Adoption

Agent Skills are supported by leading AI development tools.

VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory

xjtulyc/feishu-rich-card

Name: feishu-rich-card
Author: xjtulyc

skills/feishu-rich-card/SKILL.md

npx skillsauth add xjtulyc/MedgeClaw feishu-rich-card

Clean

TrivyContainer and dependency vulnerability scanner

Clean

SemgrepStatic code analysis for vulnerabilities

Clean

mcp-scan (Snyk)Model Context Protocol security validation

Skipped

Snyk (dep)Open source security scanning

Skipped

Socket.devSupply chain security analysis

Skipped

VirusTotalMulti-engine malware detection

Skipped

CrowdStrikeAdvanced threat intelligence

Skipped

OSV-ScannerOpen Source Vulnerability database check

Skipped

OWASP Dep-Check

Feishu Rich Card — 飞书图文混排卡片

在飞书群聊中发送图文并茂的交互式卡片，用于汇报进展、展示分析结果、项目状态等。

When to Use

汇报任务进展、项目状态
展示数据分析结果（图表 + 解读）
发送研究简报、阶段性成果
任何需要图文混排的飞书消息

Architecture

生成图片(SVG→PNG / matplotlib / PIL)
        ↓
上传图片到飞书 → 获取 image_key
        ↓
构造 Card JSON (schema 2.0) → 嵌入 img 元素 + markdown 元素
        ↓
调用飞书 API 发送 interactive 消息

Workflow

Step 1: Prepare Images

图片来源可以是：

SVG UI 模板 → 用 svg-ui-templates skill 生成 SVG → cairosvg 转 PNG
matplotlib/seaborn → 直接 savefig 为 PNG
PIL/Pillow → 程序化生成图片
已有文件 → 直接使用本地 PNG/JPG

Step 2: Upload & Send

使用 references/send_card.py 中的辅助函数：

# 完整用法参见 references/send_card.py
from send_card import FeishuCardSender

sender = FeishuCardSender()  # 自动读取 openclaw.json 凭证

# 发送图文卡片
sender.send_rich_card(
    chat_id="oc_xxx",
    title="📊 分析报告",
    elements=[
        {"type": "markdown", "content": "## 结果摘要\n\n发现 **3 个**显著差异基因"},
        {"type": "image", "path": "/tmp/volcano_plot.png", "alt": "火山图"},
        {"type": "markdown", "content": "> Gene X: FC=2.5, p<0.001"},
        {"type": "hr"},
        {"type": "image", "path": "/tmp/heatmap.png", "alt": "热图"},
        {"type": "markdown", "content": "**结论：** 样本间差异显著，建议进一步验证。"},
    ],
    header_template="blue"  # blue/indigo/green/red/purple/violet/wathet/turquoise/yellow/grey
)

Step 3: Quick One-liner (for simple cases)

sender.send_image_report(
    chat_id="oc_xxx",
    title="🧬 单细胞分析完成",
    intro="UMAP 降维完成，共识别 12 个细胞群：",
    image_path="/tmp/umap.png",
    conclusion="Cluster 5 为目标细胞群，marker: CD8A, GZMB, PRF1",
    header_template="indigo"
)

Card Elements Reference

| Element | Tag | 说明 | |---------|-----|------| | Markdown | markdown | 支持加粗、斜体、链接、列表、引用块、代码块 | | Image | img | 需要 image_key（上传后获取） | | Divider | hr | 水平分割线 | | Column Set | column_set | 多列并排布局 | | Note | note | 底部灰色备注 |

Header Templates (颜色)

blue wathet turquoise green yellow orange red carmine violet purple indigo grey

Key Rules

图片必须先上传到飞书获取 image_key，不能用 URL
Card schema 必须是 "2.0"
每张卡片最多 50 个元素
图片建议宽度 600-1200px，飞书会自动缩放
markdown 中不能嵌入图片，图片必须是独立的 img 元素
发送后 OpenClaw 的正常回复会重复，用 NO_REPLY 避免

