← Back to Skills Marketplace
314
Downloads
1
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install md-to-share
Description
将 Markdown 文件转换为原生长图的 skill，可被 OpenClaw、Claude Code 等 AI Agent 直接调用。A skill that converts Markdown to long images, callable by AI Agents like OpenClaw and Cl...
Usage Guidance
This skill appears to do what it says: convert Markdown to long images using Playwright. Before installing/using it, consider: (1) it depends on Playwright and its postinstall will download Chromium (large binary and network activity) — run npm install in a controlled environment; (2) the tool writes screenshots to disk, so avoid passing paths to sensitive files you don't want rendered; (3) OpenClaw agents will compress images (SKILL.md and docs already note two compression layers) — use the openclaw preset (1200px/5MB) if you want to avoid downstream compression; (4) review package.json and md2img.mjs if you operate under strict security policies; otherwise the skill is internally consistent and does not request unrelated credentials or hidden remote endpoints.
Capability Analysis
Type: OpenClaw Skill
Name: md-to-share
Version: 2.2.0
The skill is a legitimate utility designed to convert Markdown files into long images using Playwright and Chromium. The code logic in `md2img.mjs` is well-structured, focusing on rendering HTML and managing image splitting for platform-specific constraints (e.g., Discord's size limits), and the documentation (including a detailed investigation into image quality) demonstrates clear, helpful intent without any signs of data exfiltration, malicious execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name/description (Markdown → long image) match the included files and runtime: md2img.mjs reads .md, renders HTML in Playwright Chromium, screenshots to JPEG/PNG, and implements splitting/themes. Declared presets and channel behaviors align with the implementation.
Instruction Scope
SKILL.md limits runtime actions to parsing a markdown file, launching an isolated Playwright Chromium, rendering, producing image files, and providing examples for sending via agent message tooling. It does not instruct reading unrelated system files or exfiltrating environment variables. It does reference OPENCLAW-specific env vars for auto-detection (expected for agent integration).
Install Mechanism
There is no registry install spec, but package.json includes dependencies on 'playwright' and a postinstall script ('npx playwright install chromium'), which will download a large Chromium binary from Playwright distribution hosts when npm install is run. This is expected for Playwright-based tools but is resource-heavy and performs network downloads during install — review before running in restricted or air-gapped environments.
Credentials
The skill requests no required env vars or credentials. Optional env vars mentioned (CHROME_PATH, MD2IMG_TIMEOUT, OPENCLAW_* detection) are reasonable for customizing browser path/timeouts and environment detection. No unrelated secrets or multiple external tokens are requested.
Persistence & Privilege
Skill does not request persistent/system-wide privileges. always is false and it does not modify other skills or system configuration. It writes output image files to paths supplied by the caller (expected behavior).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install md-to-share - After installation, invoke the skill by name or use
/md-to-share - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.0
v2.0: Migrate from puppeteer-core to Playwright (bundled Chromium, no system browser needed). v2.2: Add --channel flag for channel-aware smart splitting (Discord auto-split, WeChat/iMessage keep long image). Fix bash wrapper arg forwarding and symlink resolution.
v2.1.0
Add environment-aware presets for OpenClaw vs Claude Code: auto-detection, openclaw preset (1200px, 5MB), generic preset (1600px, 8MB), new CLI options
v1.0.1
Add English documentation, highlight AI Agent compatibility (OpenClaw, Claude Code)
v1.0.0
Initial release: Convert Markdown to native long image for WeChat/Discord sharing
Metadata
Frequently Asked Questions
What is Md To Share?
将 Markdown 文件转换为原生长图的 skill，可被 OpenClaw、Claude Code 等 AI Agent 直接调用。A skill that converts Markdown to long images, callable by AI Agents like OpenClaw and Cl... It is an AI Agent Skill for Claude Code / OpenClaw, with 314 downloads so far.
How do I install Md To Share?
Run "/install md-to-share" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Md To Share free?
Yes, Md To Share is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Md To Share support?
Md To Share is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Md To Share?
It is built and maintained by DTacheng (@dtacheng); the current version is v2.2.0.
More Skills