agentleFS
ForceInjectionForceInjection/awesome-skills/skills/md-summarizer/SKILL.md

md-summarizer

Skill87 starsChanged 6 months agoApache-2.0View on GitHub

分析和总结指定的本地 Markdown 文件,并输出结构化的中文总结。当用户请求总结、分析或提取本地 Markdown 文档信息时调用此技能。

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the appropriate file reading tool to read the contents of the local Markdown file(s) specified by the user.

    line 15
  2. Distinctive:

    Verification: After reading, verify the content.

    line 16
  3. Distinctive:

    After analyzing each file individually, add a comprehensive comparison section:

    line 53
  4. Distinctive:

    Output Language: ALWAYS output the final analysis in Chinese (中文), regardless of the source language.

    line 73
  5. Distinctive:

    Formatting: Ensure that Chinese and English characters are separated by spaces.

    line 75
  6. Distinctive:

    If the user provides files without explicit instructions, default to the full structured analysis.

    line 78
  7. Very specific:

    If the user explicitly asks for a "quick summary" (简单总结), provide only the 核心概要 and 关键要点 sections.

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

English version: SKILL-en.md

Markdown Summarizer

Analyze and summarize text content from local Markdown files, outputting structured analysis in Chinese.

Workflow

Step 1: Read and Verify Content

Use the appropriate file reading tool to read the contents of the local Markdown file(s) specified by the user. If multiple files are provided, read them in parallel if possible. Verification: After reading, verify the content. If the file is completely empty or lacks substantive text content (e.g., only contains a few image links), notify the user immediately and abort the summarization for that specific file.

Step 2: Analyze Content

For each file, produce a structured analysis in Chinese with these sections. The output must be professional, objective, and insightful.

## [File Name]

### 1. 核心概要 (Executive Summary)

A single paragraph summarizing the core message and main theme of the document.

### 2. 关键要点 (Key Takeaways)

- Use an unordered list to highlight the most important points, facts, or arguments. Keep it concise.

### 3. 深度解析 (Deep Analysis)

A deep dive into the significance, context, and details of the content.

- Highlight the underlying logic or mechanisms described in the text.
- Include any critical data, statistics, or evidence presented.
- Point out the author's primary stance or bias (if applicable).

### 4. 值得关注的细节 (Notable Highlights)

Notable quotes, unique perspectives, surprising information, or edge cases mentioned.

### 5. 结论与行动建议 (Conclusion & Actionable Advice)

Actionable advice, recommendations, or next steps derived from the content. 
If not applicable, summarize the final verdict.

Step 3: Multi-File Comparison (when multiple files are provided)

After analyzing each file individually, add a comprehensive comparison section:

## 综合对比分析 (Cross-Reference Analysis)

### 共同主题 (Common Themes)

Identify shared concepts, consistent viewpoints, or industry trends across all documents.

### 差异与冲突 (Differences & Contradictions)

Highlight conflicting data, varying perspectives, or different methodologies proposed across the sources.

### 综合结论 (Synthesis)

Merge the insights from all provided documents into a unified conclusion.

Rules

  • Output Language: ALWAYS output the final analysis in Chinese (中文), regardless of the source language.
  • Accuracy: Preserve factual accuracy. Do not hallucinate or fabricate information not present in the source text.
  • Formatting: Ensure that Chinese and English characters are separated by spaces.
  • Handling Long Content: For exceptionally long documents where content is truncated, focus on the most substantive content already obtained. Add a disclaimer: "> 注意:原文内容过长,以下分析基于已获取的部分核心内容。"
  • Adaptive Output:
    • If the user provides files without explicit instructions, default to the full structured analysis.
    • If the user explicitly asks for a "quick summary" (简单总结), provide only the 核心概要 and 关键要点 sections.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.