Integration with SVG UI Templates

当需要专业级可视化时，结合 svg-ui-templates skill：

# 1. 生成 SVG（用模板或自定义）
# 2. 转 PNG
python3 -c "import cairosvg; cairosvg.svg2png(url='report.svg', write_to='report.png', output_width=2400)"
# 3. 用本 skill 上传并发送卡片

Default Chat ID

通过环境变量配置：FEISHU_DEFAULT_CHAT_ID（在 .env 中设置）

xjtulyc/feishu-rich-card

skills/feishu-rich-card/SKILL.md

Send rich interactive cards with embedded images in Feishu group chats. Use when reporting progress, sharing analysis results, or presenting any content that benefits from mixed text+image layout in Feishu. Combines SVG UI templates (or matplotlib/PIL charts) with Feishu Card Kit API.

770 stars

development

Updated Apr 21, 2026

$ install --global

skillsauth

npx skillsauth add xjtulyc/MedgeClaw feishu-rich-card

Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.

Security Scan Results

3 of 9 scanners reported clean

Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.

Scanners Passed

Scanners in report

Clean

TrivyContainer and dependency vulnerability scanner

95%

Clean

SemgrepStatic code analysis for vulnerabilities

95%

Clean

mcp-scan (Snyk)Model Context Protocol security validation

95%

Skipped

Snyk (dep)Open source security scanning

50%

Skipped

Socket.devSupply chain security analysis

50%

Skipped

VirusTotalMulti-engine malware detection

50%

Skipped

CrowdStrikeAdvanced threat intelligence

50%

Skipped

OSV-ScannerOpen Source Vulnerability database check

50%

Skipped

OWASP Dep-Check

50%

Last scanned: Apr 22, 2026, 1:52 AM120.7s2 files scanned

SKILL.md

name:: feishu-rich-card
description:: >

Feishu Rich Card — 飞书图文混排卡片

在飞书群聊中发送图文并茂的交互式卡片，用于汇报进展、展示分析结果、项目状态等。

When to Use

汇报任务进展、项目状态
展示数据分析结果（图表 + 解读）
发送研究简报、阶段性成果
任何需要图文混排的飞书消息

Architecture

生成图片(SVG→PNG / matplotlib / PIL)
        ↓
上传图片到飞书 → 获取 image_key
        ↓
构造 Card JSON (schema 2.0) → 嵌入 img 元素 + markdown 元素
        ↓
调用飞书 API 发送 interactive 消息

Workflow

Step 1: Prepare Images

图片来源可以是：

SVG UI 模板 → 用 svg-ui-templates skill 生成 SVG → cairosvg 转 PNG
matplotlib/seaborn → 直接 savefig 为 PNG
PIL/Pillow → 程序化生成图片
已有文件 → 直接使用本地 PNG/JPG

Step 2: Upload & Send

使用 references/send_card.py 中的辅助函数：

# 完整用法参见 references/send_card.py
from send_card import FeishuCardSender

sender = FeishuCardSender()  # 自动读取 openclaw.json 凭证

# 发送图文卡片
sender.send_rich_card(
    chat_id="oc_xxx",
    title="📊 分析报告",
    elements=[
        {"type": "markdown", "content": "## 结果摘要\n\n发现 **3 个**显著差异基因"},
        {"type": "image", "path": "/tmp/volcano_plot.png", "alt": "火山图"},
        {"type": "markdown", "content": "> Gene X: FC=2.5, p<0.001"},
        {"type": "hr"},
        {"type": "image", "path": "/tmp/heatmap.png", "alt": "热图"},
        {"type": "markdown", "content": "**结论：** 样本间差异显著，建议进一步验证。"},
    ],
    header_template="blue"  # blue/indigo/green/red/purple/violet/wathet/turquoise/yellow/grey
)

Step 3: Quick One-liner (for simple cases)

sender.send_image_report(
    chat_id="oc_xxx",
    title="🧬 单细胞分析完成",
    intro="UMAP 降维完成，共识别 12 个细胞群：",
    image_path="/tmp/umap.png",
    conclusion="Cluster 5 为目标细胞群，marker: CD8A, GZMB, PRF1",
    header_template="indigo"
)

