← 返回 Skills 市场
refine-markdown-to-mkdocs
作者
SmilingWayne
· GitHub ↗
· v1.0.0
· MIT-0
129
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install refine-markdown-to-mkdocs
功能描述
Refines raw reading notes by merging similar ideas, removing noise, and summarizing key points. Outputs structured markdown with different format (mkdocs mat...
安全使用建议
This skill appears coherent with its stated purpose and does not request credentials or network access. Points to consider before installing: 1) The skill is allowed to delete or rewrite your notes — keep a backup of any originals you care about. 2) It will write a plan file ({filename}-plan.md) and output refined markdown; review the plan and approve changes when prompted. 3) Although the skill pauses for confirmation, if you plan to let an autonomous agent run it, ensure the agent's policies limit destructive actions. 4) There is no external transmission specified, but if you later modify the SKILL.md or agent policy to add network calls, re-review for data exfiltration. Overall: safe-to-install from a coherence perspective, but backup your files and review plans before allowing destructive edits.
功能分析
Type: OpenClaw Skill
Name: refine-markdown-to-mkdocs
Version: 1.0.0
The skill is a legitimate utility for refining and formatting markdown notes into MkDocs-compatible structures. It follows a transparent workflow in SKILL.md that includes content classification, semantic clustering based on a reference guide (references/notes_classify.md), and user confirmation steps before modifying or creating files. No indicators of data exfiltration, malicious execution, or prompt injection were found.
能力评估
Purpose & Capability
Name and description match the instructions: the SKILL.md details classification, clustering, plan generation, and content reconstruction for notes-to-mkdocs. Nothing asked for (no env vars, no binaries, no installs) is disproportionate or unrelated to note-refinement.
Instruction Scope
Instructions explicitly tell the agent to read the input file, consult the bundled references/notes_classify.md, save a plan file ({filename}-plan.md), and then rewrite/merge/delete content per the approved plan. That behaviour is expected for a notes-refinement tool, but users should be aware the skill is permitted to delete or rewrite content locally — it pauses for confirmation at two points (category and plan), which reduces risk.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes risk because nothing is downloaded or written beyond the agent's normal outputs.
Credentials
No environment variables, credentials, or config paths are requested. All referenced files (references/notes_classify.md) are included in the package and are appropriate for the stated purpose.
Persistence & Privilege
always:false (default) and the skill does not request elevated or persistent privileges. It will create local plan and output files as part of normal operation but does not modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install refine-markdown-to-mkdocs - 安装完成后，直接呼叫该 Skill 的名称或使用
/refine-markdown-to-mkdocs触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
A custom Claude Skill built for my personal knowledge workflow, designed to refine scattered, unstructured Markdown reading/study notes into **structured, high-density knowledge text** compliant with MkDocs Material standards via intelligent categorization, semantic clustering, and content reconstruction.
Unlike basic formatters, this Skill supports flexible merging, pruning, minor supplementation, and logical rewriting of content—preserving core information while maximizing readability and knowledge density, ideal for building and maintaining personal MkDocs knowledge bases.
**Core principles**: Domain-adaptive structuring, category-specific logic, controlled information fidelity, high-density output.
Covers intelligent classification & optimization for **13 knowledge domains**:
Philosophy, Plays, Novels, Poetry, Literary Theory & Criticism, Prose, History, Art Theory, Biography, Programming & CS, Mathematical Models & Theory, Unfocused Integrated Materials, Miscellaneous Notes.
Each category includes custom **high/medium/low value content rules** to retain key insights and filter redundant noise.
## Full Workflow
1. **Content Recognition & Categorization**: Auto-read notes, identify book/chapter/genre, match knowledge domains and confirm with user
2. **Semantic Clustering Analysis**: Split knowledge points per domain rules, generate a refinement plan with merge/keep/delete markers for user approval
3. **Structured Content Reconstruction**: Assemble clustered points into MkDocs-style modules following strict formatting specs
4. **Auto Save & Backup**: Generate refined files, back up originals, output plan and processing reports
5. **Completion Statistics**: Show processing metrics, merger logs, and deletion summaries for full traceability
元数据
常见问题
refine-markdown-to-mkdocs 是什么？
Refines raw reading notes by merging similar ideas, removing noise, and summarizing key points. Outputs structured markdown with different format (mkdocs mat... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 129 次。
如何安装 refine-markdown-to-mkdocs？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install refine-markdown-to-mkdocs」即可一键安装，无需额外配置。
refine-markdown-to-mkdocs 是免费的吗？
是的，refine-markdown-to-mkdocs 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
refine-markdown-to-mkdocs 支持哪些平台？
refine-markdown-to-mkdocs 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 refine-markdown-to-mkdocs？
由 SmilingWayne（@smilingwayne）开发并维护，当前版本 v1.0.0。
推荐 Skills