跳到主要内容
Supermarket
返回能力市场
Agent Pack
programming
MIT

claude-code-templates

Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods

davila7davila7
83/ 100

公开评测 · 综合采用结论

证据充分,整体质量与安全表现优秀

查看评测依据 查找我项目的报告基于公开项目证据,非安全认证或安装推荐
33.9kstars
4.0kforks
最近更新 5小时前
评测生成时间(北京时间)
本报告引擎
v3.10.0
当前引擎
v3.17.3

本报告与当前引擎使用不同规则;原分数不会自动更新,不同版本的分数不宜直接对比。

重新评测此项目

进入后确认来源与额度,提交才会创建任务。

代码版本未记录或记录无效,无法核对本报告的 commit 与送评文本;不会用当前项目代码回填历史记录。

Evaluation report

综合采用结论

83
B
满分 100 · 静态采用参考
值得推荐中风险
决策摘要

证据充分,整体质量与安全表现优秀

95%
高置信度
92
文档
86
安全
74
质量
100
活跃
65
采用
  • 基础评测完成+25/25确定性评分与静态安全扫描已完成
  • README 有效证据+20/258,158 个去重后的有效字符
  • 独立证据来源+20/205 类非重复证据,重复文件不叠加
  • 仓库元数据+10/10已取得仓库状态与采用数据
  • 活跃记录+5/5已取得最近提交时间
  • AI 复核+15/15已完成结构化 AI 证据复核

本报告评了什么

综合分用于静态采用筛选,不是任务成功率,也不代表使用 Skill 后的能力提升。

静态检查范围
记录 10 个文件 · 65,109 字符
只检查采集到的受限文本与已知风险模式;未读取的脚本、依赖和运行环境不在结论内。
AI 内容复核
已使用
复核送评文本的说明和设计,不是安装测试或实际任务执行。记录缺失时不推断已使用或未使用。
真实任务效果
本报告未提供实测证据
没有使用/不使用 Skill 的任务对照、重复运行或耗时与 token 成本结果。采用前仍需在隔离环境验证自己的任务。

脚本引用覆盖

脚本引用覆盖记录不可得;不推断没有引用或已经检查。

How it works · 流程图

组件安装流程

README展示从命令到安装组件的步骤

AI 提取 · 证据约束

左右滑动查看完整图示

组件安装流程README展示从命令到安装组件的步骤执行命令获取组件安装配置用户CLI工具组件目录项目配置
图示依据
  • • npx claude-code-templates@latest --agent ...
  • • Browse and install interactively
  • • Install specific components
五维表现
提供丰富的Claude Code组件模板,安装命令清晰,但文档细节不足,设计证据有限。
质量证据
  • 安装命令: npx claude-code-templates@latest --agent ...
  • 组件表格列出Agents, Commands等
  • 文档链接: docs.aitmpl.com
  • 许可证: MIT License
采用建议
优势
  • 问题与用途描述
  • 有效 README
  • 安装或接入步骤
  • 可执行示例
  • 多种组件类型覆盖
关注点
  • 发现系统进程或命令执行能力
  • 缺少错误处理或排障
  • 组件具体内容未详述
  • 配置参数说明不足
  • 错误处理缺失
适合

快速搭建Claude Code环境、寻找现成Agent和命令、集成MCP服务、使用模板管理项目

不建议直接用于

需要深度定制组件的场景、对安全权限有严格要求的场景

也有自己的公开项目?先免登录查已有报告;没有报告时,可保留地址继续登录评测。

查找我项目的报告 →
文档证据
92/100
问题与用途描述10 分
有效 README12 分
安装或接入步骤14 分
可执行示例16 分
输入、参数或工具说明11 分
输出或结果说明9 分
限制、权限或边界12 分
错误处理或排障8 分
许可证信息5 分
结构化章节3 分
安全证据
中风险
发现系统进程或命令执行能力
process-executioncli-tool/components/skills/ai-research/autonomous-agent-patterns/SKILL.md:390high confidence
result = subprocess.run(

修复:限制可执行命令与参数,禁止拼接用户输入,并采用最小权限沙箱。

发现系统进程或命令执行能力
process-executioncli-tool/components/skills/ai-research/computer-use-agents/SKILL.md:299high confidence
subprocess.run(["scrot", "/t***ng"])

修复:限制可执行命令与参数,禁止拼接用户输入,并采用最小权限沙箱。

优先改进清单
  1. 01限制可执行命令与参数,禁止拼接用户输入,并采用最小权限沙箱。
  2. 02补充错误处理或排障
方法、证据与局限展开
数据来源

GitHub Repository API

扫描范围

10 个文件 · 65,109 字符

评测引擎

v3.10.0 · AI 内容复核:已使用(deepseek-chat)

局限
  • 静态评测不会安装或执行项目代码
  • 安全扫描基于高信号文件与已知模式,不能替代人工审计
  • 流行度只反映采用程度,不代表安全或工程质量

30 天热度趋势

README

npm version npm downloads License: MIT PRs Welcome Sponsored by Z.AI Claude for Open Source Neon Open Source Program GitHub Sponsors Buy Me A Coffee GitHub stars

davila7%2Fclaude-code-templates | Trendshift

Vercel OSS Program    Neon Open Source Program    Claude for Open Source


Swiftproxy

Sponsored by Swiftproxy

Swiftproxy proudly supports this project.
Connect your AI-powered workflows to reliable residential proxies for web data collection, browser automation, and AI-driven research.
90M+ residential IPs across 220+ locations, rotating and static residential proxies, with HTTP(S) and SOCKS5 support.