Card Elements Reference

Header Templates (颜色)

blue wathet turquoise green yellow orange red carmine violet purple indigo grey

Key Rules

图片必须先上传到飞书获取 image_key，不能用 URL
Card schema 必须是 "2.0"
每张卡片最多 50 个元素
图片建议宽度 600-1200px，飞书会自动缩放
markdown 中不能嵌入图片，图片必须是独立的 img 元素
发送后 OpenClaw 的正常回复会重复，用 NO_REPLY 避免

Integration with SVG UI Templates

当需要专业级可视化时，结合 svg-ui-templates skill：

# 1. 生成 SVG（用模板或自定义）
# 2. 转 PNG
python3 -c "import cairosvg; cairosvg.svg2png(url='report.svg', write_to='report.png', output_width=2400)"
# 3. 用本 skill 上传并发送卡片

Default Chat ID

通过环境变量配置：FEISHU_DEFAULT_CHAT_ID（在 .env 中设置）

Related Skills

xjtulyc/svg-ui-templates

development

VerifiedTrustedCommunity

Generate professional SVG UI panels for structured information display. Use when presenting lists, task checklists, pipeline/dependency status diagrams, or rich-text report layouts as SVG images. Covers four templates - list-panel, checklist-panel, pipeline-status, richtext-layout. Style is professional, business-oriented, academic-grade with Material Design color palette.

770SKILL.mdUpdated Apr 21, 2026

xjtulyc/svg-ui-templates

xjtulyc/paper-reproduce

tools

VerifiedTrustedCommunity

Systematic methodology for reproducing published academic papers using provided data. Use when the user asks to reproduce, replicate, or verify results from a published paper, including sample selection, descriptive statistics, regression analyses, and generating reproduction reports (Markdown + LaTeX PDF). Covers the full pipeline: data exploration, variable identification/mapping, sample filtering, variable construction, statistical analysis, result comparison, and documentation. Applicable to any observational study, clinical cohort, or survey-based research paper.

770SKILL.mdUpdated Apr 21, 2026

xjtulyc/paper-reproduce

xjtulyc/skills/dashboard

development

VerifiedTrustedCommunity

# Local Research Dashboard Skill ## 概述每次科研任务开始时，生成一个临时的本地 dashboard，动态展示任务关键信息和产物预览。 ## 组件 - `state.json`：数据协议，openclaw 负责写入和更新 - `dashboard.html`：本地单文件页面，轮询 state.json 并渲染 - `dashboard_serve.py`：静态文件服务器，serve 任务根目录所有文件放在**任务独立目录**中（如 `data/<task_name>/dashboard/`）。 --- ## state.json Schema ```json { "title": "任务标题", "updated_at": "2024-01-01 12:00:00", "panels": [ { "type": "progress|text|list|code|table|image|files|step", "label": "面板标题（可折叠的标识）", "content":

770SKILL.mdUpdated Apr 21, 2026

xjtulyc/skills/dashboard

xjtulyc/cjk-viz

tools

VerifiedTrustedCommunity

CJK (中日韩) 字体检测与 matplotlib 配置。任何涉及中文标签、标题、图例的可视化任务启动前必须先执行本 skill 的字体检测流程，确保不会出现方块乱码。适用于 matplotlib / seaborn / plotly 静态导出等场景。

770SKILL.mdUpdated Apr 21, 2026

Download

For Claude Desktop. Download once, then upload the file in the app — no terminal needed.

Need help? View full Cowork setup guide →

Install manually

Choose your platform

# Clone the repo
git clone https://github.com/xjtulyc/MedgeClaw.git

# Copy into Claude Code skills folder (global)
cp -r MedgeClaw/skills/feishu-rich-card ~/.claude/skills/

Claude Code Skills — official skills path docs.

Repository

xjtulyc/MedgeClaw

770 stars

Compatible with

Claude Code

OpenAI Codex CLI

ChatGPT