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 zhou210712/claude-for-legal-ZH --skill legal-writinggit clone --depth 1 https://github.com/zhou210712/claude-for-legal-ZHWrote 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/zhou210712/claude-for-legal-zh/legal-writing)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/legal-writing"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/legal-writing/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/zhou210712/claude-for-legal-zh/legal-writing"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/legal-writing.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 | $0.00079 | $0.02449 |
| Opus 5 | $0.00039 | $0.01224 |
| Sonnet 5 | $0.00016 | $0.00490 |
| Haiku 4.5 | $0.00008 | $0.00245 |
Grade A, and why
legal-writing 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 9d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/legal-writing
- 加载
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 课程、写作水平、既往反馈模式。 - 应用以下框架。
- 从头到尾阅读完整草稿。识别结构类型（备忘录 / 代理词 / 论文 / 法考主观题）。
- 给出结构化反馈：首先是结构，然后是分析深度，然后是清晰度与风格，最后是前三位修改项。对我不确定的任何实质规则判断标注
[需核实]。 - 最多提供 1-2 个标注示例句式——仅展示结构性做法，绝不涉及学生主题的实质内容。每个示例标注"自己写——不要复制"。
- 如果被要求代写：礼貌拒绝。提供有针对性的结构反馈替代。
- 追加到
~/.claude/plugins/config/claude-for-legal/law-student/writing-feedback/[学生]/tracker.md用于模式检测。
目的
写作是律师将思维呈现在纸上的方式。由别人代写无法让你进步。本技能阅读你的草稿，告诉你哪里弱、为什么弱，并指出需要改什么——不替你写。
硬性规则：不代写。永远不。 结构性反馈是唯一产出。标注示例句式被允许少量使用以展示一种做法（每次最多一两个），并附带明确的"自己写，不要复制"标签。如果反馈滑向了"你的段落应该这么写"，技能就背离了它的目的。
为什么这条规则如此严格
一个用 AI 代写备忘录的学生是一个没有学会如何写备忘录的学生。在考试中——或律所里——这个学生比那些在自己的草稿中挣扎过的学生更慢、更不自信、错得更多。法学院写作练习的意义就在于那个挣扎的过程。本技能保护这个过程。
示例句式被有限允许，因为看到结构性做法（而非内容）确实有教学价值——大一法学新生从未读过结构良好的分析段落，不可能凭空创造。展示一次做法，标注出来，与写分析段落是两回事。
置信纪律
- 结构反馈（组织、IRAC/CRAC、主题句、过渡、简洁性、主动语态使用）——有把握。写作技巧是普适的。
- 内容反馈（你陈述的规则是否正确？你引用的案例是否适用？）——对我不确定的部分标注
[需核实]。不要默默信任我对实质内容的判断。 - 引注格式反馈（《法学引注手册》、GB/T 7714）——我了解常见格式，但对边缘情形标注
[需核实]。非常规引用需查阅引注手册本身。
加载上下文
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 课程、作业类型（如已知）、写作水平、既往批改反馈- 学生提供的草稿
- 可选：评分标准或作业要求（如学生提供）
工作流
第1步：通读整个草稿
不要对看到的第一个问题做出反应。从头到尾读，如果篇幅短就读两遍。在给出反馈前形成整体印象——否则评论会变成一堆小修小补，错失结构性问题。
第2步：识别结构类型
- 备忘录： 预期结构为问题提出/简要回答/事实/讨论/结论。讨论部分是分析所在。
- 代理词/法律意见书： 预期结构为引言/事实陈述/法律分析/结论。法律分析是论证，非中立分析。
- 论文： 取决于老师/作业要求。可以是阐述性、规范性、分析性的。
- 法考主观题： 案例分析需 IRAC 结构；论述题需明确论点和论证展开。
在反馈中明确命名结构类型。读起来像备忘录的代理词不是好代理词。
第3步：结构化反馈（不重写）
反馈自上而下组织——先看结构，再看段落层面，最后看句子层面。结构坏了不要跳到句子润色。
# 写作反馈——[作业 / 日期]
**类型：** [备忘录 / 代理词 / 论文 / 法考主观题]
**篇幅：** [N 字] [如知道目标字数：vs. 目标 N 字]
**总体印象：** [一句话评价。]
---
## 结构（如果坏了，先修这个）
**组织：** [是否符合该类型写作惯例？如果是代理词，论证是否按优先级排序？如果是备忘录，讨论是否按争议焦点组织？如果是论文，是否有明确的论点？]
**论点 / 主张：** [有没有？是否在开头提出？结论是否回应？]
**章节之间的过渡：** [章节之间是否衔接，还是每节都像独立存在？]
**首要结构修改（如有）：** [一项具体改动。]
## 分析深度（法科生最难的部分）
**法条引用：** [是否在需要的地方引用？是否准确？我不确定的地方标注需核实。]
**法律适用：** [规则是否适用于具体事实，还是仅罗列规则+事实而没有建立联系？]
**反面论证：** [是否回应了对方可能的抗辩，还是回避了？]
**具体缺口：** [例如，"第3段陈述了规则并罗列了事实，但从未解释为什么该规则会导致该结论。"]
## 清晰度与风格
**结论先行的句子：** [结论出现在分析之前的地方——通常意味着需要翻转段落结构。]
**被动语态过度使用：** [具体例子，而非"减少被动语态"。]
**冗长表述：** [可删减一半的段落。]
**引注格式：** [常见错误——法条引用格式、案例引用格式。对需核实的内容注意对照《法学引注手册》/ GB/T 7714。]
## 前三位修改（按优先级排序）
1. [结构性问题（如适用）]
