exam-ready

作者: github

当学生提供学习材料(PDF或粘贴的笔记)和教学大纲,并希望准备考试时,激活此技能。

npx skills add https://github.com/github/awesome-copilot --skill exam-ready

exam-ready

Activate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an exam.

What this skill does

For each syllabus topic, extract from the provided material:

  • What it is (1 line definition — exam-ready)
  • 3–5 key points an examiner expects
  • Important keywords to use in the answer (bold them)
  • Any important diagram or figure — describe what it shows in 2 lines
  • 1–2 sentences the student can directly write in their exam answer (or MCQ trick if exam type is MCQ)
  • 1 examiner-style practice question to test recall

Do NOT explain the full topic. Do NOT add context outside the provided material. Do NOT explain things the syllabus didn't ask for. Never tell the student to "read more" or "refer to chapter X". Give them what they need right here.

Input format

Student will provide:

  1. A PDF file or pasted notes (their study material)
  2. A syllabus — either pasted as text or listed as topics
  3. Optionally: exam type (MCQ / short-answer / long-answer) and time available

Handling missing inputs

  • If no study material is provided: say "Please share your notes or PDF first. I won't use outside knowledge."
  • If no syllabus is provided: say "Please list your syllabus topics so I cover exactly what's being tested."
  • If exam type is not mentioned: default to long-answer format, but ask once: "Is this MCQ or written?"
  • If a topic is not found in the provided material: say "This topic was not found in your notes. Check your material."

Triage mode (when student gives a time constraint)

If the student says "I have X hours":

  1. First, output a priority list — number all syllabus topics in order of:
    • Explicit weightage (if syllabus mentions marks)
    • Frequency of appearance in the PDF (more coverage = higher priority)
    • Breadth of subtopics under it
  2. Then expand each topic in that priority order, not syllabus order.
  3. If time is very short (≤1 hour), cut output to definition + key points + exam line only. Skip diagrams.

Output format per topic


[Topic Name]

Definition: [1 sentence]

Key Points:

  • [point 1]
  • [point 2]
  • [point 3]

Keywords to use: keyword1, keyword2, keyword3

Diagram (if any): [What the diagram shows and what to label]

Write this in your exam: (skip if MCQ — show MCQ trick instead) [1–2 ready-to-write sentences the student can use directly]

MCQ trick: (only if exam type is MCQ) [How to identify the correct option or eliminate wrong ones for this topic]

Cross-references: (only if this topic's keywords appeared in another topic) [e.g., "The term 'X' used here also appears in [Topic Y] — examiners may link them"]

Practice question: [1 examiner-style question to test recall on this topic]


Rules

  • Stay strictly within the provided material. Do not add outside knowledge under any circumstance.
  • If exam type is MCQ, replace "Write this in your exam" with "MCQ trick".
  • If no weightage is given in the syllabus, prioritize topics that appear most in the PDF.
  • If a keyword from one topic reappears in another, flag it under "Cross-references".
  • If the PDF contradicts the syllabus topic name or scope, use the PDF content but note: "Your notes cover this as [X] — answering based on that."
  • Keep everything short. The student is cramming, not researching.

Trigger phrases

  • "I have an exam tomorrow on [subject]"
  • "explain [topic] from my notes"
  • "what do I need to know about [topic] for my exam"
  • "go through my syllabus"
  • "I only have [X] hours, help me prepare"
  • "quiz me on [topic]"

来自 github 的更多技能

console-rendering
github
在Go中使用基于结构体标签的控制台渲染系统的说明
official
acquire-codebase-knowledge
github
当用户明确要求映射、记录或熟悉现有代码库时使用此技能。触发词如“映射此代码库”、“记录…
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
通过AgentRC指令命令生成定制化的AI代理指令文件。生成.github/copilot-instructions.md(默认,推荐用于VS Code中的Copilot…
official
acreadiness-policy
github
帮助用户选择、编写或应用AgentRC策略。策略通过禁用无关检查、覆盖影响/级别、设置…来定制就绪评分。
official
add-educational-comments
github
为代码文件添加教育性注释,将其转化为有效的学习资源。根据三个可配置的知识水平(初级、中级、高级)调整解释深度和语气。若未提供文件,自动请求文件,并附带编号列表以便快速选择。仅通过教育性注释将文件扩展最多125%(硬性限制:新增400行;超过1000行的文件限制为300行)。保留文件编码、缩进风格、语法正确性以及...
official
adobe-illustrator-scripting
github
使用ExtendScript(JavaScript/JSX)编写、调试和优化Adobe Illustrator自动化脚本。在创建或修改操作…的脚本时使用。
official
agent-governance
github
声明式策略、意图分类及审计追踪,用于控制AI代理工具访问与行为。可组合的治理策略定义允许/禁止的工具、内容过滤器、速率限制及审批要求——以配置而非代码形式存储。语义意图分类在执行工具前通过基于模式的信号检测危险提示(数据泄露、权限提升、提示注入)。工具级治理装饰器在函数层面强制执行策略...
official