Back to Details

exam-forecast

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/exam-forecast

/exam-forecast

  1. Load 
    ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md
    → class, professor, exam format, syllabus.
  2. Apply the workflow below.
  3. Intake past exams (PDF, paste, or paths). Confirm sample size.
  4. Analyze each past exam: format, subject coverage, question style, fact-pattern density, recurring traps.
  5. Cross-exam pattern analysis — what's stable, what varies.
  6. Combine with current syllabus to produce forecast: subject weights, format, hobby horses, study emphasis.
  7. Write 
    ~/.claude/plugins/config/claude-for-legal/law-student/exam-forecasts/[class]/forecast-[YYYY-MM-DD].md
    . Framed as weighting heuristic, not prediction.
  1. 加载 
    ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md
    → 获取课程、教授、考试形式、教学大纲信息。
  2. 应用以下工作流程。
  3. 接收过往考试资料（PDF、粘贴文本或文件路径），确认样本数量。
  4. 分析每份过往考试：形式、科目覆盖范围、题型、事实模式密度、反复出现的陷阱。
  5. 跨考试模式分析——找出稳定规律与变化点。
  6. 结合当前教学大纲生成预测：科目权重、考试形式、教授偏好考点、学习重点。
  7. 将预测结果写入 
    ~/.claude/plugins/config/claude-for-legal/law-student/exam-forecasts/[class]/forecast-[YYYY-MM-DD].md
    ，需将其表述为权重参考而非确定预测。

Purpose

目的

Every professor's exam has fingerprints. The same hypo structures recur. The same traps come back. The same subject ratios repeat. Students who have prior exams study smarter; students who don't, study harder. This skill analyzes the prior exams you have and surfaces the patterns.
Not magic. A forecast, not a prediction. The skill cannot tell you what's on the exam — it can tell you what's been on past exams and what's likely to recur based on syllabus coverage.
每位教授的考试都有其独特的「印记」：相同的hypo结构会重复出现，相同的陷阱会反复设置，相同的科目占比会保持稳定。拥有过往考试资料的学生能更高效地学习；没有的学生则需要花费更多精力。本功能会分析你提供的过往考试资料，挖掘其中的规律。
这并非魔法，只是基于规律的预测而非确定结果。本功能无法告诉你考试具体内容——但它能告诉你过往考试的考点，以及基于教学大纲覆盖范围，哪些内容可能再次出现。

Confidence discipline

置信度规范

  • Pattern analysis (what subjects appeared, how many questions per topic, how often policy vs. rule-application) — confident where the exams are clearly in front of me.
  • Inference about likely emphasis on upcoming exam — 
    [UNCERTAIN]
    is the default; these are forecasts, not certainties. Explicitly frame as "based on the [N] past exams you shared, [topic] appeared in [M]. Your upcoming exam may emphasize it, or the professor may rotate — use this as a weighting for review time, not a prediction."
  • If only 1-2 past exams are available, say so explicitly — any pattern inferred from 1 exam is noise.
  • If the professor is new (no past exams available), skill can't forecast. Say so; fall back to syllabus-based "these are the subjects covered" only.
  • 模式分析（哪些科目出现过、每个主题的题量、政策类与规则应用类题型的出现频率）——当有明确的考试资料时，分析结果可信度较高。
  • 对即将到来的考试重点的推断——默认标注 
    [UNCERTAIN]
    ；这些是预测，并非确定事实。需明确表述为：「基于你分享的[N]份过往考试资料，[主题]出现过[M]次。你即将参加的考试可能会侧重该主题，但教授也可能调整考点——请将此作为复习时间分配的参考，而非确定预测。」
  • 若仅提供1-2份过往考试资料，需明确说明——从1份考试资料中推断的模式可能只是偶然现象。
  • 若教授是新任教（无过往考试资料），本功能无法进行预测。需告知用户；仅能退而求其次，基于教学大纲提供「以下是本学期覆盖的科目」的信息。

