公开日）
根据子用例展示法律相关日期：
  • 新颖性检索→优先权日（与发明预期申请日对比）
  • FTO分析→授权日+状态（有效/过期）
  • 态势分析→公开日（成为公共知识的日期）
  • 尽职调查→授权日+转让日
  • 诉讼检索→目标专利的优先权日（现有技术截止日期）

Phase 7: Deliver

阶段7：交付

  • Save: 
    <output-dir>/patent_<invention-slug>_<sub-use-case>_<YYYY-MM-DD>.docx
  • Chat summary: file path + sub-use-case + verdict + audit counts + plan-tier
  • Validate: 
    python scripts/office/validate.py <docx>
  • Reminder: "Consult patent attorney before filing/licensing"
  • 保存路径：
    <output-dir>/patent_<invention-slug>_<sub-use-case>_<YYYY-MM-DD>.docx
  • 聊天摘要：文件路径+子用例+结论+审计计数+套餐层级
  • 验证：
    python scripts/office/validate.py <docx>
  • 提醒：“提交申请/许可决策前请咨询专利律师”

Tooling

工具列表

ScriptRole
scripts/citation_tracker.py
Multi-source three-count audit (Google Patents + Espacenet + USPTO + Lens.org) at 
~/.patent_sessions/<session>.json
scripts/family_resolver.py
Group same-invention filings across jurisdictions by family ID / priority number
scripts/sub_use_case_router.py
Deterministic search-strategy selection from intake answers
脚本作用
scripts/citation_tracker.py
多源三项计数审计（Google Patents + Espacenet + USPTO + Lens.org），存储于
~/.patent_sessions/<session>.json
scripts/family_resolver.py
按同族ID/优先权号对跨司法辖区的同一发明申请进行分组
scripts/sub_use_case_router.py
根据引导阶段答案确定检索策略

References

参考文档

  • references/sub_use_case_routing.md
     — 5-sub-use-case canon (7+ sources)
  • references/cpc_classification_canon.md
     — CPC/IPC class follow-up rationale (7+ sources)
  • references/legal_disclaimer_discipline.md
     — when + why disclaimer mandatory (7+ sources)
  • references/sub_use_case_routing.md
    ——5个子用例规范（7+来源）
  • references/cpc_classification_canon.md
    ——CPC/IPC分类后续检索依据（7+来源）
  • references/legal_disclaimer_discipline.md
    ——法律声明的适用场景及原因（7+来源）

Error Handling

错误处理

FailureBehavior
User refuses to commit to sub-use-caseRefuse to proceed. Re-ask Q2 with examples.
Invention description is genericReject answer. Re-ask Q1 with "what does it do that existing systems don't?"
Google Patents rate-limitsWait 3s, retry once. Fall back to Espacenet for that query. Log in audit.
Lens.org key missingSkip citation graph section, note "manual review recommended" in DOCX.
Claim text extraction failsFall back to abstract; flag as "abstract-only" in relevance rationale.
Family resolution incompleteNote in audit; same-invention duplicates may appear; suggest manual deduplication.
All searches return <3 hitsSurface explicitly as "either niche art or genuine gap"; never fabricate.
3 consecutive tool failuresStop, alert user, explain what's missing.
DOCX generation failsSave raw data as JSON fallback so user doesn't lose work.
Target patent number invalid (litigation)Validate format before search; ask user to confirm.
故障场景处理方式
用户拒绝选定子用例拒绝继续执行。重新提问Q2并给出示例。
发明描述模糊拒绝回答。重新提问Q1，要求说明“它能实现哪些现有系统无法做到的功能？”
Google Patents速率限制等待3秒，重试1次。改用Espacenet执行该查询。记录到审计日志。
缺少Lens.org密钥跳过引用图谱章节，在DOCX中注明“建议手动查看”。
权利要求文本提取失败改用摘要文本；在相关性说明中标记“仅摘要”。
同族专利去重不完整在审计日志中注明；可能出现同一发明重复结果；建议手动去重。
所有检索结果<3个明确告知用户“要么是小众技术，要么确实存在技术空白”；绝不编造结果。
连续3次工具调用失败停止操作，提醒用户，说明缺失内容。
DOCX生成失败将原始数据保存为JSON作为备份，避免用户丢失工作成果。
目标专利号无效（诉讼检索）检索前验证格式；请用户确认。

Anti-Patterns To Reject

需拒绝的反模式

  • Starting any search before user commits to a sub-use-case (refuses generic "patent help")
  • Batching all intake questions instead of one at a time
  • Accepting vague invention descriptions ("AI for healthcare")
  • Keyword-only search without CPC/IPC class follow-up
  • Treating family members as separate hits (must be deduplicated)
  • Confusing filing date with priority date with publication date
  • Skipping the legal disclaimer when sub-use-case has legal consequences
  • Reporting a verdict without claim-text evidence
  • Fabricating Lens.org citation data when key is absent
  • Suggesting design-arounds without acknowledging attorney review is required
  • Skipping the audit log
Version: 1.0.0 Source spec: 
megaprompts/11-patent-megaprompt.md
 Build pattern: Path B (direct conversion). Research-pack sibling, sub-use-case routing variant.
  • 用户未选定子用例就启动检索（拒绝通用“专利辅助”请求）
  • 一次性提出所有引导问题，而非逐一提问
  • 接受模糊的发明描述（如“医疗AI”）
  • 仅进行关键词检索，未执行CPC/IPC分类后续检索
  • 将同族专利视为独立结果（必须去重）
  • 混淆申请日、优先权日、公开日
  • 子用例涉及法律后果时跳过法律声明
  • 未提供权利要求文本证据就给出结论
  • 缺少密钥时编造Lens.org引用数据
  • 给出规避设计建议但未提及需咨询律师
  • 跳过审计日志
版本: 1.0.0 来源规范: 
megaprompts/11-patent-megaprompt.md
 构建模式: Path B（直接转换）。研究包姊妹篇，子用例路由变体。