Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

claude-agentsClaude Agent 搜索

Agent Skill

claude-agents 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

235

周安装

10

GitHub Stars

17

下载量

82
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:claude-agents(Claude Agent 搜索)
来源仓库:https://github.com/vinnie357/claude-skills
仓库路径:skills/claude-agents
安装命令:
npx skills add https://github.com/vinnie357/claude-skills --skill claude-agents
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/vinnie357/claude-skills --skill claude-agents

简介

用于查找、检索和筛选相关信息,适配多种宿主环境。

  • 支持基于关键词或任务场景快速定位内容。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。
  • 通过 npx skills add 命令从 GitHub 仓库安装使用。
  • 安装前应确认权限及是否触发联网或文件操作。
  • claude-agents 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Claude Code Agents

Guide for creating custom agents that provide specialized behaviors and tool access for specific tasks.

When to Use This Skill

Activate this skill when:

  • Creating custom agent types for specific workflows
  • Defining agent behaviors and tool permissions
  • Configuring agent capabilities
  • Understanding agent vs skill differences
  • Implementing domain-specific agents

What Are Agents?

Agents are specialized Claude instances with:

  • Specific tool access: Limited or specialized tool sets
  • Defined behaviors: Pre-configured instructions and constraints
  • Task focus: Optimized for particular workflows
  • Autonomous operation: Can execute multi-step tasks independently

Agents vs Skills

FeatureAgentsSkills
ActivationExplicitly launched via Task toolAuto-activated based on context
Tool AccessConfigurable, can be restrictedInherit from parent context
StateIndependent, isolatedShare parent context
Use CaseComplex multi-step tasksKnowledge and guidelines
PersistenceSingle executionAlways available when loaded

Agent File Structure

Location

Agents are defined in markdown files located in:

  • Plugin: <plugin-root>/agents/
  • User-level: .claude/agents/

File Naming

  • Use kebab-case: code-reviewer.md
  • File name becomes the agent type
  • Be descriptive about the agent's purpose

Basic Agent Format

---
name: code-reviewer
description: Reviews code for quality and best practices
tools: Read, Grep, Glob
model: sonnet
---

You are a code reviewer. Analyze code for quality, security, and best practices.

## Workflow

1. **Find files**: Glob to locate target files
2. **Read code**: Examine contents
3. **Check patterns**: Grep for anti-patterns
4. **Report**: Provide prioritized feedback

## Guidelines

- **Specific**: Reference file:line locations
- **Actionable**: Suggest concrete fixes
- **Prioritized**: Critical issues first

Agent Writing Style

Effective agents use direct, imperative language:

Opening Statement

  • Do: "You are a [role]. Your role is to [primary function]."
  • Don't: "I am a specialized [role] focused on..."

Workflow Steps

  • Do: Numbered steps with specific commands
  • Don't: Bullet lists describing capabilities

Guidelines Section

  • Do: Single-word bold labels with brief explanations
  • Don't: Verbose explanations of best practices

Agent Configuration

YAML Frontmatter

Required and optional fields:

---
name: agent-name                    # Required: kebab-case identifier
description: Brief description      # Required: What this agent does
tools:                             # Optional: Tool allowlist
  - Read
  - Write
  - Bash
model: sonnet                      # Optional: Model to use (sonnet, opus, haiku)
max_iterations: 10                 # Optional: Maximum task iterations
timeout: 300                       # Optional: Timeout in seconds
---

Tool Allowlist

Restrict agent to specific tools:

  • Can read files
  • Can search code
  • Can find files
  • Cannot use Write, Edit, Bash, etc.

Example:

---
tools: Read, Grep, Glob
---

No tool restrictions (access to all tools):

---
# Omit tools field entirely
---

Model Selection

Choose appropriate model for the task:

---
model: haiku        # Fast, cost-effective for simple tasks
# model: sonnet     # Balanced (default)
# model: opus       # Most capable for complex tasks
---

Common Agent Patterns

Read-Only Analysis Agent

For security scans, code reviews, or audits. Restricted to Read, Grep, Glob.

See: templates/read-only-analyzer.md

Write-Capable Agent

For generating tests, documentation, or code. Includes Write tool.

