SKILLS & AGENTS/Skill 与 Agent·MULTI-AGENT
ZHangZHengEric/Sage
Multi-Agent System Framework For Complex Tasks
怎么装:Install: git clone https://github.com/ZHangZHengEric/Sage.git
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
09 OCT 202609 OCT 2026
状态STATUS
持续活跃Active
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ Node 用户的安装方式。The install route for Node users.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserapp/skills/agent-browser/SKILL.md
# Or with explicit CDP port
02执行 Shell 命令Runs shell commandsapp/skills/agent-browser/SKILL.md
allowed-tools: Bash(npx
03控制浏览器Controls a browserapp/skills/agent-browser/SKILL.md
allowed-tools: agent-browser:*)
04执行 Shell 命令Runs shell commandsapp/skills/agent-browser/SKILL.md
allowed-tools: Bash(agent-browser:*)
05需要系统权限Needs system permissionsapp/skills/ui-ux-pro-max/SKILL.md
sudo apt update && sudo apt install python3
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-ai",
"evidence": "app/skills/algorithmic-art/SKILL.md: …ile that works immediately in claude.ai artifacts or any browser. Sta…"
},
{
"agent": "claude-code",
"evidence": "app/skills/doc-coauthoring/SKILL.md: …agents is available (e.g., in Claude Code):** Perform the testing dire…"
},
{
"agent": "vscode",
"evidence": "app/skills/excalidraw-diagram-generator/SKILL.md: …e file - Or use Excalidraw VS Code extension ## Best Practices…"
}
],
"apiKey": "able model: ```python \"\"\"Set MODEL_API_KEY and replace your-model below; no sage.y",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 6,
"dev-tools": 1,
"indie-web": 1,
"skill-agent": 0,
"productivity": 4
},
"primary": "skill-agent",
"secondary": "multi-agent"
},
"localRuntime": null,
"skillMdTotal": 26,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 4,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "26 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "MCP SDK dependency",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"app/skills/agent-browser/SKILL.md",
"app/skills/algorithmic-art/SKILL.md",
"app/skills/brainstorming/SKILL.md",
"app/skills/brand-guidelines/SKILL.md",
"app/skills/canvas-design/SKILL.md",
"app/skills/claw-skill-shub/SKILL.md",
"app/skills/deep-research-agent/SKILL.md",
"app/skills/doc-coauthoring/SKILL.md",
"app/skills/docx/SKILL.md",
"app/skills/excalidraw-diagram-generator/SKILL.md",
"app/skills/excel-analysis/SKILL.md",
"app/skills/frontend-design/SKILL.md",
"app/skills/himalaya/SKILL.md",
"app/skills/internal-comms/SKILL.md",
"app/skills/mcp-builder/SKILL.md",
"app/skills/memory-organizer/SKILL.md",
"app/skills/pdf/SKILL.md",
"app/skills/pptx/SKILL.md",
"app/skills/skill-creator/SKILL.md",
"app/skills/slack-gif-creator/SKILL.md",
"app/skills/social-push/SKILL.md",
"app/skills/theme-factory/SKILL.md",
"app/skills/ui-ux-pro-max/SKILL.md",
"app/skills/web-artifacts-builder/SKILL.md",
"app/skills/webapp-testing/SKILL.md",
"app/skills/xlsx/SKILL.md"
],
"skillMdFetched": 26
}