Not in the top 1,000 by GitHub stars
xjtulyc/MedgeClaw
Open-source AI research assistant for biomedicine — chat to run RNA-seq, drug discovery, clinical analysis, and more. Built on Claude Code with 140 K-Dense scientific skills, real-time dashboard, and RStudio/JupyterLab integration. | 开源生物医学 AI 研究助手,对话即可驱动转录组、药物发现、临床分析等工作流,集成 140 个科学技能与实时研究看板。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/biomed-dispatch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fef51d37ee3e
No earlier version was observed for comparison.
skills/charls-reproduce/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fef51d37ee3e
No earlier version was observed for comparison.
skills/cjk-viz/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → fef51d37ee3e
No earlier version was observed for comparison.
skills/dashboard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fef51d37ee3e
No earlier version was observed for comparison.
skills/feishu-rich-card/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fef51d37ee3e
No earlier version was observed for comparison.
skills/paper-reproduce/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fef51d37ee3e
No earlier version was observed for comparison.
skills/svg-ui-templates/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fef51d37ee3e → fef51d37ee3e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fef51d37ee3e
No earlier version was observed for comparison.
Verified commit fef51d37ee3e1f5754790d9ae20f72c006c78dcc
git clone --filter=blob:none --no-checkout https://github.com/xjtulyc/MedgeClaw.git .hotskills/xjtulyc-medgeclaw && git -C .hotskills/xjtulyc-medgeclaw checkout --detach fef51d37ee3e1f5754790d9ae20f72c006c78dcc
# Copy each selected skill directory from .hotskills/xjtulyc-medgeclaw into .claude/skills/<skill-name>/Heat
0.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- biomed-dispatch
skills/biomed-dispatch - charls-reproduce
skills/charls-reproduce - cjk-viz
skills/cjk-viz - dashboard
skills/dashboard - feishu-rich-card
skills/feishu-rich-card - paper-reproduce
skills/paper-reproduce - svg-ui-templates
skills/svg-ui-templates
How it works
biomed-dispatch
When your agent uses it
Dispatch biomedical research and data analysis tasks to Claude Code with K-Dense Scientific Skills. Use this skill when the user asks to run any bioinformatics, genomics, drug discovery, clinical data analysis, proteomics, multi-omics, medical imaging, or scientific computation task. Also use for literature search (PubMed, bioRxiv), pathway analysis, protein structure prediction, or scientific writing tasks.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
2,390 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use
- Workflow
- 科学写作任务的特殊处理
- Output handling
- Example dispatches
- 输出路径约束(重要)
- Important rules
Files
SKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytesSKILL.mdcore9,148 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcharls-reproduce
When your agent uses it
CHARLS (China Health and Retirement Longitudinal Study) database-specific knowledge for reproducing published papers. Use when reproducing or analyzing papers that use CHARLS data, including variable mapping from harmonized to raw questionnaire items, cognitive function scoring (episodic memory, mental status, TICS), CESD-10 depression screening, social isolation index construction, and chronic disease coding. Also use for any CHARLS data cleaning, variable construction, or cohort selection task.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
3,637 tokensWhen the skill is activated
Reference documents
2,214 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CHARLS 概览
- Harmonized 数据集 vs 原始数据
- 核心变量映射表
- 日期定向子变量
- 常见缺失率(Wave1 参考)
- 样本筛选经验
- Wave 间数据合并
- 标准化 OLS 回归模板
- 环境注意事项
Files
SKILL.mdcore10,539 bytesSKILL.mdcore10,539 bytesSKILL.mdcore10,539 bytesSKILL.mdcore10,539 bytesreferences/variable_dictionary.mddoc5,806 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcjk-viz
When your agent uses it
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。
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
1,779 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时使用
- 快速使用
- 关键陷阱:`.ttc` 文件与 matplotlib
- 字体优先级
- 与其他 skill 配合
- 验证
Scripts executed separately
scripts/setup_cjk_font.py
Files
SKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytesscripts/setup_cjk_font.pyruns10,562 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
2,156 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概述
- 组件
- state.json Schema
- 交互功能
- 配色
- openclaw 的职责
- 使用方式
Scripts executed separately
dashboard_serve.py
Files
SKILL.mdcore7,139 bytesSKILL.mdcore7,139 bytesSKILL.mdcore7,139 bytesSKILL.mdcore7,139 bytesdashboard.htmlasset35,077 bytesdashboard_serve.pyruns2,650 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfeishu-rich-card
When your agent uses it
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.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,124 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Architecture
- Workflow
- Card Elements Reference
- Header Templates (颜色)
- Key Rules
- Integration with SVG UI Templates
- Default Chat ID
Scripts executed separately
references/send_card.py
Files
SKILL.mdcore3,824 bytesSKILL.mdcore3,824 bytesSKILL.mdcore3,824 bytesSKILL.mdcore3,824 bytesreferences/send_card.pyruns10,243 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpaper-reproduce
When your agent uses it
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.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,461 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 复现流程(6 阶段)
- 输出目录结构
- 常见陷阱
- 参考
Files
SKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytesSKILL.mdcore8,372 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsvg-ui-templates
When your agent uses it
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.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
574 tokensWhen the skill is activated
Reference documents
2,601 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Templates
- Workflow
- Key Rules
Files
../feishu-rich-card/SKILL.mddoc3,824 bytesSKILL.mdcore2,270 bytesSKILL.mdcore2,270 bytesassets/checklist-panel.svgasset6,101 bytesassets/list-panel.svgasset4,589 bytesassets/pipeline-status.svgasset7,742 bytesassets/richtext-layout.svgasset5,438 bytesreferences/template-guide.mddoc4,250 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- biomed-dispatch
- charls-reproduce
- cjk-viz
- feishu-rich-card
- paper-reproduce
- svg-ui-templates
Repository facts
- License
- No license detected
- Created
- Feb 24, 2026
- Last pushed
- Mar 12, 2026
- Forks
- 133
- Open issues
- 4
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 31 notes
skills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/biomed-dispatch/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/charls-reproduce/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/charls-reproduce/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/charls-reproduce/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cjk-viz/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cjk-viz/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cjk-viz/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cjk-viz/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cjk-viz/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cjk-viz/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dashboard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dashboard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dashboard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 44 network referencesin 10 files: dashboard/dashboard.html:232 feishu-rich-card/references/send_card.py:52 dashboard/dashboard_serve.py:21 and 7 more
- No hidden or obfuscated text
- 21 instruction override signalsin 1 file: biomed-dispatch/SKILL.md:67
- 3 executable scriptsin 3 files: cjk-viz/scripts/setup_cjk_font.py:1 dashboard/dashboard_serve.py:1 feishu-rich-card/references/send_card.py:1
- 3 references to secretsin 1 file: feishu-rich-card/references/send_card.py:24
- No requests to vote in Hot
Show all 71 signals by file
skills/biomed-dispatch/SKILL.md
- Network accessline 44
# Start server python "$TASK_DIR/dashboard/dashboard_serve.py" --port <free_port> & # Tell user the URL immediately: http://localhost:<port>/dashboard/dashboard.html - Network accessline 46
# Tell user the URL immediately: http://localhost:<port>/dashboard/dashboard.html - Instruction override signalline 67
cd "$TASK_DIR" && claude -p "短任务描述。先读 skill 文件。完成后: openclaw system event --text 'Done: 摘要' --mode now" --output-format stream-json --verbose --dangerously-skip-permissions - Instruction override signalline 69
--verbose \ --dangerously-skip-permissions \ - Instruction override signalline 70
--dangerously-skip-permissions \ - Instruction override signalline 73
# 旧方式(不推荐,无可观测性) claude --dangerously-skip-permissions -p "Use available scientific skills. [TASK]. Input: [PATH]. Outputs: $TASK_DIR/output/. Update dashboard at $TASK_DIR/dashboard/state.json after each step (step panels with code + ou - Instruction override signalline 74
claude --dangerously-skip-permissions -p "Use available scientific skills. [TASK]. Input: [PATH]. Outputs: $TASK_DIR/output/. Update dashboard at $TASK_DIR/dashboard/state.json after each step (step panels with code + outputs). Completion: - Instruction override signalline 86
# Phase 1: 文献搜索 + 大纲(5-10 分钟) cd writing_outputs/<task_name> && claude -p "读 ~/next-medgeai/MedgeClaw/scientific-skills/scientific-skills/literature-review/SKILL.md 和 scientific-writing/SKILL.md。按 literature-review 流程搜索文献,创建 outline.md(Stag - Instruction override signalline 87
cd writing_outputs/<task_name> && claude -p "读 ~/next-medgeai/MedgeClaw/scientific-skills/scientific-skills/literature-review/SKILL.md 和 scientific-writing/SKILL.md。按 literature-review 流程搜索文献,创建 outline.md(Stage 1)。" --output-format stre - Instruction override signalline 88
--output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 90
# Phase 2: 写正文(分章节,每章 5-10 分钟) cd writing_outputs/<task_name> && claude -p "读 outline.md 的第 1-3 节。用 Edit 工具在 manuscript.tex 中补充这些章节的正文。写完整的学术散文。" \ --output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 91
cd writing_outputs/<task_name> && claude -p "读 outline.md 的第 1-3 节。用 Edit 工具在 manuscript.tex 中补充这些章节的正文。写完整的学术散文。" --output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 92
--output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 94
# Phase 3: 创建 BibTeX + 添加引用(5 分钟) cd writing_outputs/<task_name> && claude -p "读 manuscript.tex 和 outline.md。创建 references/references.bib(至少 30 篇),在 tex 中添加 \cite{}(每节至少 5 处),在 \end{document} 前加 \bibliographystyle{unsrt} 和 \bibliography{ref - Instruction override signalline 95
cd writing_outputs/<task_name> && claude -p "读 manuscript.tex 和 outline.md。创建 references/references.bib(至少 30 篇),在 tex 中添加 \cite{}(每节至少 5 处),在 \end{document} 前加 \bibliographystyle{unsrt} 和 \bibliography{references}。" --output-format stre - Instruction override signalline 96
