Chalk Labs
Need help deploying learning-exercises?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yushenliu06-learning-exercises
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/learning-exercises
What's inside
- Skill name
learning-exercises- Description
- 根据给定材料和自然语言目标设计跨学科练习,按学习站现有结构固定题目、参考与评分量表。
- License
- MIT
- Instructions
- 141 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
依据本次材料、目标、疑问和已有错误出题,不预设学科;题型与难度应能检验所学理解,而非复制原文凑题。
- 用明确题面检验一个或相连的少量目标,难度适度;必要时使用小案例、迁移或对比。
- 短且有限答案才用 exact;开放作答用 self。接受成立的替代解法,避免把措辞差异当成知识错误。
- 主观题在用户作答前固定合理的 rubric,各项说明可判断、分值符合现有约束;不要事后改变标准或冒充官方考试评分。
- 严格按本次提供的结构输出题目、参考答案、解析、来源和量表,不增造字段或来源ID。参考交由程序隐藏,题面和摘要不提前泄露答案。
- 练习按钮与 generate_exercises 工具遵循同一指导;工具参数仍须通过现有校验与持久化回执,文字不代表保存成功。
修改已有练习或解释本地 Markdown 格式时,按需加载 `learning-exercise-markdown`。已有题目的修订结构不同于下面的新建参数,不要直接重写页面正文来改变评分答案。
## 完整样例
下面两组样例字段与两侧真实校验完全一致:exact(客观题)与 self(主观自评)各一组;每组把「generate_exercises 工具入参」与「practice 模式最终输出」分成两份 JSON 成对展示,不可混用或合并。
- 工具入参 JSON:在 question/explain 等模式经 generate_exercises 工具保存练习时作为参数提交,按工具 schema 校验;顶层只有 requirements(本轮用户要求)、summary、exercises 三项。
- 最终输出 JSON:practice 模式直接输出的练习产物,交由 Rust 校验后保存;顶层只有 exercises、summary 两项,没有 requirements,也不要写 id、answerMatch 等程序生成字段(校验通过后由程序补齐)。
- 样例中的 sourceIds(src_demo_material、src_demo_note)仅为示意;实际取值只能来自本轮授权引用清单(context manifest)中的稳定 ID(使用“本轮练习可引用来源”的 sourceId,文件路径不是 sourceId),不得重复、不得虚构,AI 回复里的编号不算来源。
### 样例一:exact(客观题)
generate_exercises 工具入参:
```json
{
"requirements": "依据本次材料出一道单位换算客观题,只检验一个目标,答案短且有限。",
"summary": "考查千米与米的换算,并接受千分位等价写法。",
"exercises": [
{
"question": "3.5 千米等于多少米?只填写数值。",
"format": "exact",
"answers": ["3500", "3,500"],
"explanation": "1 千米 = 1000 米,3.5 × 1000 = 3500;3,500 是千分位写法,同为正确。",
"tags": ["单位换算"],
"sourceIds": ["src_demo_material"]
}
]
}
```
practice 模式最终输出:
```json
{
"exercises": [
{
"question": "3.5 千米等于多少米?只填写数值。",
"format": "exact",
"answers": ["3500", "3,500"],
"explanation": "1 千米 = 1000 米,3.5 × 1000 = 3500;3,500 是千分位写法,同为正确。",
"tags": ["单位换算"],
"sourceIds": ["src_demo_material"]
}
],
"summary": "针对单位换算疑点:等价写法全部列入参考答案,按去首尾空白后的文本精确核对。"
}
```
### 样例二:self(主观自评)
generate_exercises 工具入参:
```json
{
"requirements": "出一道开放解释题,用户用自己的话说明现象与依据,作答前先固定评分量表。",
"summary": "考查比热容概念与昼夜温差解释,附固定评分量表。",
"exercises": [
{
"question": "用自己的话解释:为什么海边的昼夜温差通常比内陆小?说明判断依据。",
"format": "self",
"answers": ["海水比热容比沙石大,吸收或放出同样热量时温度变化更慢,从而调节了海边气温。"],
"explanation": "开放作答按量表评分,参考答案只是一种表述,同义或更完整的解释同样成立。",
"tags": ["比热容", "现象解释"],
"sourceIds": ["src_demo_material", "src_demo_note"],
"rubric": {
"criteria": [
{
"id": "heat_capacity",
"label": "比热容差异",
"description": "指出海水比热容大于内陆沙石,同等热量下温度变化更小。",
"maxPoints": 4
},
{
"id": "regulation",
