Skip to main content
claude-agents This skill should be used when creating agents, writing agent frontmatter, configuring subagents, or when "create agent", "agent.md", "subagent", or "Task tool" are mentioned.
Ir a la instalación Skills Marketplace Descubre y explora habilidades de IA creadas por la comunidad.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Mostrar detalles del prompt Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.
npx skills add https://github.com/outfitter-dev/agents --skill claude-agentsEl comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.
¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.
Descargar Zip Descargando... Más de este repositorio gitbutler-complete-branch This skill should be used when the user asks to "complete a branch", "merge to main", "finish my feature", "ship this branch", "integrate to main", "create a PR from GitButler", or when `--complete-branch` flag is mentioned. Guides completion of GitButler virtual branches with safety snapshots, integration workflows, and cleanup.
This skill should be used when coordinating multiple AI agents working concurrently, handling agent handoffs, transferring commits between agents, or when "multi-agent", "concurrent agents", "parallel agents", "agent collaboration", or "parallel execution" are mentioned with GitButler. Provides virtual branch patterns for parallel execution without coordination overhead.
This skill should be used when creating stacks, dependent branches, or when "stack", "stacked branches", "anchor", "--anchor", "but branch new -a", "create dependent branch", or "break feature into PRs" are mentioned with GitButler. Covers anchor-based stacking for dependent features and reviewable PR breakdown.
Explorador de archivos
15 archivos Ocupaciones relacionadas SOC
Basado en la clasificación ocupacional SOC
name claude-agents description This skill should be used when creating agents, writing agent frontmatter, configuring subagents, or when "create agent", "agent.md", "subagent", or "Task tool" are mentioned. metadata {"version":"1.0.0","related-skills":["skills-dev","claude-plugins","claude-hooks"]}
Claude Agent Development
Create and validate specialized subagents that extend Claude Code with focused expertise.
Agents vs Skills
Critical distinction :
Aspect Agents (This Skill) Skills Purpose Specialized subagents with focused expertise Capability packages with instructions Invocation Task tool (subagent_type parameter) Automatic (model-triggered by context) Location agents/ directoryskills/ directoryStructure Single .md file with frontmatter Directory with SKILL.md + resources
See agent-vs-skill.md for details.
Quick Start
Using Templates
Copy a template from templates/:
basic.mdSimple agents with focused expertise advanced.mdFull-featured agents with all config options
Scaffolding ./scripts/scaffold-agent.sh security-reviewer -t reviewer
Workflow Overview
Discovery - Define purpose, scope, and triggersDesign - Choose archetype and configurationImplementation - Write frontmatter and instructionsValidation - Verify against quality standards
Stage 1: Discovery Before writing code, clarify:
Purpose : What specialized expertise does this agent provide?Triggers : What keywords/phrases should invoke it?Scope : What does it do? What does it NOT do?Location : Personal (~/.claude/agents/), project (agents/), or plugin?
Is this a specialized role or a general capability? (Role = agent, Capability = skill)
What user phrases should trigger this agent?
What tools does it need access to?
Stage 2: Design
Agent Archetypes Type Purpose Typical Tools Analyzer Examine without modifying Glob, Grep, Read, Skill, Task, TaskCreate, TaskUpdate, TaskList, TaskGetImplementer Build and modify code Full access (inherit) Reviewer Provide feedback Glob, Grep, Read, Skill, Task, TaskCreate, TaskUpdate, TaskList, TaskGetTester Create and manage tests Glob, Grep, Read, Write, Edit, Bash, ...Researcher Find and synthesize info ..., WebSearch, WebFetchDeployer Handle infrastructure ..., Bash(kubectl *), Bash(docker *)
Frontmatter Schema ---
name: agent-name
description: |
Use this agent when [conditions ]. Triggers on [keywords ].
<example>
Context: [Situation ]
user: "[User message]"
assistant: "I'll use the agent-name agent to [action]."
</example>
model: inherit
tools: Glob, Grep, Read
skills: tdd, debugging
permissionMode: default
---
Model Selection Model When to Use inheritRecommended default - adapts to parent context haikuFast exploration, simple tasks, low-latency sonnetBalanced cost/capability (default if omitted) opusNuanced judgment, security/architecture review, irreversible decisions
Tool Configuration Philosophy : Don't over-restrict. Only limit tools when there's a specific safety reason.
Baseline (always include when restricting):
tools: Glob, Grep, Read, Skill, Task, TaskCreate, TaskUpdate, TaskList, TaskGet
Stage 3: Implementation
Agent File Structure ---
name: security-reviewer
description: |
Use this agent for security vulnerability detection.
Triggers on security audits, OWASP, injection, XSS.
<example > </example > model: inherit
---
# Security Reviewer
You are a security expert specializing in [expertise].
## Expertise
- Domain expertise 1
- Domain expertise 2
## Process
### Step 1: [Stage Name]
- Action item
- Action item
### Step 2: [Stage Name]
- Action item
## Output Format
For each finding:
- **Severity** : critical|high|medium|low
- **Location** : file:line
- **Issue** : Description
- **Remediation** : How to fix
## Constraints
**Always:**
- Required behavior
**Never:**
- Prohibited action
Description Guidelines Descriptions are the most critical field for agent discovery:
Start with trigger conditions : "Use this agent when..."Include 3-5 trigger keywords : specific terms users would sayAdd 2-3 examples : showing user request -> assistant delegationBe specific : avoid vague descriptions like "helps with code"
Best Practices
description: SQL injection vulnerability detector
description: Security expert handling all issues
## What I Don't Do
- I analyze, not implement fixes
- I review, not build from scratch
Define structured output so results are predictable and parseable.
Stage 4: Validation After creating an agent, validate against these checklists.
YAML Frontmatter Checks
Naming Conventions Good : code-reviewer, test-runner, security-auditor
Bad : helper, my-agent, the-best-agent
Description Quality
"Helps with code" - too vague
No trigger conditions
Missing keywords
System Prompt Quality
"You are helpful" - too vague
No process defined
Missing constraints
Scope creep
Tool Configuration
tools: Glob, Grep, Read, Skill, Task, TaskCreate, TaskUpdate, TaskList, TaskGet
tools: Glob, Grep, Read, Skill, Task, TaskCreate, TaskUpdate, TaskList, TaskGet, Bash(git show:*), Bash(git diff:*)
tools: Glob, Grep, Read, Skill, Task, TaskCreate, TaskUpdate, TaskList, TaskGet, WebSearch, WebFetch
Validation Report Format # Agent Validation Report: [Agent Name]
## Summary
- **Status** : PASS | FAIL | WARNINGS
- **Location** : [path]
- **Issues** : [count critical] / [count warnings]
## Critical Issues (must fix)
1. [Issue with specific fix]
## Warnings (should fix)
1. [Issue with specific fix]
## Strengths
- [What's done well]
Agent Scopes Scope Location Priority Visibility Project agents/Highest Team via git Personal ~/.claude/agents/Medium You only Plugin <plugin>/agents/Lowest Plugin users
Project agents override personal agents with the same name.
Testing Agents
Manual Testing
Create agent file in agents/
In Claude Code: "Use the [agent-name] agent to [task]"
Claude invokes via Task tool
Review results
Verify Discovery
~/.claude/agents/ (personal)./agents/ (project)Plugins (installed)
Debug with: claude --debug
Troubleshooting
Agent Not Being Invoked
Check file location: agents/agent-name.md
Validate YAML frontmatter syntax
Make description more specific with trigger keywords
Add example conversations
Wrong Agent Invoked
Make description more distinct
Add specific trigger keywords
Include negative examples (what NOT to use it for)
Agent Has Wrong Tools Prefer model: inherit to use parent's tool access. Only specify tools: when agent needs different access.
References See EXAMPLES.md for complete real-world agent examples.
See templates/ for starter templates.
Related Skills
skills-development : Create Skills (different from agents)claude-plugin-development : Bundle agents into plugins 