What makes exam-rescue-html notable?

1.3K downloads. Trust evidence available

How should exam-rescue-html be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

exam-rescue-html

读取 knowledge_map.json，生成三分区考前抢救清单 HTML：核心公式速记 / 高频考点清单 / 高频错点清单，以卡片形式呈现，支持打印。全程零等待，自动完成内容生成、模板填充、文件写入。 Skill: exam-rescue-html Owner: zhoucha833-lang Summary: 读取 knowledge_map.json，生成三分区考前抢救清单 HTML：核心公式速记 / 高频考点清单 / 高频错点清单，以卡片形式呈现，支持打印。全程零等待，自动完成内容生成、模板填充、文件写入。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-12T05:07:34.423Z | user Initial release of exam-rescue-html. - Generates a printable three-section "exam rescue" checklist HTML: Core Formulas, High-Frequency Points, and Common Mistakes, based on knowledge

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.0release · observed May 12, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b87qx14janve53g6m4mxwgs86g9n8:exam-rescue-html

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zhoucha833-lang-exam-rescue-html/snapshot"

Documentation

CLAWHUB

11,178 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: exam-rescue-html
description: >
  读取 knowledge_map.json，生成三分区考前抢救清单 HTML：
  核心公式速记 / 高频考点清单 / 高频错点清单，以卡片形式呈现，支持打印。
  全程零等待，自动完成内容生成、模板填充、文件写入。
license: MIT
---

# ⚡️ 静默执行协议

**[SYSTEM CRITICAL]**

1. **Do not ask for confirmation to proceed.**
2. **全流程一次完成。** 生成三类卡片内容 → 写 JSON → 填模板 → 写 HTML → 引导。
3. **不向用户输出中间生成过程。** 不输出"正在处理第X个考点…"之类提示。
4. **All errors are silent fallback.** 遇到问题静默处理，不暴露给用户。

---

# Skill：exam-rescue-html

## 1. 触发条件

- **自动触发**：exam-question-generator 完成后，用户说「继续」
- **用户触发**：用户说「生成抢救清单」或「最后冲刺」或「重新生成」

---

## 2. 执行流程

```
Step 1   确认 .exam-session/knowledge_map.json 存在且有效
Step 2   读取 {baseDir}/references/content-rules.md（三类卡片生成规则）

Step 3   生成「核心公式速记」（formula_cards）：
           从 knowledge_map.points 中找含公式/定理/法则/定律的考点
           调用 knowledge-base 技能的 note_retrieve 接口检索原文
           为每条生成：name + formula + condition（可选）+ memory_hook（可选）

Step 4   生成「高频考点清单」（hotspot_cards）：
           筛选 importance ≥ 0.75 的考点，按 importance 降序，最多 20 个
           调用 knowledge-base 技能的 note_retrieve 接口检索原文
           为每条生成：name + core_note（≤2句话）

Step 5   生成「高频错点清单」（mistake_cards）：
           取 is_weak_point = true 的考点，补充知识库返回含"误区/注意/陷阱"的考点
           调用 knowledge-base 技能的 note_retrieve 接口检索原文
           为每条生成：name + wrong（❌开头）+ right（✅开头）+ tip（可选）

Step 6   写入 .exam-session/rescue_notes.json（格式见"输出格式"）
Step 7   读取 {baseDir}/assets/template.html
Step 8   为三类卡片各自生成 HTML 片段（格式见"模板填充规范"）
Step 9   将 template.html 中所有 {{占位符}} 替换为实际值，得到完整 HTML
Step 10  将完整 HTML 字符串写入 exam-rescue-YYYYMMDD.html（写到工作区根目录）
Step 11  发送引导消息
```