"label": "调节过程",
"description": "说明白天升温慢、夜间降温慢,两者共同缩小昼夜温差。",
"maxPoints": 4
},
{
"id": "evidence",
"label": "依据引用",
"description": "引用本轮材料的原文或数据支持结论,不虚构来源。",
"maxPoints": 2
}
]
}
}
]
}
```
practice 模式最终输出:
```json
{
"exercises": [
{
"question": "用自己的话解释:为什么海边的昼夜温差通常比内陆小?说明判断依据。",
"format": "self",
"answers": ["海水比热容比沙石大,吸收或放出同样热量时温度变化更慢,从而调节了海边气温。"],
"explanation": "开放作答按量表评分,参考答案只是一种表述,同义或更完整的解释同样成立。",
"tags": ["比热容", "现象解释"],
"sourceIds": ["src_demo_material", "src_demo_note"],
"rubric": {
"criteria": [
{
"id": "heat_capacity",
"label": "比热容差异",
"description": "指出海水比热容大于内陆沙石,同等热量下温度变化更小。",
"maxPoints": 4From YuShenLiu06/learning-station, MIT.
More from YuShenLiu06/learning-station
- 0.586score
yushen-code-quality-review
YuShenLiu06
审查 PR 中的死代码、无意义抽象、重复实现与可复用替代方案,输出带证据和统一口径的 PR 反馈。仅提出意见,不自动删除、重构、安装依赖或采用外部代码。
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
yushen-pr-cycle
YuShenLiu06
将用户确认的软件需求拆成小 PR,协调实现、原生代码和安全审查、修复复查、集成验收,并根据有效返工反馈改进规则。适用于用户委托开发任务,不为普通讨论自动启动实现。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
learning-exercise-markdown
YuShenLiu06
说明学习站练习题的本地 Markdown 格式,以及生成、读取和逐题修改时题面与评分数据的对应关系。用于解释练习文件或修改已有练习,不替代出题指导。
SkillAFreshness: A★ 1Claude Code +9 - 0.573score
learning-explore
YuShenLiu06
在探索学习模式中,围绕用户问题逐步形成可验证的理解、当前结论与未解疑问。
SkillAFreshness: A★ 1Claude Code +9 - 0.573score
learning-review
YuShenLiu06
在AI复习引导中,先让用户回忆或作答,再依据已有错误与来源提供反馈和针对练习。
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 25
- Last commit (this folder)
- Oct 24, 2026 (7 days ago)
- Last release
- Oct 24, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/YuShenLiu06/learning-station
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from YuShenLiu06
- 0.586score
yushen-code-quality-review
YuShenLiu06
审查 PR 中的死代码、无意义抽象、重复实现与可复用替代方案,输出带证据和统一口径的 PR 反馈。仅提出意见,不自动删除、重构、安装依赖或采用外部代码。
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
yushen-pr-cycle
YuShenLiu06
将用户确认的软件需求拆成小 PR,协调实现、原生代码和安全审查、修复复查、集成验收,并根据有效返工反馈改进规则。适用于用户委托开发任务,不为普通讨论自动启动实现。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
learning-exercise-markdown
YuShenLiu06
说明学习站练习题的本地 Markdown 格式,以及生成、读取和逐题修改时题面与评分数据的对应关系。用于解释练习文件或修改已有练习,不替代出题指导。
SkillAFreshness: A★ 1Claude Code +9 - 0.573score
learning-explore
YuShenLiu06
在探索学习模式中,围绕用户问题逐步形成可验证的理解、当前结论与未解疑问。
SkillAFreshness: A★ 1Claude Code +9 - 0.573score
learning-review
YuShenLiu06
在AI复习引导中,先让用户回忆或作答,再依据已有错误与来源提供反馈和针对练习。
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get learning-exercises running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
learning-exercises skill. Agent Mart. https://agentmart.dev/skills/yushenliu06-learning-exercises (last updated 2026-10-24)