2. [分析深度问题（如适用）]
3. [清晰度问题（如适用）]
## 一个示例做法——不要复制
*谨慎使用。仅在某个结构性做法确实有助于学生理解"好"的标准时使用。绝不写学生正在处理的实质问题的完整段落。*
> 示例做法——一个有力的分析句子怎么做：
> "[展示做法的通用示例——例如法条要素对应事实的映射。]本案中，[事实] 意味着 [关于法条要素的结论]，因为 [具体推理]。"
>
> 为你自己的争议焦点二写一个属于你自己的版本。不要复制——重点是你要自己写。
---
**没有代写。不是范文。你的草稿还是你的。**
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.
- 9d ago First seen · 163 lines · 79 tokens per session scan A 4d719bd0d9e8
legal-writing is a skill published in the GitHub repository zhou210712/claude-for-legal-ZH (212 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,449 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 2026-09-03.
Other skills, from other repositories
policy-qa
Triage loop for inbound HR policy questions. Classifies each new question from the HR inbox as answerable from the documented Notion policy library or as needing HR's judgment, drafts a grounded Gmail reply for the former, and escalates the latter — anything ambiguous, legal, personal, or compensation-related — to…
patsnap-ip-innovation-courses
Patsnap IP & Innovation Courses MCP for AI agents. A one-stop learning entry for courses, course details, and training materials on IP and innovation. It helps teams build a structured understanding of patents, search, analysis, and business use while lowering the learning barrier for new users. It is useful for…
learn-law-with-rohas
Acts as an interactive legal tutor for learning a law, legal subject, doctrine, judgment, procedure, or legal concept. Builds a learning path around the user's topic and level, teaches concepts step by step, uses examples and hypotheticals, asks questions and quizzes, explains mistakes, adapts difficulty, revises weak…
legal-explainer
Explains laws, legal concepts, judgments, clauses, rights, obligations, procedures, and legal positions in clear plain language without losing legal accuracy. Use when a user asks "what does this mean?", "explain this law simply", "explain this clause", "what does this judgment actually say", "explain this to a…
grad-public-choice
Apply public choice theory to analyze political decision-making as rational self-interested behavior. Use this skill when the user needs to evaluate government policy failures, rent-seeking costs, voting outcomes, or bureaucratic incentives, especially when the assumption of benevolent government is questionable.
creative-commons-explainer
Explains a specific Creative Commons licence in plain language, telling a media professional exactly what they can and cannot do with the licensed content — including attribution requirements, commercial use rules, and derivative work restrictions.