← Back to Skills Marketplace
suka233

KMind文档转思维导图

by suka233 · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
104
Downloads
1
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install kmind-markdown-to-mindmap-cn
Description
将 Markdown 大纲或纯文本转换为 KMind 导图，并导出 SVG 或 PNG 图片。支持主题、布局、连线、深浅色和彩虹分支配置。
README (SKILL.md)

KMind Zen 是一个专业的思维导图软件，提供桌面端、网页端、思源插件和 Obsidian 插件，官网为 https://kmind.app。

这个 skill 用于把 Markdown 大纲或纯文本转换成 KMind 导图图片，本 skill 是纯离线工具，无需任何网络链接即可在本地转换导图。

它的优势是可以在本地离线生成精美、风格统一的思维导图，并支持导出 SVG / PNG，同时支持配置主题预设、根布局、分支连线、深浅色外观和彩虹分支。

如果用户需要可继续编辑的导图包，优先导出 .kmindz.svg。.kmindz.svg 包可以无缝导入到任意 KMind Zen 端继续编辑；即使当前机器上没有客户端，也依然可以先把它当作 SVG 文件快速查看导图内容，后续再导入客户端继续编辑。

适用于会议提纲、读书笔记、脑暴清单、项目方案、中文 Markdown 转导图等场景。

这是一个可发布、可独立分发的 skill。始终通过 {baseDir} 下的入口执行：

node {baseDir}/scripts/kmind-render.mjs ...

工作流：

  1. 如果用户希望指定主题、布局或连线风格，先查看可选项： node {baseDir}/scripts/kmind-render.mjs themes --format json
  2. 如果用户提供的是原始 Markdown 文本，而不是文件路径，就通过 stdin 传入。
  3. 使用 render-markdown 启动导出。
  4. 默认会尝试自动调用用户本机的 Chromium 浏览器进行无头渲染。
  5. 第一行 stdout 是 status: "ready" 的 JSON。
  6. 命令结束后，最后一行 stdout 是 status: "done" 的 JSON，其中包含最终 outputPath。
  7. 只有在自动浏览器不可用时，才使用 --browser manual 手动打开打印出来的本地 URL。

如果用户本机没有可用的 Chromium 浏览器，则自动 SVG / PNG 导出不可用。此时要么使用 --browser manual 手动打开本地页面完成导出，要么明确告知当前环境暂不可用，不能伪造成功。

常用命令模板：

node {baseDir}/scripts/kmind-render.mjs render-markdown INPUT_OR_DASH --output OUTPUT.svg|OUTPUT.png --theme-preset PRESET_ID --layout LAYOUT_ID --edge-route EDGE_ROUTE_ID --appearance light|dark --rainbow auto|on|off --png-scale 1 --browser auto

参数建议：

  • --output 在未显式传 --image-format 时决定输出格式：.svg 表示矢量图，.png 表示位图。
  • --theme-preset 请从 themes 输出里选。推荐候选： kmind-material-3-slate kmind-rainbow-breeze kmind-midnight-neon kmind-material-3-rounded-orthogonal-ocean kmind-material-3-rounded-orthogonal-forest
  • --layout 请从 themes 输出里选。常用候选： logical-right logical-left mindmap-both-auto
  • --edge-route 请从 themes 输出里选。常用候选： cubic edge-lead-quadratic center-quadratic orthogonal
  • --appearance dark 强制使用暗色模式。
  • --rainbow on 会强制开启彩虹分支，即使当前主题默认没开。
  • --png-scale 1 与当前 webapp 默认导出一致；只有在用户明确要求更高分辨率 PNG 时再调大。
  • --browser auto 是默认值，会尝试自动调用本机浏览器。
  • --browser manual 是手动兜底模式。
  • 不要主动向用户暴露 --svg-mode 和 --png-mode。当前内部默认已经使用最接近 webapp 实际导出效果的组合：SVG=fidelity、PNG=accurate。只有当用户明确要求低层导出调优时才提这些高级参数。

默认值：

  • theme-preset: kmind-material-3-slate
  • image-format: 优先从 --output 推断，推断不出来时回退为 svg
  • layout: 默认不显式覆盖，沿用 KMind 默认根布局
  • edge-route: 默认不显式覆盖，沿用主题预设的连线风格
  • appearance: light
  • rainbow: auto
  • svg-mode: 内部默认 fidelity
  • png-mode: 内部默认 accurate
  • png-scale: 1
  • viewport-width: 1600
  • viewport-height: 900