Get 10% off with code PROXY90


Claude Code Templates (aitmpl.com)

Ready-to-use configurations for Anthropic's Claude Code. An open catalog of about 1,900 components (skills, agents, slash commands, MCP integrations, settings, hooks, mods, loops, sandboxes and project templates), installable with one command.

Browse & Install Components and Templates

Browse all components: search the catalog, preview every file a component writes, and combine several components into a single install command.

The aitmpl.com component catalog

🚀 Quick Installation

# Install a complete development stack
npx claude-code-templates@latest --agent development-team/frontend-developer --command testing/generate-tests --mcp integration/github-integration --yes

# Browse and install interactively
npx claude-code-templates@latest

# Install specific components
npx claude-code-templates@latest --skill creative-design/frontend-design --yes
npx claude-code-templates@latest --agent development-tools/code-reviewer --yes
npx claude-code-templates@latest --command performance/optimize-bundle-size --yes
npx claude-code-templates@latest --setting mcp/mcp-timeouts --yes
npx claude-code-templates@latest --hook git/conventional-commits --yes
npx claude-code-templates@latest --mcp database/postgresql-integration --yes
npx claude-code-templates@latest --mod security/secret-redactor --yes
npx claude-code-templates@latest --loop engineering/docs-sweep-loop --yes  # also installs the components the loop uses

What You Get

ComponentDescriptionExamples
🎨 Skills (890+)Reusable capabilities with progressive disclosurePDF processing, frontend design, code review
🤖 Agents (420+)AI specialists for specific domainsSecurity auditor, frontend developer, database architect
⚡ Commands (280+)Custom slash commands/generate-tests, /optimize-bundle-size, /security-audit
🔌 MCPs (100+)External service integrationsGitHub, PostgreSQL, Stripe, Supabase, Sentry
⚙️ Settings (75+)Claude Code configurationsTimeouts, permissions, status lines
🪝 Hooks (60+)Automation triggersConventional commits, blocking direct pushes
🧩 Mods (45+)Plugins that change Claude Code's own interface and behavior (Claude Code 2.1.287+)Secret redaction, protected paths, terminal games
🔁 Loops (18)Autonomous workflows with a goal, an interval and a stop conditionDocs sweep, build-test-fix, adversarial review
📦 Sandboxes (11)Launchers that run Claude Code in an isolated environment, kept in cli-tool/components/sandbox/ (the CLI's --sandbox was removed in 1.31.0)E2B, Cloudflare, Docker
🗂️ Templates (14)Complete project configurationsLanguage and framework setups

Current counts are in dashboard/public/counts.json.

🛠️ Additional Tools

Beyond the template catalog, the CLI includes three local tools. The two dashboards listen on 127.0.0.1 only and answer only to localhost, because they serve your conversation history.

📊 Claude Code Analytics

Monitor your Claude Code sessions in real time with live state detection and usage metrics, at http://localhost:3333.

npx claude-code-templates@latest --analytics

💬 Conversation Browser

Read and search your Claude Code conversations in a mobile-friendly web UI, at http://localhost:9876.

npx claude-code-templates@latest --chats

To open it from another device, forward the port over SSH (ssh -L 9876:localhost:9876 <host>); the public --tunnel option was removed in 1.31.0.

🔍 Health Check

Diagnostics for your Claude Code installation and project setup (--health, --check and --verify are aliases).

npx claude-code-templates@latest --health-check

Removed in 1.31.0

--plugins, --skills-manager, --command-stats, --hook-stats, --mcp-stats, --agents, --chats-mobile, --teams, --2025, --studio, --sandbox, --tunnel, --create-agent, --list-agents, --update-agent, --remove-agent and --clone-session were removed. Running one prints what replaced it. To see what is installed in each scope (plugins, skills, commands, hooks, MCPs), use the stack viewer mod: npx claude-code-templates@latest --mod ui/stack-viewer, then /stack in Claude Code. See the CHANGELOG for details.

📖 Documentation

📚 docs.aitmpl.com - Complete guides, examples, and API reference for all components and tools.

Contributing

We welcome contributions! Browse existing templates to see what's available, then check our contributing guidelines to add your own skills, agents, commands, MCPs, settings, hooks or mods. Every pull request is checked by Claude Code's plugin validator and scanned by NVIDIA SkillSpector.

Please read our Code of Conduct before contributing.

Attribution

This collection includes components from multiple sources:

Scientific Skills:

Official Anthropic:

Community Skills & Agents:

  • obra/superpowers by Jesse Obra - MIT License (14 workflow skills)
  • alirezarezvani/claude-skills by Alireza Rezvani - MIT License (36 professional role skills)
  • wshobson/agents by wshobson - MIT License (48 agents)
  • NerdyChefsAI Skills - Community contribution - MIT License (specialized enterprise skills)

Commands & Tools:

Each of these resources retains its original license and attribution, as defined by their respective authors. We respect and credit all original creators for their work and contributions to the Claude ecosystem.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Links

Stargazers over time

Stargazers over time


⭐ Found this useful? Give us a star to support the project!

Sponsor on GitHub

Buy Me A Coffee