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 seed-forge/harness-ai-kit --skill patent-reviewgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/patent-review)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/patent-review"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/patent-review/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/seed-forge/harness-ai-kit/patent-review"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/patent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.02542 |
| Opus 5 | $0.00032 | $0.01271 |
| Sonnet 5 | $0.00013 | $0.00508 |
| Haiku 4.5 | $0.00006 | $0.00254 |
Grade A, and why
patent-review 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
patent-review
用途
面向中文专利技术交底书的 多轮循环严格审查 技能。在 patent-disclosure-workflow（编写层）和 work-sc-patent-docx-exporter（导出层）之间插入审查闭环，确保交底材料在导出前经过充分逻辑验证。
适用场景：
- 专利交底书
.md初稿完成后，需要逐行审查逻辑闭合性 - 多份关联专利文档之间的跨文档接口一致性检查
- 需要量化审查质量：多轮循环直到连续N轮无阻塞问题
- 客户审阅或提交专利局前的最后一次质量把关
与现有专利技能的关系
patent-disclosure-workflow (编排层)
├── patent-specification-writer (写作)
├── patent-review (审查闭环) ← 本技能
│ ├── 多轮循环审查
│ ├── 多维度审查
│ └── 可选修复（默认dry-run）
└── work-sc-patent-docx-exporter (导出)
本技能不负责：写作、润色、格式调整、Word 导出、权利要求书起草。
输入
- 一份或多份专利技术交底书
.md文件（绝对路径） - 可选：
--fix标志（启用自动修复模式，默认关闭） - 可选：
--rounds N（最大审查轮次，默认无限制） - 可选：
--dimensions（指定审查维度子集，默认全维度） - 可选：附图文件（PNG/drawio XML）用于图文一致性审查
输出
- 每轮审查的问题清单（按严重程度分级：阻塞/中等/轻微）
- 问题趋势报告（问题数量随轮次递减曲线）
- 修复状态追踪（哪些已修复、哪些需人工确认）
- 最终交付结论（是否建议导出Word/提交客户审阅）
核心工作流
阶段一：启动审查
- 确认输入文件存在且为
.md格式 - 识别输入文件数量：
- 单文件模式：仅审查单份交底书的内部逻辑闭合性
- 多文件模式：额外启用跨文档接口一致性检查
- 读取全部输入文件全文
- 若含
--dimensions，从审查维度矩阵中选择指定维度；否则默认全部7个维度（见专题引用）
阶段二：多轮循环审查
FOR round = 1, 2, 3, ... UNTIL 连续N轮无阻塞问题：
1. 从零逐行审查（不参考前一轮结果，确保独立判断）
2. 按7个审查维度逐一检查
3. 输出问题清单（阻塞/中等/轻微分级）
4. 若发现阻塞问题：
a. 默认模式（dry-run）：列出问题，等待用户指令
b. --fix 模式：中等和轻微问题自动修复；阻塞问题列出示警，AskUserQuestion 逐项确认后修复
5. 记录本轮问题数量和严重程度
6. 若本轮无阻塞问题，clean_count++；否则 clean_count=0
7. 若 clean_count >= REQUIRED_CLEAN_ROUNDS (默认3)，输出最终报告并结束
END FOR
收敛判断：连续3轮无阻塞问题即可交付。如果连续3轮后问题数仍在下降趋势中，继续审查直到收敛平稳。
阶段三：输出最终报告
- 全轮次问题数量趋势表
- 剩余已知优化项（非阻塞）清单
- 交付结论：是否建议导出Word/提交客户审阅
- 修复记录摘要
审查维度矩阵
| 编号 | 维度 | 检查内容 | 阻塞判定 |
|---|---|---|---|
| D1 | 数据流闭合 | 步骤间输入/输出是否一一对应；字段是否有明确的写入步骤和读取步骤；表格定义但正文未使用的"孤儿字段" | 数据来源断裂、无写入步骤的字段 |
| D2 | 术语一致性 | 状态名、枚举值、字段名、编号格式、版本号、错误代码是否前后一致 | 同一概念在不同位置使用不同名称 |
| D3 | 状态迁移 | 状态机是否覆盖所有迁移路径；失败分支是否有对应处理；超时/异常是否有兜底 | 未定义的迁移路径、死循环 |
| D4 | 公式完整性 | 每个公式的变量定义、取值范围、边界兜底是否完整；是否存在除零或语义歧义 | 公式变量无定义、除零风险 |
| D5 | 错误代码分流 | 每个错误代码是否有明确的分流路径；同一代码是否承载多种语义（过载） | 错误代码语义过载导致分流歧义 |
| D6 | 实施例一致性 | 实施例中的步骤顺序、状态值、术语是否与正文对应；时序描述是否矛盾 | 实施例与正文描述直接冲突 |
| D7 | 图文一致性 | 附图中的节点文本、连线方向、步骤编号是否与正文一致（需 .drawio 或 .xml 附图文件，由 drawioctl inspect --json 取证） |
附图与正文描述不一致 |
What ships with it
7 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.
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 · 177 lines · 64 tokens per session scan A adcc0c13e459
patent-review is a skill published in the GitHub repository seed-forge/harness-ai-kit (22 stars, last pushed 11d ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,542 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
meta-ad-policy-checker
Pre-flight policy check for Meta ads. Takes ad copy plus advertiser context, resolves and fetches the relevant Meta transparency-center policy pages at runtime, and returns a Pass / Fix Required / Block verdict with cited findings and rewrites.
who-really-owns-it
Research companies, directors, shareholders and ultimate beneficial ownership in official corporate registries, filings and offshore datasets — OpenCorporates, UK Companies House and the PSC register, SEC EDGAR, US Secretary of State registries, EU business registers, GLEIF LEI records, OpenOwnership, OpenSanctions…
x-ray-a-company
Corporate due-diligence workflow — resolve a brand or website to its registered legal entity, map group structure and beneficial ownership, profile officers and directors, enumerate the digital estate, and screen litigation, insolvency, procurement, sanctions, PEP and adverse media. Use when asked to check out, vet or…
comprehensive-enrichment
Enrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…