--output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 98
# Phase 4: 生成图表(5-10 分钟) cd writing_outputs/<task_name> && claude -p "在 figures/ 下创建 5 个 Python 脚本生成图表 PDF。中文标签用 Noto Sans CJK SC 字体。" \ --output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 99
cd writing_outputs/<task_name> && claude -p "在 figures/ 下创建 5 个 Python 脚本生成图表 PDF。中文标签用 Noto Sans CJK SC 字体。" --output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 100
--output-format stream-json --verbose --dangerously-skip-permissions 2>/dev/null | tail -1 - Instruction override signalline 131
python "$TASK_DIR/dashboard/dashboard_serve.py" --port 7790 & # 4. Dispatch to Claude Code claude --dangerously-skip-permissions -p "分析 CHARLS 队列中 ACE 与 CVD 的关联。Input: data/charls_ace/charls.dta. Output: data/charls_ace/output/. 每步更新 dashbo - Instruction override signalline 133
claude --dangerously-skip-permissions -p "分析 CHARLS 队列中 ACE 与 CVD 的关联。Input: data/charls_ace/charls.dta. Output: data/charls_ace/output/. 每步更新 dashboard state.json(step panels with code + outputs)。完成后: openclaw system event --text 'Done: AC - Instruction override signalline 138
claude --dangerously-skip-permissions -p "Use DESeq2 scientific skill. Run differential expression. Counts: /workspace/data/counts.csv, metadata: /workspace/data/meta.csv, contrast: treatment vs control. Save to /workspace/data/rnaseq/outpu - Instruction override signalline 143
claude --dangerously-skip-permissions -p "Use Scanpy scientific skill. Analyze 10X data at /workspace/data/10x/. QC, clustering, markers. Save to /workspace/data/10x/output/. Update dashboard state.json with step panels."
skills/charls-reproduce/SKILL.md
- Network accessline 17
|------|------| | 全称 | China Health and Retirement Longitudinal Study (中国健康与养老追踪调查) | | 官网 | https://charls.pku.edu.cn/ | - Network accessline 18
| 全称 | China Health and Retirement Longitudinal Study (中国健康与养老追踪调查) | | 官网 | https://charls.pku.edu.cn/ | | 覆盖 | 全国 150 县级单位、450 社区,45 岁以上居民 | - Network accessline 19
| 官网 | https://charls.pku.edu.cn/ |
skills/cjk-viz/scripts/setup_cjk_font.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/dashboard/SKILL.md
skills/dashboard/dashboard.html
- Network accessline 232
async function fetchState() { try { const res = await fetch('state.json?t=' + Date.now()); - Network accessline 233
try { const res = await fetch('state.json?t=' + Date.now()); if (!res.ok) return; - Network accessline 234
const res = await fetch('state.json?t=' + Date.now()); - Network accessline 488
if (!el) return; try { const res = await fetch(src + '?t=' + Date.now()); - Network accessline 489
try { const res = await fetch(src + '?t=' + Date.now()); if (!res.ok) throw new Error('HTTP ' + res.status); - Network accessline 490
const res = await fetch(src + '?t=' + Date.now()); - Network accessline 508
async function loadTableFromSrc(src, el) { try { const res = await fetch(src + '?t=' + Date.now()); - Network accessline 509
try { const res = await fetch(src + '?t=' + Date.now()); if (!res.ok) throw new Error('HTTP ' + res.status); - Network accessline 510
const res = await fetch(src + '?t=' + Date.now()); - Network accessline 603
async function previewCsv(path, name) { try { const res = await fetch(path + '?t=' + Date.now()); - Network accessline 604
try { const res = await fetch(path + '?t=' + Date.now()); if (!res.ok) throw new Error('HTTP ' + res.status); - Network accessline 605
const res = await fetch(path + '?t=' + Date.now()); - Network accessline 619
async function previewText(path, name) { try { const res = await fetch(path + '?t=' + Date.now()); - Network accessline 620
try { const res = await fetch(path + '?t=' + Date.now()); if (!res.ok) throw new Error('HTTP ' + res.status); - Network accessline 621
const res = await fetch(path + '?t=' + Date.now());
skills/dashboard/dashboard_serve.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 21
def find_free_port(start=7788): for port in range(start, start + 20): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: - Network accessline 22
for port in range(start, start + 20): with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: if s.connect_ex(("localhost", port)) != 0: - Network accessline 23
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: - Network accessline 70
httpd = DashboardServer(("", port), DashboardHandler) url = f"http://localhost:{port}/dashboard/dashboard.html" - Network accessline 71
url = f"http://localhost:{port}/dashboard/dashboard.html"
skills/feishu-rich-card/references/send_card.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 24
[Credential-related source omitted] - Network accessline 52
def _api_base(domain: str = "feishu") -> str: if domain == "lark": return "https://open.larksuite.com/open-apis" - Network accessline 53
if domain == "lark": return "https://open.larksuite.com/open-apis" return "https://open.feishu.cn/open-apis" - Network accessline 54
return "https://open.larksuite.com/open-apis" - Network accessline 55
return "https://open.feishu.cn/open-apis" - Network accessline 67
base = _api_base(creds.get("domain", "feishu")) resp = requests.post( - Network accessline 68
resp = requests.post( - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Network accessline 98
with open(image_path, "rb") as f: resp = requests.post( - Network accessline 99
resp = requests.post( - Network accessline 181
if reply_to: resp = requests.post( - Network accessline 182
resp = requests.post( - Network accessline 189
) else: resp = requests.post( - Network accessline 190
else: resp = requests.post( f"{self.base}/im/v1/messages", - Network accessline 191
resp = requests.post(
skills/svg-ui-templates/assets/checklist-panel.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 720" font-family="'Inter','Helvetica Neue','Microsoft YaHei',sans-serif">
skills/svg-ui-templates/assets/list-panel.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 680" font-family="'Inter','Helvetica Neue','Microsoft YaHei',sans-serif">
skills/svg-ui-templates/assets/pipeline-status.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 700" font-family="'Inter','Helvetica Neue','Microsoft YaHei',sans-serif">
skills/svg-ui-templates/assets/richtext-layout.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 700" font-family="'Inter','Helvetica Neue','Microsoft YaHei',sans-serif">
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 2 facts
- Contacts open.larksuite.com, which SKILL.md, the README and the plugin manifest do not mentionfeishu-rich-card/references/send_card.py:54High confidence
- Contacts open.feishu.cn, which SKILL.md, the README and the plugin manifest do not mentionfeishu-rich-card/references/send_card.py:55High confidence
Signal confidence: 52 facts
- Network access in code of the SKILL.mdbiomed-dispatch/SKILL.md:44High confidence
- Network access in code of the SKILL.mdbiomed-dispatch/SKILL.md:46High confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:67Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:69Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:70Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:73Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:74Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:86Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:87Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:88Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:90Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:91Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:92Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:94Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:95Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:96Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:98Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:99Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:100Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:131Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:133Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:138Low confidence
- Instruction override signal in code of the SKILL.mdbiomed-dispatch/SKILL.md:143Low confidence
- Network access in prose of the SKILL.mdcharls-reproduce/SKILL.md:17Low confidence
- Network access in prose of the SKILL.mdcharls-reproduce/SKILL.md:18Low confidence
- Network access in prose of the SKILL.mdcharls-reproduce/SKILL.md:19Low confidence
- Executable script in code of a file that runscjk-viz/scripts/setup_cjk_font.py:1High confidence
- Network access in prose of the SKILL.mddashboard/SKILL.md:192Low confidence
- Network access in prose of the SKILL.mddashboard/SKILL.md:206Low confidence
- Executable script in code of a file that runsdashboard/dashboard_serve.py:1High confidence
- Network access in code of a file that runsdashboard/dashboard_serve.py:21High confidence
- Network access in code of a file that runsdashboard/dashboard_serve.py:22High confidence
- Network access in code of a file that runsdashboard/dashboard_serve.py:23High confidence
- Network access in code of a file that runsdashboard/dashboard_serve.py:70High confidence
- Network access in code of a file that runsdashboard/dashboard_serve.py:71High confidence
- Executable script in code of a file that runsfeishu-rich-card/references/send_card.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuefeishu-rich-card/references/send_card.py:24Low confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:52High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:53High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:54High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:55High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:67High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:68High confidence
- Access to secrets in code of a file that runsfeishu-rich-card/references/send_card.py:69High confidence
- Access to secrets in code of a file that runsfeishu-rich-card/references/send_card.py:76High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:98High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:99High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:181High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:182High confidence
- Network access in code of a file that runsfeishu-rich-card/references/send_card.py:189High confidence
and 2 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path CLAUDE.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/biomed-dispatch/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/biomed-dispatch/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/biomed-dispatch/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/biomed-dispatch/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/biomed-dispatch/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.