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 exam-forecastgit 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/exam-forecast)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/exam-forecast"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/exam-forecast/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/exam-forecast"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/exam-forecast.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 | $0.00085 | $0.02447 |
| Opus 5 | $0.00043 | $0.01223 |
| Sonnet 5 | $0.00017 | $0.00489 |
| Haiku 4.5 | $0.00009 | $0.00245 |
Grade A, and why
exam-forecast 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/exam-forecast
- 加载
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 课程、授课教师、考试形式、教学大纲。 - 应用以下工作流。
- 接收历年考题（PDF、粘贴文本或文件路径）。确认样本量。
- 分析每份历年考题：格式、科目覆盖、题型风格、案例事实密度、反复出现的陷阱。
- 跨考题模式分析——哪些稳定，哪些变化。
- 结合当前教学大纲生成预测：科目权重、格式、教师偏好、复习重点。
- 写入
~/.claude/plugins/config/claude-for-legal/law-student/exam-forecasts/[课程]/forecast-[YYYY-MM-DD].md。定义为权重启发式，非确定预测。
目的
每位老师的试卷都有指纹。同样的案例假设结构反复出现。同样的陷阱反复回归。同样的科目比例反复再现。有历年考题的学生学得更聪明；没有的学生学得更辛苦。本技能分析你拥有的历年考题并揭示模式。
不是魔法。是预测，不是确定答案。技能不能告诉你考卷上具体有什么——它能告诉你的只是历年考卷上出现过什么，以及基于教学大纲覆盖范围什么可能再次出现。
置信纪律
- 模式分析（哪些科目出现、每个主题多少题、政策题vs法条适用的比例）——当考题清晰地在我面前时有把握。
- 关于今年考试可能重点的推断——
[不确定]是默认状态；这些是预测，非确定。明确表达为"基于你分享的 [N] 份历年考题，[主题] 出现了 [M] 次。你的考试可能重点考查它，也可能老师会轮换考点——将其作为分配复习时间的权重参考，而非确定性预测。" - 如果只有 1-2 份历年考题，明确说明——从 1 份考题推断出的任何模式都是噪音。
- 如果该教师是新教师（无历年考题），技能无法预测。直说；仅退回基于教学大纲的"这些是已覆盖的科目"。
加载上下文
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 当前课程、考试形式、教学大纲（如有）- 用户提供的历年考题（PDF、粘贴文本、路径）
- 可选：当前课程的教学大纲（用于"截至目前已讲授内容"）
如果上传的历年考题有教师姓名，用它来匹配模式（同一教师的考题是最高信号输入）。如果没有，按科目和结构匹配。 不要要求用户输入教师姓名——使用材料中已有的。如果用户在对话中主动提供也没问题；不要提示。
工作流
第1步：接收材料
- 我们要预测哪门课？
- 该教师有多少份历年考题？
- 它们是同一门课的，还是同一教师不同课程的？
- 其中是否有带回/开卷/不同格式的变体，与你本次考试的典型格式不同？
- 你本次课程的教学大纲？
如果不到 3 份历年考题：标记为样本不足。模式推断更弱。 如果考题来自不同课程：部分模式可迁移（题型风格、政策vs法条比例）；科目特定模式不可迁移。
第2步：阅读每份历年考题
对每份历年考题：
- 格式（题目数量、篇幅、时间限制、开/闭卷）
- 科目覆盖（考查了哪些主题，占比多少）
- 题型风格（案例分析、单争议焦点深入、政策论述、选择题型、混合）
- 案例事实密度（事实密集型假设、事实稀疏侧重法条、或无事实的政策提示）
- 反复出现的陷阱（如教师总是在一个看似干净的案例事实中隐藏管辖权问题；教师总是问例外而非规则）
- 政策vs法条比例
- 特殊结构（论选题 + 选择混合、模拟法庭场景等）
第3步：跨考题模式分析
汇总各份考题中一致的内容：
稳定模式（出现在大多数/全部历年考题中）：
- 科目权重（如"对价和变更持续占考试分数的30%"）
- 题型风格（如"总是1个长案例分析 + 2个短假设题"）
- 教师偏好（如"即使课堂上是小主题，总是考第三人利益"）
变动模式（出现在部分而非全部）：
- 政策论述（如"4份考题中出现了2次——通常是学期后半段有政策密集主题时"）
- 开卷 vs 闭卷差异
- 带回 vs 当堂差异
值得注意的缺失模式：
- 课堂讲授但在历年考题中从未出现过的主题——不要跳过这些，但也不加权重
- 历年考题中出现但不在你当前教学大纲中的主题——可能不再回归
第4步：为本次考试做预测
标题——必需，预测的第一行，无论是在聊天中还是保存的文件中。 根据插件配置 ## Outputs，每个学习产出都带有统一的学习笔记标题。预测是学习产出。不要省略、改写或重定位标题。标题不是学生可以要求删除的免责声明；它是产出的身份标识，防止预测被误认为确定的考题或法律建议：
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 · 160 lines · 85 tokens per session scan A ec0024926a9a
exam-forecast 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 85 tokens to every session and 2,447 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.