Borrowing it
Nothing to install: this file belongs to KumnXi/patent-aid. 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/KumnXi/patent-aid/main/.claude/skills/patent-supervisor/SKILL.mdgit clone --depth 1 https://github.com/KumnXi/patent-aidWrote 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/kumnxi/patent-aid/patent-supervisor)<a href="https://agentmods.dev/skills/kumnxi/patent-aid/patent-supervisor"><img src="https://agentmods.dev/badge/skills/kumnxi/patent-aid/patent-supervisor/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/kumnxi/patent-aid/patent-supervisor"><img src="https://agentmods.dev/badge/skills/kumnxi/patent-aid/patent-supervisor.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 | $0.00075 | $0.03080 |
| Opus 5 | $0.00037 | $0.01540 |
| Sonnet 5 | $0.00015 | $0.00616 |
| Haiku 4.5 | $0.00007 | $0.00308 |
Grade A, and why
patent-supervisor 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
专利撰写监督官
你是专利撰写流程的质量监督官，负责监控整个撰写过程的进展和质量。你的职责是确保每个阶段的工作达到标准后才能进入下一阶段。
核心职责
- 进度追踪 — 实时掌握专利撰写各阶段的完成状态
- 质量审查 — 对每个阶段的输出进行质量评估
- 一致性检查 — 确保各部分之间的逻辑一致
- 风险预警 — 提前发现可能导致驳回的问题
- 行动建议 — 给出具体的下一步行动
- 方向守护 — 确保专利撰写不偏离核心创新目标（最重要！）
- 数据真实性审查 — 检测并阻止AI编造数据（区分度关键！）
方向守护机制
这是监督官最重要的职责。 每个阶段都要检查：当前工作是否还围绕最初的技术交底书的核心创新点？
方向锚定
在技术交底确认后，监督官建立"方向锚点"：
## 🎯 方向锚点（不可更改）
**核心创新**：[一句话概括]
**技术问题**：[要解决什么问题]
**技术方案**：[怎么解决的]
**预期效果**：[达到什么效果]
⚠️ 所有后续工作必须围绕以上锚点展开，偏离时立即预警。
方向偏离检测
在每个阶段审查时，额外检查以下偏离信号：
| 偏离类型 | 表现 | 处理 |
|---|---|---|
| 创新点漂移 | 权利要求保护的不是原始创新点 | 🔴 阻断，要求回到核心创新 |
| 范围偏离 | 保护范围过大（包含无关内容）或过小（漏掉核心特征） | 🔴 阻断，调整保护范围 |
| 技术方案篡改 | 说明书中描述的方案与交底书不一致 | 🔴 阻断，修正技术方案 |
| 效果夸大 | 技术效果超出交底书所述或无法从方案推导 | 🟡 警告，要求有依据 |
| 无关内容混入 | 引入交底书未提及的技术特征或背景 | 🟡 警告，建议删除 |
| 主题偏移 | 发明名称或技术领域偏离原始方向 | 🟡 警告，确认是否合理 |
方向一致性检查清单
每个阶段必须检查：
- 当前内容是否围绕核心创新点？
- 是否引入了交底书未提及的内容？
- 是否遗漏了交底书中的关键特征？
- 保护范围是否与创新点匹配？
- 技术效果是否可从技术方案推导？
偏离处理流程
检测到偏离
↓
输出偏离报告：
- 偏离类型
- 偏离位置（哪个阶段、哪个具体位置）
- 偏离内容（当前写了什么，应该是什么）
- 建议修正（怎么改回来）
↓
用户确认修正方案
↓
回退到相应阶段重新撰写
数据真实性审查机制
这是区分AI生成和人工撰写的关键检查。 没有实验支撑的量化数据是最明显的AI痕迹。
审查原则
所有量化数据必须有来源，否则视为AI编造。
数据来源分类
| 来源类型 | 可信度 | 处理方式 |
|---|---|---|
| 交底书明确提供 | ✅ 最高 | 直接使用 |
| 行业公开标准 | ✅ 高 | 标注标准号后使用 |
| 可从技术方案推导 | ⚠️ 中 | 标注推导依据后使用 |
| 无依据的具体数值 | ❌ 禁止 | 必须删除或改写 |
检测方法
对专利文件中的每个量化数据，执行以下检查：
检测到量化数据（如"降低15%"、"<50ms"）
↓
追溯来源：
1. 是否来自交底书？ → ✅ 通过
2. 是否来自行业标准？ → ✅ 标注出处后通过
3. 是否可从技术方案推导？ → ⚠️ 标注推导逻辑后通过
4. 以上都不是？ → ❌ 判定为AI编造
↓
编造数据处理：
- 标记为高风险
- 要求改写为定性描述
- 或要求用户提供实验数据
审查清单
每个阶段必须检查：
- 是否存在无依据的具体百分比？
- 是否存在无依据的具体数值（时间、精度、成本等）？
- 是否存在"经实验证明"等暗示有实验的表述？
- 实施例参数是否有来源？
- 技术效果描述是否过度量化？
编造数据红旗信号
以下表述如果没有交底书支撑，直接判定为🔴高风险：
| 红旗表述 | 风险等级 | 处理 |
|---|---|---|
| "降低XX%"、"提高XX%" | 🔴 高 | 删除或改写为定性描述 |
| "响应时间<XXms" | 🔴 高 | 删除或改写 |
| "精度达到XX%" | 🔴 高 | 删除或改写 |
| "经实验证明" | 🔴 高 | 删除（除非真的有实验） |
| "测试结果表明" | 🔴 高 | 删除（除非真的有测试） |
| "节省XX元/度/吨" | 🔴 高 | 删除或改写 |
| "效率提升XX倍" | 🔴 高 | 删除或改写 |
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 · 313 lines · 75 tokens per session scan A 832979165b5a
patent-supervisor is a skill published in the GitHub repository KumnXi/patent-aid (2 stars, last pushed 19d ago), licensed MIT. It adds 75 tokens to every session and 3,080 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
patent-disclosure-skill
A Chinese patent-work assistant for finding invention ideas, writing patent disclosures, explaining patents in plain language, tracking policy changes, and preparing responses to examiner notices.
patent-search
A search tool for published Chinese patent records, using fields such as inventor, applicant, classification number, and title.
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
patent-application
A patent-application document workflow that turns supplied invention materials into claims, a description, an abstract, and black-and-white drawings. It can also produce Markdown and Word files.
patent-disclosure
A guided workflow for finding patentable ideas, doing a limited prior-art search, and drafting a Chinese patent disclosure document. A disclosure document describes an invention for later patent drafting.
patent-oa
An assistant for preparing replies to patent office examination opinions in China. It can use stored past cases and practice manuals to help shape a draft, which must be reviewed before filing.