Load context

加载上下文

  • ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md
    → current classes, exam formats, syllabus if captured
  • User-provided past exams (PDF, pasted text, paths)
  • Optional: syllabus for the current class (for "what's been covered to date")
If the uploaded past exams have a professor's name, use it to match patterns (same-professor exams are the highest-signal input). If not, match on subject and structure. Don't ask the user to type in the professor's name — use what's in the materials. If the user volunteers it in conversation that's fine; don't prompt for it.
  • ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md
    → 当前课程、考试形式、已记录的教学大纲
  • 用户提供的过往考试资料（PDF、粘贴文本、文件路径）
  • 可选：当前课程的教学大纲（用于确认「至今已覆盖的内容」）
若上传的过往考试资料中有教授姓名，用其匹配规律（同一位教授的考试资料是最具参考价值的输入）。若无教授姓名，则按科目和考试结构匹配。不要要求用户输入教授姓名——使用资料中已有的信息即可。若用户在对话中主动提供教授姓名，可使用该信息；但不要主动询问。

Workflow

工作流程

Step 1: Intake

步骤1：接收信息

  • Which class are we forecasting for?
  • How many past exams from this professor are available?
  • Are they from the same course, or different courses by the same professor?
  • Are any of them the take-home / open-book / different-format variants, vs. the typical format for your upcoming exam?
  • Syllabus for your current class?
If fewer than 3 past exams: flag as thin sample. Pattern inference is weaker. If exams are across different courses: some patterns transfer (question style, policy vs. doctrine ratio); subject-specific patterns don't.
  • 我们要预测哪门课程的考试？
  • 有多少份该教授的过往考试资料可用？
  • 这些资料是来自同一门课程，还是该教授的其他课程？
  • 其中是否有开卷/带回家完成/其他特殊形式的考试，与你即将参加的常规考试形式不同？
  • 是否有当前课程的教学大纲？
若过往考试资料少于3份：标注为样本量不足。模式推断的可信度较低。 若考试资料来自不同课程：部分规律可迁移（题型、政策类与学说类题型的占比）；但科目特定规律无法迁移。

Step 2: Read each past exam

步骤2：分析每份过往考试

For each past exam:
  • Format (number of questions, length, time limit, open/closed book)
  • Subject coverage (which topics tested, in what proportion)
  • Question style (issue-spotter, single-issue deep, policy essay, short-answer MBE-style, mix)
  • Fact pattern density (fact-heavy hypos, sparse facts with doctrinal focus, or policy prompts with no facts)
  • Recurring traps (e.g., professor always hides the jurisdictional issue in an otherwise-clean fact pattern; professor always asks about the exception rather than the rule)
  • Policy vs. doctrine ratio
  • Unusual structures (essays + MBE hybrid, moot court scenario, etc.)
针对每份过往考试：
  • 形式（题量、时长、时间限制、开卷/闭卷）
  • 科目覆盖范围（测试哪些主题，各主题占比）
  • 题型（考点识别题、单一主题深度题、政策论述题、MBE风格简答题、混合题型）
  • 事实模式密度（事实密集型hypo、侧重学说的稀疏事实题、无事实的政策题）
  • 反复出现的陷阱（例如：教授总是在看似清晰的事实模式中隐藏管辖权问题；教授总是考查规则的例外而非规则本身）
  • 政策类与学说类题型的占比
  • 特殊结构（论述题+MBE混合题型、模拟法庭场景等）

Step 3: Cross-exam pattern analysis

步骤3：跨考试模式分析

Roll up what's consistent across exams:
Stable patterns (appeared in most/all past exams):
  • Subject weights (e.g., "consideration and modification account for 30% of exam points consistently")
  • Question style (e.g., "always one long issue-spotter + two short-answer hypos")
  • Professor hobby horses (e.g., "always tests third-party beneficiaries even when it's a minor topic in class")
Variable patterns (appeared in some but not all):
  • Policy essays (e.g., "appeared in 2 of 4 past exams — usually when the semester covered a policy-heavy topic late")
  • Open-book vs. closed-book differences
  • Take-home vs. in-class differences
Absent patterns worth noting:
  • Topics covered in class that have NEVER been tested in past exams — don't skip these, but don't weight them heavily either
  • Topics tested in past exams that aren't in your current syllabus — probably not coming back
汇总所有考试中的一致规律：
稳定规律（在大多数/所有过往考试中出现）：
  • 科目权重（例如：「对价与修改题型始终占考试分值的30%」）
  • 题型（例如：「总是包含1道长篇考点识别题 + 2道简短hypo简答题」）
  • 教授偏好考点（例如：「即使第三方受益人是课堂上的次要主题，教授也总会对其进行测试」）
可变规律（在部分但非全部考试中出现）：
  • 政策论述题（例如：「在4份过往考试资料中出现过2次——通常当学期后期覆盖政策密集型主题时会出现」）
  • 开卷与闭卷的差异
  • 带回家完成与课堂考试的差异
值得注意的缺失规律：
  • 课堂上覆盖但从未在过往考试中测试过的主题——不要完全跳过，但也不要过度侧重
  • 过往考试中测试过但未出现在当前教学大纲中的主题——很可能不会再次出现

Step 4: Forecast for the upcoming exam

步骤4：生成即将到来的考试预测

Header — required, first line of the forecast, both in-chat and in the saved file. Per plugin config 
## Outputs
, every study output carries the verbatim study-notes header. The forecast is a study output. Do not omit, rephrase, or relocate the header. The header is not a disclaimer the student can ask to drop; it is the output's identity and prevents the forecast from being mistaken for a predicted exam or for legal advice:
STUDY NOTES — NOT LEGAL ADVICE
Combine pattern analysis with current syllabus:
markdown
STUDY NOTES — NOT LEGAL ADVICE
标题——必填，为预测内容的第一行，无论是聊天输出还是保存的文件。 根据插件配置 
## Outputs
，所有学习输出都需包含完整的学习笔记标题。本预测属于学习输出。请勿省略、改写或移动标题。该标题并非学生可以要求移除的免责声明；它是输出内容的标识，可避免预测被误认为是确定的考试内容或法律建议：
STUDY NOTES — NOT LEGAL ADVICE
结合模式分析与当前教学大纲：
markdown
STUDY NOTES — NOT LEGAL ADVICE

Exam Forecast — [class / professor] — [date]

考试预测 — [课程/教授] — [日期]

Past exams analyzed: [N] Sample confidence: [thin (<3) / moderate (3-5) / strong (6+)] Caveats: [e.g., "one of the past exams was an open-book final; your upcoming is closed-book. Pattern transfer is partial."]
已分析的过往考试数量： [N] 样本置信度： [不足(<3) / 中等(3-5) / 较高(6+)] 注意事项： [例如：「其中一份过往考试是开卷期末考试；你即将参加的是闭卷考试。规律的可迁移性有限。」]

Subject weighting (historical)

科目权重（历史数据）

TopicPast exam weight (avg)In current syllabus?Forecast weight
[topic 1][%][yes/partial/no][heavier / stable / lighter]
主题过往考试平均权重是否在当前教学大纲中？预测权重
[主题1][%][是/部分覆盖/否][加重/稳定/减轻]

Question-style forecast

题型预测

  • Format likely: [X issue-spotters + Y short answers + Z policy, or similar]
  • Fact-pattern density: [fact-heavy / sparse / mixed]
  • Call style: [one broad call / multiple specific calls / bullet sub-parts]
  • 可能的形式： [X道考点识别题 + Y道简答题 + Z道政策题，或类似表述]
  • 事实模式密度： [事实密集型/稀疏/混合]
  • 提问方式： [宽泛提问/多个具体提问/分点提问]

Professor hobby horses to watch

需要关注的教授偏好考点

  • [topic A] — appeared in [M of N] past exams. Weighted 3-5x its syllabus share.
  • [topic B] — [pattern]
  • [trap pattern] — e.g., "hides jurisdictional issue in otherwise-clean facts"
  • [主题A] — 在[N]份过往考试中的[M]份出现过。其权重是教学大纲中占比的3-5倍。
  • [主题B] — [规律描述]
  • [陷阱规律] — 例如：「在看似清晰的事实中隐藏管辖权问题」

Topics covered this semester but rarely tested

本学期覆盖但很少被测试的主题

[list — don't skip, but don't over-weight]
[列表——不要跳过，但不要过度侧重]

