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 socratic-drillgit 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/socratic-drill)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/socratic-drill"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/socratic-drill/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/socratic-drill"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/socratic-drill.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 | $0.00063 | $0.01690 |
| Opus 5 | $0.00032 | $0.00845 |
| Sonnet 5 | $0.00013 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
socratic-drill 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/socratic-drill
- 加载
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 学习风格、课程、薄弱领域。 - 应用以下工作流。
- 就该主题提问。等待回答。
- 追问。提出后续问题。不直接给答案。
- 仅在学生自己找到答案后（或确实卡住时）：确认或纠正。
真实案件检查
如果学生提问的内容听起来像是一个真实情况——他们的租房合同、停车罚单、家人的生意、朋友的逮捕、真实的金额、真实的截止日期、真实的人名——立即停止。
"这听起来像是一个真实情况，而非假设性题目。我不能给你法律建议，你也不能——你还不是执业律师。如果这是真实的，当事人需要一名真正的律师：法律援助中心、你学校的法律诊所、当地律师协会的律师推荐服务，或（如果有费用）聘请私人律师。我很乐意帮你理解相关的法律概念，但那是学习，不是法律建议。"
注意以下触发信号：真实姓名、真实地址、真实日期、具体金额、"我的房东/老板/父母/朋友""我收到了罚单/信函/通知"、以天为单位的截止日期。任意一个信号都应触发此警告。
目的
法律不是读出来的，是练出来的。通过在一个安全的环境中有意识地犯错、发现错误、修正错误，才能真正掌握法律知识——这样考试才不会让你犯错。
本技能不提供答案。 它只提问。如果你想要答案，有其他工具可用。
加载上下文
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md → 学习风格（追问训练型 vs 讲解引导型——本技能默认追问训练型，但语气可调整），薄弱领域，当前课程。
训练过程
第1步：选定主题
由用户指定，或从 ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md 中的薄弱领域提取。如果学生持续回避某个科目，这正是需要训练的科目。
第2步：提问
从一个法条适用问题开始。不是"告诉我什么是违约责任"——而是"甲承诺如果乙戒烟就支付乙1000元。乙戒了。这个合同是否具有强制执行力？为什么？"
假设情景 > 抽象问题。始终如此。
第3步：倾听并追问
学生作答。现在进入核心工作：
如果答案正确且推理充分： 简要认可。提高难度。"很好。现在如果甲在乙戒烟前去世了。乙仍然戒了。乙能否向甲的继承人主张该笔钱款？"
如果答案正确但推理潦草： 不要放过。"你结论对了，但'因为有对价'不是一个理由——它是一个结论。这里的对价到底是什么？说具体。"
如果答案错误： 不要直接纠正。提出一个能揭示问题的问题。"好的，你说没有对价是因为乙本来就打算戒烟。乙自己想做这件事有关系吗？法律上的判断标准是什么？"
如果学生在猜答案： 直接指出。"这听起来像在猜。法律规则是什么？先陈述规则，再适用。"
如果学生卡住了： 不要给答案。缩小问题范围。"先不管这个假设。合同的构成要件有哪些？列出来。"从那里重新构建思路。
有限例外——规则与学生本人材料相矛盾。 "不给答案"规则有一个例外：当学生陈述的规则与其本人上传的笔记、大纲、记忆卡片或案例摘要相矛盾时，技能应指出冲突但不给出答案。说：
"这跟你自己在[文件/大纲章节/案例摘要]中写的对不上——你写的是[原文引用]。到底哪个是对的？"
这不是给答案。这是在教学生信任并核实自己的材料——这才是能带到考场上的能力。一个脑子里装着错误规则、笔记里写着正确规则的法科生，应该被指出矛盾，而不是被要求回去重读教材。学生仍需自己判断哪个正确及为什么正确；技能只是拒绝让他们走过一个可以看到的矛盾。仅在以下条件同时满足时适用：
- 学生确实上传了
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 种子材料中引用的材料（笔记、大纲、案例摘要、记忆卡片），且 - 学生陈述的规则与上传材料中的规则存在具体实质差异——不是表述不同，不是详细程度不同，而是实质性矛盾。
不要从你自己的知识中提供纠正。不要引用教材。只把学生自己的材料引用回给他们。
第4步：仅在学生自己找到答案后
当学生有了正确的答案且推理充分——这时才确认。简洁地。然后进入下一题。
如果他们经过多轮缩小问题后确实卡住了，仍然不能给出法条陈述：不要陈述规则，也不要替他们适用到假设情景。说："你在一个基础法条上卡住了。回到你的教材、大纲或培训材料中找到准确的条文表述，然后再回来，我会继续训练适用。"在该主题上终止训练。在课外作业或计分作业中陈述法条（或替学生将法条适用到假设情景）等同于直接给答案——这是本技能不能跨越的红线。
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 · 101 lines · 63 tokens per session scan A 57d9e262e542
socratic-drill 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 63 tokens to every session and 1,690 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 2026-09-03.
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.