---

## 3. 输出格式

写入 `.exam-session/rescue_notes.json`：

```json
{
  "rescue": {
    "exam_type": "string",
    "exam_date": "YYYY-MM-DD",
    "days_remaining": 0,
    "target_score": "string",
    "generated_at": "YYYY-MM-DD",
    "formula_count": 0,
    "hotspot_count": 0,
    "mistake_count": 0,
    "formula_cards": [
      {
        "id": "f_001",
        "name": "公式/定理名",
        "formula": "公式内容（数学用 $LaTeX$，其他学科用文字）",
        "condition": "适用条件 | null",
        "memory_hook": "口诀 | null"
      }
    ],
    "hotspot_cards": [
      {
        "id": "h_001",
        "name": "考点名",
        "importance": 0.92,
        "is_weak_point": false,
        "core_note": "≤2句核心要点"
      }
    ],
    "mistake_cards": [
      {
        "id": "m_001",
        "name": "错点名称",
        "wrong": "❌ 常见错误理解",
        "right": "✅ 正确做法",
        "tip": "辨别提示 | null"
      }
    ]
  }
}
```

---

## 4. 模板填充规范

**输出路径**：`exam-rescue-YYYYMMDD.html`（工作区根目录）

**模板占位符**：

| 占位符 | 取值 |
|--------|-----|
| `{{exam_type}}` | rescue.exam_type |
| `{{days_remaining}}` | rescue.days_remaining |
| `{{target_score}}` | rescue.target_score |
| `{{formula_count}}` | rescue.formula_count |
| `{{hotspot_count}}` | rescue.hotspot_count |
| `{{mistake_count}}` | rescue.mistake_count |
| `{{formula_cards_html}}` | 所有公式卡片 HTML 拼接 |
| `{{hotspot_cards_html}}` | 所有考点卡片 HTML 拼接 |
| `{{mistake_cards_html}}` | 所有错点卡片 HTML 拼接 |