Study emphasis recommendation

学习重点建议

Based on past exam patterns AND current syllabus coverage:
Heavy: [topics likely to anchor the exam — 40-50% of study time] Moderate: [supporting topics — 30-40%] Sanity check: [topics covered but historically under-represented — 10-20%, just in case]
基于过往考试规律与当前教学大纲覆盖范围：
重点： [可能成为考试核心的主题——分配40-50%的复习时间] 次重点： [辅助主题——分配30-40%的复习时间] Sanity Check： [本学期覆盖但历史上占比低的主题——分配10-20%的时间，以防万一]

[UNCERTAIN — framing]

[UNCERTAIN — 表述框架]

This forecast is derived from [N] past exams. Professors vary. Professors rotate. Topics that were emphasized in past years can be de-emphasized when the syllabus shifts. Treat this as a weighting heuristic for study time, not a prediction. The exam will include surprises.
undefined
本预测基于[N]份过往考试资料。教授会调整考点，也会轮换主题。往年侧重的主题可能因教学大纲调整而不再被侧重。请将此作为复习时间分配的参考工具，而非确定预测。考试中总会有意外内容。
undefined

Step 5: Output location

步骤5：输出位置

Write to 
~/.claude/plugins/config/claude-for-legal/law-student/exam-forecasts/[class]/forecast-[YYYY-MM-DD].md
. Versioned — if the student gets another past exam mid-semester, re-run and append.
将预测结果写入 
~/.claude/plugins/config/claude-for-legal/law-student/exam-forecasts/[class]/forecast-[YYYY-MM-DD].md
。采用版本化管理——若学生在学期中期获得新的过往考试资料，需重新运行本功能并追加内容。

Integration

集成功能

  • outline-builder: forecast weights feed into outline depth decisions — weight depth on heavy topics
  • flashcards: forecast-heavy topics get more cards generated
  • bar-prep-questions: irrelevant for bar prep (that has its own forecast model); exam-forecast is for class-specific finals
  • irac-practice: use forecast topics as the subject areas for IRAC practice hypos
  • outline-builder（大纲构建工具）： 预测权重会影响大纲的深度决策——重点主题需更深入的大纲内容
  • flashcards（抽认卡工具）： 预测的重点主题会生成更多抽认卡
  • bar-prep-questions（律师资格考试备考题）： 与律师资格考试备考无关（该领域有独立的预测模型）；exam-forecast专为课程期末考设计
  • irac-practice（IRAC练习工具）： 将预测主题作为IRAC练习hypo的主题领域

Close with the next-steps decision tree

以下一步决策树收尾

End with the next-steps decision tree per CLAUDE.md 
## Outputs
. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.
根据CLAUDE.md中的 
## Outputs
，以下一步决策树结束输出。可根据本功能生成的内容自定义选项——五个默认分支（起草X、升级处理、获取更多事实、观望等待、其他）是起点，而非固定选项。决策树是输出内容的一部分，由使用者选择下一步行动。

What this skill does not do

本功能不支持的操作

  • Predict specific questions. Past exams show patterns; they don't show you tomorrow's prompt.
  • Work without past exams. If you don't have prior exams from this professor, the skill can't forecast — it falls back to "here's what the syllabus covers, study that."
  • Replace studying everything on the syllabus. Forecast is weighting, not elimination. Skipping a topic because it's historically under-represented is how students get burned.
  • Account for changes you don't know about. If the professor has shifted focus this year (e.g., emphasized a new case in class lectures), the skill doesn't see that unless you tell it.
  • Work reliably with 1-2 past exams. Thin sample. Flag as such.
  • 预测具体考题：过往考试只能体现规律，无法告诉你未来的考题内容。
  • 无过往考试资料时使用：若没有该教授的过往考试资料，本功能无法进行预测——只能退而求其次，提供「以下是教学大纲覆盖的内容，请重点学习这些」的信息。
  • 替代对教学大纲全部内容的学习：预测是权重分配参考，而非考点排除依据。因为某主题历史上占比低就跳过学习，是学生失分的常见原因。
  • 考虑未知的变化：若教授今年调整了教学重点（例如：在课堂上重点讲解了某个新案例），除非你告知本功能，否则它无法感知到这些变化。
  • 在仅1-2份过往考试资料时可靠运行：样本量不足，需明确标注。