当前这个可发布 skill 仅开放如下安全候选：

  • layouts：logical-right、logical-left、mindmap-both-auto
  • edge-routes：cubic、edge-lead-quadratic、center-quadratic、orthogonal

如果用户要的是 KMind 项目文件，而不是图片，不要走这个图片导出流程，改用：

node {baseDir}/scripts/kmind-render.mjs import-markdown INPUT_OR_DASH --output OUTPUT.kmindz.svg

Usage Guidance
What to consider before installing/running: 1) Source is unknown and there is no homepage — prefer packages from known authors. 2) The skill bundles several megabytes of JS and will execute locally; inspect the vendor files (search for network calls, puppeteer/playwright, fetch/https/http, and any hardcoded URLs). 3) The SKILL.md triggered 'base64-block' and 'unicode-control-chars' heuristics — open the SKILL.md in a hex/text viewer and search for hidden or encoded payloads; decode any base64 you find. 4) Run the tool in a sandboxed environment (isolated VM or container) the first time; use --browser manual and avoid automatic browser launches until you confirm behavior. 5) If you need higher assurance, ask the author for source/origin or for a minimal audited build; absence of network requests and a clean SKILL.md would raise confidence. If you want, I can: (a) search the bundled files for network-related strings (http, https, puppeteer, download), (b) extract and display any base64 blocks for inspection, or (c) point out exact files/lines that look suspicious.
Capability Analysis
Type: OpenClaw Skill Name: kmind-markdown-to-mindmap-cn Version: 0.1.0 The skill is a legitimate tool for converting Markdown outlines into mind map images (SVG/PNG). It uses a bundled KMind CLI (`scripts/vendor/cli.mjs`) which starts a temporary local HTTP server on the loopback address (127.0.0.1) and automates a local Chromium-based browser to perform headless rendering. While it possesses risky capabilities like spawning child processes and running a network server, these are strictly used for the stated rendering functionality and do not show signs of data exfiltration, remote communication, or malicious intent.
Capability Assessment
✓ Purpose & Capability
Name/description match the requested binaries and config. Requesting node and access to a browser (browser.enabled) is coherent for a local HTML/headless‑render export tool. Bundling a CLI and render code is expected for an offline renderer.
ℹ Instruction Scope
Runtime instructions are narrowly scoped to running the bundled CLI: node scripts/kmind-render.mjs ... and to using a local Chromium/browser for rendering. The SKILL.md explicitly states offline operation and does not declare network endpoints. However, the SKILL.md contains pre-scan prompt‑injection indicators (base64 block and unicode control characters) which could hide or obfuscate instructions — that is a red flag and warrants inspection of the raw SKILL.md for hidden content.
✓ Install Mechanism
No external install/downloads are declared; the skill is instruction+bundled code (no URL downloads). That is lower risk than fetching arbitrary remote binaries. The vendor files are large (several MB) — expected for a bundled renderer UI but they should be audited because the code will run locally.
✓ Credentials
The skill declares no environment variables or credentials. It only needs node and browser access, which match the stated purpose. No unrelated secrets are requested.
✓ Persistence & Privilege
always is false and the skill does not request system‑wide changes. It spawns a local child node process; nothing indicates it will modify other skills or agent config autonomously.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install kmind-markdown-to-mindmap-cn
  3. After installation, invoke the skill by name or use /kmind-markdown-to-mindmap-cn
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
- Initial release: Convert Markdown outlines or plain text into KMind mind maps with SVG or PNG export. - Supports theme, layout, connector, light/dark appearance, and rainbow branch configurations. - Operates fully offline; no internet connection required. - Enables easy command-line use with sensible defaults and manual/auto browser modes. - Exposes only safe theme, layout, and edge route options for enhanced security. - Offers `.kmindz.svg` export for further editing in KMind Zen clients.
Metadata
Slug kmind-markdown-to-mindmap-cn
Version 0.1.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is KMind文档转思维导图?

将 Markdown 大纲或纯文本转换为 KMind 导图，并导出 SVG 或 PNG 图片。支持主题、布局、连线、深浅色和彩虹分支配置。 It is an AI Agent Skill for Claude Code / OpenClaw, with 104 downloads so far.

How do I install KMind文档转思维导图?

Run "/install kmind-markdown-to-mindmap-cn" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is KMind文档转思维导图 free?

Yes, KMind文档转思维导图 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does KMind文档转思维导图 support?

KMind文档转思维导图 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created KMind文档转思维导图?

It is built and maintained by suka233 (@suka233); the current version is v0.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments