SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL
shanraisshan/claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
怎么装:Install: npm install -g appium && appium driver install xcuitest
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.1%+0.1%
67k → 67k stars · 2 个快照67k → 67k stars · 2 snapshots
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
$ 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 browserreadme
| use mcp ([Claude in Chrome](https://code.claude.com/docs/en/chrome), [Playwright](https://github.com/microsoft/playwright-mcp), [Chrome De
02执行 Shell 命令Runs shell commands.claude/skills/agent-browser/SKILL.md
allowed-tools: Bash(agent-browser:*)
03控制浏览器Controls a browser.claude/skills/agent-browser/SKILL.md
allowed-tools: Bash(agent-browser:*)
04读写本地文件Reads and writes local filesagent-teams/.claude/skills/time-svg-creator/SKILL.md
allowed-tools: Write
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-code",
"evidence": "tree: .claude/"
},
{
"agent": "codex",
"evidence": "tree: .codex/"
},
{
"agent": "claude-ai",
"evidence": "readme: …)  | `claude.ai/code` | [Routines](https://co…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …CLIProxyAPI) | 32k | Router | Gemini CLI, Codex, Claude Code, Antigrav…"
},
{
"agent": "vscode",
"evidence": "readme: …x) terminals instead of IDE ([VS Code](https://code.visualstudio.co…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 3,
"dev-tools": 0,
"indie-web": 3,
"skill-agent": 7,
"productivity": 3
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": "outer | OpenRouter, DeepSeek, Ollama, Gemini, Kimi, Qwen, Groq, +more | Rout",
"skillMdTotal": 9,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 6,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "9 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 9 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": ".mcp.json (configures servers it uses)",
"weight": 0.3
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/agent-browser/SKILL.md",
".claude/skills/presentation/presentation-structure/SKILL.md",
".claude/skills/presentation/presentation-styling/SKILL.md",
".claude/skills/presentation/vibe-to-agentic-framework/SKILL.md",
".claude/skills/time-skill/SKILL.md",
".claude/skills/weather-fetcher/SKILL.md",
".claude/skills/weather-svg-creator/SKILL.md",
"agent-teams/.claude/skills/time-fetcher/SKILL.md",
"agent-teams/.claude/skills/time-svg-creator/SKILL.md"
],
"skillMdFetched": 9
}