College Exam Sprint

v1.0.0

面向大学课程期末复习的 OpenClaw 助学 skill,支持首次建档、20 天总计划、每日任务、当日小测、进度反馈与动态调整;适配计算机网络、数据结构、高等数学等课程。

0· 62·0 current·0 all-time
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill's name and description (20‑day university exam sprint planner/coach) match the provided instructions and document modules. It does not request unrelated credentials, binaries, or external services. One minor note: the skill expects a dedicated workspace under ~/study_university_sprint/ for storing data, which is consistent with its purpose but was not declared as a required config path in the registry metadata.
Instruction Scope
All runtime instructions are focused on collecting exam/course info, generating plans, running daily flows, producing small tests, and updating progress. The SKILL.md and module docs explicitly instruct the agent to read and write files in the user's recommended workspace (e.g., reading the progress panel and previous day records, writing daily records). This file I/O is consistent with the skill’s purpose but grants the agent access to files under the user’s home — users should be aware of which files they place there.
Install Mechanism
No install spec and no code files beyond markdown docs. Being instruction-only means nothing is downloaded or written to disk by an install step, which is the lowest‑risk install posture.
Credentials
The skill declares no required environment variables, no primary credentials, and no config paths in the registry. The behavior described (local file read/write of study materials) does not require secrets or external credentials, so the lack of requested credentials is proportional. (Reminder: the skill will access files under the recommended workspace if present.)
Persistence & Privilege
always is false and the skill allows normal autonomous invocation (disable-model-invocation false), which is the platform default and appropriate for an assistant that can be asked to start daily flows. The skill does not request to modify other skills or system settings.
Assessment
This skill is coherent and appears to do what it says: plan and coach a 20‑day exam sprint. Key things to consider before installing: - The skill’s runtime instructions expect to read and write files in a recommended workspace (~/study_university_sprint/). Only put study materials (notes, slides, exercises) there — do not place sensitive files or credentials in that folder. - There are no external installs or credentials requested, which reduces risk. Still confirm where your agent runs (local vs. hosted) because filesystem access differs by environment. - The skill includes clear academic‑honesty constraints (it refuses to do assignments or fabricate records); if you need stronger guarantees, test a few refusal scenarios (e.g., ask it to produce a finished assignment) to confirm behavior. - If you prefer tighter containment, create a sandbox directory with only the materials you want the skill to access and point the skill to use that folder rather than your entire home directory.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

📘 Clawdis
OSLinux · macOS · Windows
latestvk9762gcm5n6kp4zyjjqcfkz7k184bm3k
62downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0
Linux, macOS, Windows

这个 skill 是做什么的

这是一个面向大学课程期末冲刺场景的助学 skill。它的目标不是一次性回答某道题,而是围绕一次明确的考试周期,把考试信息、课程资料、复习计划、每日任务、当日测试和进度调整组织成一个连续项目。

它适用于常见高校课程的期末复习场景,例如《计算机网络》《数据结构》《操作系统》《高等数学》等。系统应先识别课程类型、考试要求、资料结构和用户当前薄弱点,再按统一流程生成计划、讲解、测试与调整。文档中的《计算机网络》只作为展示性示例,不限制本 skill 的实际适用范围。

什么时候使用

当用户需要完成以下任务时使用本 skill:

  1. 首次录入课程名称、考试时间、题型、教材、课件、笔记和每天可用时间;
  2. 生成 20 天总计划和第 1 天任务;
  3. 在后续每天通过“开始今天任务”进入当日学习流程;
  4. 在学习过程中请求讲解、例题、提示、总结或错因分析;
  5. 生成“今天的小测”或“阶段模拟题”;
  6. 提交完成情况,让系统更新进度并对未来几天做局部调整。

推荐工作区结构

所有数据建议存放在 ~/study_university_sprint/

~/study_university_sprint/
├── 01_考试信息/
│   ├── 考试安排.md
│   ├── 课程清单.md
│   ├── 每日复习时间.md
│   └── 目标分数.md
├── 02_输入材料/
│   ├── 教材/
│   ├── 课件PPT/
│   ├── 课堂笔记/
│   ├── 教师重点/
│   └── 参考习题与往年题/
├── 03_进度记录/
│   ├── 第01天记录.md
│   ├── ...
│   └── 每周总结.md
├── 04_中间结果/
│   ├── 总体计划/
│   ├── 每日任务/
│   ├── 知识点总结/
│   ├── 习题与小测/
│   └── 反馈报告/
├── 05_最终输出/
│   ├── 最终20天计划.md
│   ├── 最终重点清单.md
│   ├── 易错点总结.md
│   ├── 模拟测试题.md
│   └── 考前3天速记版.md
└── 06_归档区/
    └── 备份笔记/

模块调用逻辑

1. 首次建档

当用户第一次输入课程、考试时间、资料、每天可用时间和当前掌握情况时,先调用 setup_profile.md 建立冲刺档案,再调用 study_scheduler.md 生成初始计划,并由 policy_guard.md 约束输出边界。

2. 首次生成

系统生成 20 天总计划、第 1 天任务和初始进度面板。此时核心依赖 study_scheduler.mdprogress_tracker.md

3. 每日开始

当用户发送“开始今天任务”时,系统应读取原计划、上一日记录和当前掌握状态,调用 progress_tracker.md 判断今天应正常推进、局部补强还是压缩其他内容,再由 daily_coach.md 组织当天输出。

4. 学习过程

当用户请求讲解、例题或提示时,调用 daily_coach.md。如果需要配套训练,则联合 study_scheduler.md 按当天学习范围生成对应练习。

5. 当日测试

当用户发送“生成今天测试”时,由 study_scheduler.md 负责题型结构与难度控制,并确保题目范围与当天任务一致。

6. 提交反馈

当用户提交“今天完成了 80%,错了 2 道,某知识点还不稳”一类反馈时,系统调用 progress_tracker.md 更新进度,必要时再由 daily_coach.md 给出补强建议。

7. 自动更新

系统根据反馈更新学习记录、后续计划和节奏提醒,但默认只做局部调整,不直接推翻整张 20 天总计划。

默认触发语句

  • “开始今天任务”
  • “生成今天测试”
  • “讲一下今天的重点”
  • “给我一个例题并一步步提示”
  • “这是我今天的完成情况,帮我更新进度并判断要不要调整后面三天”

强约束

  • 不直接代写作业,不伪造学习记录,不编造老师划重点;
  • 不把押题包装成确定结论,只能给出基于资料的复习建议;
  • 可以提供讲解、提示、例题、练习和纠错,但不能替代学生完成正式考核;
  • 任何计划调整都应说明依据,并保留用户最终确认。

Comments

Loading comments...