← Back to Skills Marketplace
Mermaid 转飞书图片 Canvas 渲染版
by
icesumer-lgtm
· GitHub ↗
· v2.0.1
· MIT-0
340
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install mermaid-to-feishu
Description
自动将 Mermaid 代码通过浏览器 Canvas 渲染为 PNG 图片并上传发送到飞书对话,实现图表可视化展示。
Usage Guidance
This skill appears to do what it says — render Mermaid and send images to Feishu — but take these precautions before installing:
- Confirm the skill actually needs Feishu app_id/app_secret and only grant an app with the minimal permissions required; prefer using a short-lived token or app with limited scope.
- The registry metadata does NOT declare the required env vars; treat that as a red flag and verify SKILL.md before supplying credentials.
- Avoid storing app_secret in plaintext under ~/.agents/skills unless you control the machine and understand the file's permissions; prefer environment variables or a secure secret store if available.
- Review any scripts (send-mermaid.py or similar) placed in your ~/.agents/skills directory before running them — the SKILL.md shows subprocess usage and file writes which can be abused if modified.
- If possible, run initial tests in a sandboxed agent environment and monitor network requests to ensure images are only uploaded to Feishu and no unexpected external endpoints are contacted.
- If you are unsure, ask the skill author for an updated manifest that declares required env vars and provides a signed/hosted script or code repository for review.
Capability Analysis
Type: OpenClaw Skill
Name: mermaid-to-feishu
Version: 2.0.1
The mermaid-to-feishu skill bundle is designed to render Mermaid diagrams into images and send them to Feishu (Lark) via its API. The skill provides two legitimate workflows: using the OpenClaw browser tool for Canvas-based rendering and a Python script (send-mermaid.py) that utilizes mermaid-cli (mmdc). The code snippets and instructions in SKILL.md are consistent with the stated purpose, using standard libraries like requests for Feishu API interaction (open.feishu.cn) and tempfile for secure intermediate file handling. No evidence of data exfiltration, unauthorized execution, or malicious prompt injection was found.
Capability Assessment
Purpose & Capability
The described capability (render Mermaid → PNG → upload to Feishu) is coherent with the instructions: browser-based Canvas rendering or mermaid-cli and calls to Feishu API are appropriate. However, the registry metadata lists no required environment variables or credentials while SKILL.md explicitly requires FEISHU_APP_ID, FEISHU_APP_SECRET and a receive_id (or a config file). That mismatch is an incoherence that should be resolved before trusting the skill.
Instruction Scope
SKILL.md instructs the agent to create HTML/markdown files, run a browser tool to open file:// paths and take snapshots, and optionally run a local mermaid-cli via subprocess. Those actions are within the skill's stated purpose. The instructions also tell the agent to write a config file under ~/.agents/skills/... containing app secrets (or read them from env vars). Writing and reading secrets from a user-home config file broadens the scope and should be treated carefully.
Install Mechanism
This is an instruction-only skill with no install spec or code files to execute from the registry. Optional guidance to install mermaid-cli via npm is standard. No remote arbitrary download/extract operations are specified in the manifest.
Credentials
The SKILL.md requires Feishu credentials (app_id, app_secret, receive_id) to call Feishu APIs — that is proportionate to the task. The concern is registry/manifest omission: the skill metadata does not declare these required env vars. Also SKILL.md suggests storing app secrets in a plaintext JSON under the user's home directory, which increases risk of credential exposure if not handled securely.
Persistence & Privilege
The skill is not set to always:true and is user-invocable only. It instructs placing scripts/config under ~/.agents/skills which is typical for user-installed skills. It does not request system-wide privileges or modification of other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mermaid-to-feishu - After installation, invoke the skill by name or use
/mermaid-to-feishu - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.1
修复安全问题:config.json 改用占位符,添加到.clawhubignore
v2.0.0
更新为 Browser/Canvas 渲染方案,飞书不支持直接渲染 Mermaid
v1.0.0
Initial release of Nano Banana Pro image generation & editing skill.
- Generate or edit images using Google's Gemini 3 Pro Image API.
- Supports text-to-image and image-to-image workflows with selectable 1K, 2K, or 4K resolution.
- Includes clear command usage, filename generation conventions, and prompt templates.
- Guides for common issues and preflight checks.
- Output: saves PNG images in the current user directory and displays the path.
Metadata
Frequently Asked Questions
What is Mermaid 转飞书图片 Canvas 渲染版?
自动将 Mermaid 代码通过浏览器 Canvas 渲染为 PNG 图片并上传发送到飞书对话,实现图表可视化展示。 It is an AI Agent Skill for Claude Code / OpenClaw, with 340 downloads so far.
How do I install Mermaid 转飞书图片 Canvas 渲染版?
Run "/install mermaid-to-feishu" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Mermaid 转飞书图片 Canvas 渲染版 free?
Yes, Mermaid 转飞书图片 Canvas 渲染版 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Mermaid 转飞书图片 Canvas 渲染版 support?
Mermaid 转飞书图片 Canvas 渲染版 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Mermaid 转飞书图片 Canvas 渲染版?
It is built and maintained by icesumer-lgtm (@icesumer-lgtm); the current version is v2.0.1.
More Skills