**HTML 片段格式**：

```html
<!-- 公式卡片 -->
<div class

_meta.json

{
  "ownerId": "kn79n8rjw599q4q8hq9txtde5d86g2ht",
  "slug": "exam-rescue-html",
  "version": "1.0.0",
  "publishedAt": 1778562454423
}

references/content-rules.md

# 抢救清单内容规则

## 一、核心公式速记（formula_cards）

### 筛选来源
从 knowledge_map.points 中找出满足以下任一条件的考点：
- point.name 或 point.evidence 含"公式"/"定理"/"法则"/"定律"/"性质"/"推论"
- RAG 检索返回的原文中含数学表达式、化学方程式、物理公式等

### 每张卡片字段
| 字段 | 要求 |
|------|------|
| name | 公式/定理/法则名称，≤20字 |
| formula | 公式或定义正文；数学公式用 $LaTeX$ 格式；非数学学科写文字公式/原文 |
| condition | 适用条件/前提/范围，≤30字；无则 null |
| memory_hook | 口诀/关键词，≤10字；无则 null，不强制 |

### 写法规范
- formula 直接写内容，不写"公式为："等引导语
- 数学：`$f'(x) = \lim_{h\to0}\frac{f(x+h)-f(x)}{h}$`
- 物理：`$F = ma$`，condition 填"质量恒定，合外力=F"
- 文科/法律：用简洁文字原文，不强行 LaTeX

---

## 二、高频考点清单（hotspot_cards）

### 筛选规则
```
主条件：importance ≥ 0.75
降级（筛选后 < 5 个时）：importance ≥ 0.6
按 importance 降序，上限 20 个
```

### 每张卡片字段
| 字段 | 要求 |
|------|------|
| name | 考点名，与 knowledge_map 保持一致 |
| importance | 取自 knowledge_map |
| is_weak_point | 取自 knowledge_map |
| core_note | ≤2句话，30–80字，直接陈述；公式>条件>步骤>概念 |

### core_note 按知识类型写法
**公式类**：写公式 + 使用条件
> "sin²x + cos²x = 1；变体：1 + tan²x = sec²x（x ≠ kπ + π/2）。"

**条件判断类**：写充分/必要条件 + 典型反例
> "f'(x₀)=0 是极值必要条件，非充分条件；x³ 在 x=0 处导数为零但非极值。"

**步骤类**：写关键步骤，跳过显然步骤
> "1. 令分母=0求奇点；2. 验证左右极限是否相等；3. 与函数值比较。"

**概念辨析类**：写最精简的区分点
> "充分条件→推出结论；必要条件←结论倒推；充要条件←→双向。"

### 优先级颜色（imp-dot class）
| importance 范围 | class |
|----------------|-------|
| ≥ 0.8 | high |
| 0.6–0.79 | mid |
| < 0.6 | low |

---

## 三、高频错点清单（mistake_cards）

### 筛选来源
- knowledge_map.points 中 is_weak_point = true 的所有考点
- 补充：RAG 检索返回的原文中含"错误"/"误区"/"注意"/"容易混淆"/"陷阱"的考点
- 上限 15 个，按 importance 降序

### 每张卡片字段
| 字段 | 要求 |
|------|------|
| name | 错点名，描述错误本质，如"极限与连续的混淆"，≤20字 |
| wrong | 常见错误理解/做法，以"❌"开头，≤40字 |
| right | 正确理解/做法，以"✅"开头，≤40字 |
| tip | 辨别/记忆技巧，≤20字；无则 null |

### 写法规范
- wrong 和 right 必须形成对比，不是错误的解释而是正确做法的呈现
- 示例：
  - wrong: `❌ 极限存在则函数在该点连续`
  - right: `✅ 极限存在且等于函数值，才连续`
  - tip: `可导必连续，连续不必可导`

---

## 四、无内容兜底规则

| 场景 | 处理 |
|------|------|
| 该学科无公式（如纯文科） | formula_cards = []，`{{formula_count}}` = 0，隐藏该分区（Claude 在 HTML 中不输出该 section） |
| 筛选后考点数 < 5 | 触发降级条件，降至 importance ≥ 0.6 |
| 无薄弱点且无错误线索 | mistake_cards = []，`{{mistake_count}}` = 0，隐藏该分区 |
| 知识库某考点无返回 | 仅凭 point.name + point.evidence 生成，继续 |

skill-card.md

## Description:

Generates a printable three-section exam rescue checklist HTML from knowledge_map.json, covering core formulas, high-frequency points, and common mistakes.

This skill is ready for commercial/non-commercial use.

## Publisher:

[zhoucha833-lang](https://clawhub.ai/user/zhoucha833-lang)

### License/Terms of Use:

MIT-0

## Use Case:

External learners and exam-preparation agents use this skill to turn an existing exam knowledge map into a compact printable review sheet before a test. It is designed for Chinese-language study workflows that need formula, hotspot, and mistake cards generated into HTML.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill suppresses confirmations and errors during generation.

Mitigation: Review the generated HTML and rescue notes before relying on them, especially when the input knowledge map may be incomplete or malformed.

Risk: The generated HTML may include unescaped study content.

Mitigation: Use trusted knowledge_map.json content or ensure fields are escaped before opening or sharing the generated HTML.

Risk: Opening the generated HTML can load and execute JavaScript from unpkg.com.

Mitigation: Open the file only in environments where CDN access and client-side KaTeX rendering are acceptable.

Risk: The workflow writes and may overwrite files in the workspace.

Mitigation: Run the skill in a workspace where exam-rescue-YYYYMMDD.html and .exam-session/rescue_notes.json writes are expected.

## Reference(s):

- [Content Rules](references/content-rules.md)
- [ClawHub Skill Page](https://clawhub.ai/zhoucha833-lang/skills/exam-rescue-html)
- [Publisher Profile](https://clawhub.ai/user/zhoucha833-lang)

## Skill Output:

**Output Type(s):** [text, code, configuration]

**Output Format:** [JSON study notes plus generated HTML file and a concise completion message]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Writes .exam-session/rescue_notes.json when possible and creates exam-rescue-YYYYMMDD.html in the workspace root.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.