md-summarizer
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.
More from forceinjection/awesome-skills
doc-reviewer
审查技术文档。支持四种独立评审类型:大纲评审(检查目录与结构逻辑)、内容评审(检查文字准确性与代码质量)、资产评审(校验链接与引用合规)、格式评审(校对纯视觉排版与标点)。当用户请求审查或修正 Markdown 文档时使用。
5agent-skill-reviewer
Review Agent Skill directories and SKILL.md files against best practices. Use this skill when the user wants to review, validate, or check an Agent Skill implementation.
5project-analyzer
Generate a comprehensive project documentation (whitepaper) based on deep codebase analysis, covering architecture, modules, testing, and deployment.
4dir-organizer
整理和优化项目目录结构。当用户请求整理目录、分类文件、清理无用文件或重构文件夹结构时调用此技能。
4code-reader
Use when you want to deeply understand an unfamiliar codebase and generate reusable cognitive skills from it, by providing a local path or GitHub URL
4update-submitter
Analyzes git status, groups related file changes, and generates standardized Conventional Commits. Invoke when the user wants to commit changes, submit updates, or create a PR.
3