See: templates/write-capable-agent.md

Full-Access Agent

For refactoring, migrations, or complex modifications. Omit tools field entirely for no restrictions.

See: templates/full-access-agent.md

MCP-Enabled Agent

For browser automation, external APIs, or specialized MCP server tools. Mix core tools with MCP tools.

See: templates/mcp-agent.md

Agent Plugin Configuration

In plugin.json

{
  "agents": [
    "./agents/code-reviewer.md",
    "./agents/test-generator.md",
    "./agents/security-analyzer.md"
  ]
}

Directory-Based Loading

{
  "agents": "./agents"
}

Loads all .md files in agents/ directory.

Invoking Agents

Agents are launched via the Task tool:

# In parent Claude conversation
Task(
    subagent_type="code-reviewer",
    description="Review authentication module",
    prompt="""
    Review the authentication module for:
    - Security vulnerabilities
    - Error handling
    - Input validation
    - Best practices
    """
)

Agent Communication

Input to Agent

  • Task description
  • Detailed prompt
  • Access to conversation history (if configured)

Output from Agent

  • Final report/result
  • No ongoing dialogue
  • One-time execution

Best Practices

Clear Purpose

Each agent should have a specific, well-defined purpose:

---
name: migration-helper
description: Assists with database schema migrations
---

# Database Migration Agent

Specialized in creating and validating database migrations.

Appropriate Tool Access

Only grant necessary tools:

---
# Analysis agent - read-only
tools: Read, Grep, Glob
---
---
# Implementation agent - can modify
tools: Read, Write, Edit, Glob, Grep
---

Model Selection

Match model to task complexity:

  • haiku: Simple, repetitive tasks
  • sonnet: Standard tasks (default)
  • opus: Complex reasoning required

Iteration Limits

Set appropriate limits for task complexity:

---
max_iterations: 5   # Simple, focused task
# max_iterations: 20  # Complex, multi-step workflow
---

Clear Instructions

Provide explicit behavior guidelines:

# Testing Agent

## Mandatory Requirements

- Generate tests for ALL public methods
- Achieve minimum 80% code coverage
- Include edge cases and error scenarios
- Use project's testing framework conventions

## Constraints

- Do not modify source code
- Follow existing test file naming patterns
- Use appropriate assertions

Security Considerations

Tool Restrictions

Limit dangerous operations:

---
# Don't give Bash access to untrusted agents
tools:
  - Read
  - Write  # Safer than arbitrary shell commands
---

Input Validation

Validate agent inputs:

# Deployment Agent

Before deploying:
1. Verify target environment is valid
2. Check deployment permissions
3. Validate configuration
4. Confirm destructive operations

Sensitive Data

Never hardcode:

  • Credentials
  • API keys
  • Private URLs
  • Access tokens

Agent Examples

For complete, production-ready agent templates:

  • templates/basic-agent.md - Official minimal example
  • templates/read-only-analyzer.md - Security analyzer pattern
  • templates/write-capable-agent.md - Test generator pattern
  • templates/full-access-agent.md - Refactoring pattern (no tool restrictions)
  • templates/mcp-agent.md - Browser testing with MCP tools

Troubleshooting

Agent Not Found

  • Verify agent file location matches plugin.json
  • Check file naming (kebab-case,.md extension)
  • Ensure plugin is properly installed

Tool Access Denied

  • Check tools allowlist in frontmatter
  • Verify tool names match exactly
  • Ensure parent context permits delegation

Unexpected Behavior

  • Review agent instructions for clarity
  • Check model selection appropriateness
  • Verify iteration limits aren't too restrictive
  • Test with verbose output

References

Templates directory:

  • templates/basic-agent.md - Official minimal example
  • templates/read-only-analyzer.md - Security analysis pattern
  • templates/write-capable-agent.md - Test generation pattern
  • templates/full-access-agent.md - Refactoring pattern (no tool restrictions)
  • templates/mcp-agent.md - MCP tools pattern (browser automation)

Documentation:

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.47%
按下载量换算30

Claude

29.27%
按下载量换算24

Cursor

16.62%
按下载量换算14

Gemini CLI

8.78%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills