best-skills is a collection of reusable skills for coding agents, including tools for writing papers, creating diagrams and presentations, generating code documentation, and other tasks. Users install its skills into agents such as Cursor, Claude Code, Codex, or OpenClaw so those agents can recognize relevant requests and run the corresponding workflows. The catalogue entries are examples of the skills included in the collection.
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 xstongxue/best-skills --skill patent-writegit clone --depth 1 https://github.com/xstongxue/best-skillsWrote 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/xstongxue/best-skills/patent-write)<a href="https://agentmods.dev/skills/xstongxue/best-skills/patent-write"><img src="https://agentmods.dev/badge/skills/xstongxue/best-skills/patent-write/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/xstongxue/best-skills/patent-write"><img src="https://agentmods.dev/badge/skills/xstongxue/best-skills/patent-write.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 | $0.00095 | $0.01077 |
| Opus 5 | $0.00048 | $0.00539 |
| Sonnet 5 | $0.00019 | $0.00215 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
patent-write 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 11d 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.
What it actually says
中文发明专利撰写
使用时机
- 用户要写中文发明专利
- 用户要补写某一章节，如摘要、权利要求、具体实施方式
- 用户给了参考专利，希望蒸馏写法、结构和表达套路
- 用户要对现有专利草稿做统稿、收敛或术语一致性检查
Step 1：识别任务类型
| 用户表述 / 关键词 | 执行文件 |
|---|---|
| 完整专利、全文、完整说明书、帮我写整个专利 | reference/full-patent.md |
| 题目、名称、题目优化、题目收敛 | reference/title.md |
| 摘要 | reference/abstract.md |
| 背景技术、现有技术缺陷 | reference/background.md |
| 发明内容、技术方案、有益效果 | reference/invention-content.md |
| 权利要求、独立权利要求、从属权利要求 | reference/claims.md |
| 附图说明、图号 | reference/figures-desc.md |
| 附图绘制（Draw.io 黑白中文） | reference/figures-drawio.md |
| 具体实施方式、实施例 | reference/implementation.md |
| 统稿、检查、术语一致性、自检 | reference/review.md |
| 参考专利蒸馏、仿写套路、结构提炼 | reference/distill.md |
Step 2：收集输入
优先收集以下材料，缺什么补什么：
- 技术方案说明：解决什么问题，核心手段是什么
- 现有草稿：已有题目、摘要、权利要求、说明书任一部分
- 参考专利：供蒸馏结构、语言和颗粒度，不直接照抄
- 附图或流程图：模块图、流程图、架构图、时序图
- 创新点：相对现有技术的具体区别与效果
若用户要写全文，默认按以下顺序推进：
- 先提炼创新点与保护对象
- 先搭权利要求骨架
- 再写摘要、发明内容
- 再展开具体实施方式
- 最后做统稿和一致性检查
Step 3：执行并输出
- 读取对应 reference 的写法规则、结构模板和禁忌
- 严格围绕用户提供材料写，不补不存在的实验数据、实施结果或硬件参数
- 同一轮输出尽量给成品，不只给原则
- 若信息不足以支撑正式专利文本，先列缺失项，再给可落地草稿
通用原则
- 不编造：材料里没有的模块、步骤、实验数据、性能指标不要写
- 结构先行：先定保护骨架，再写展开文本
- 术语统一：同一对象全篇只用一种主称呼
- 技术对应：背景缺陷、发明目的、技术方案、有益效果要一一对应
- 少写空话：避免只有功能结果、没有实现路径
- 先宽后窄：独立权利要求概括核心方案，从属权利要求再细化步骤、条件、模块和公式
从参考专利蒸馏出的高频规律
- 题目优先落在“方法、系统、设备及介质”这一类常见命名结构
- 摘要写“公开内容 + 核心步骤 + 技术效果”，不照搬权利要求长串句式
- 背景技术要写到现有方法的具体缺陷，不能只写行业趋势
- 发明内容先写目的，再写技术方案，再写有益效果
- 权利要求 1 负责总流程或核心模块；从属权利要求负责细化子步骤、参数、约束、依赖关系
- 具体实施方式要和附图、步骤编号、模块名称闭环
What ships with it
11 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.
- reference/abstract.md 1.9 KB
- reference/background.md 4.6 KB
- reference/claims.md 4.1 KB
- reference/distill.md 1.2 KB
- reference/figures-desc.md 1.2 KB
- reference/figures-drawio.md 7.0 KB
- reference/full-patent.md 1.8 KB
- reference/implementation.md 4.0 KB
- reference/invention-content.md 6.8 KB
- reference/review.md 1.4 KB
- reference/title.md 1.3 KB
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.
- 11d ago First seen · 71 lines · 95 tokens per session scan A 24a8fae5c9e4
patent-write is a skill published in the GitHub repository xstongxue/best-skills (2,811 stars, last pushed 16d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,077 once invoked, about $0.0005 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
play-policy-insights
Automated auditor designed to verify Android applications against Google Play Policy domains. It cross-references static code analysis with Play Store declarations to generate deterministic compliance reports, identifying undeclared data collection, architectural risks, and missing disclosures across Permissions and…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gh-pr-review
Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…
prepare-release
Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run /prepare-release.
claude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what…
gh-create-issue
Use when user wants to create a GitHub issue for the current repository. Must read and follow the repository's issue template format.