Agent skill · AI & Agents

fercracix33-poli2-clean-architecture-claude-skills-agent-creator

Purpose: Guide creation of Claude Code agents following Anthropic official best practices.'

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill fercracix33-poli2-clean-architecture-claude-skills-agent-creator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 18 KB
Bundled scripts: none
Path: skills/agent/fercracix33-poli2-clean-architecture-claude-skills-agent-creator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

--- name: agent-creator description: Use this skill when architecting new Claude Code agents following Anthropic best practices. Guides through YAML frontmatter creation, agent structure definition, role boundaries, and validation. Critical for creating minimal agent files (~150 lines) with proper skill invocations. Examples: <example>Context: User wants to create a new agent for security auditing user: "Create a security-auditor agent" assistant: "I'll use the agent-creator skill to build this agent following Anthropic best practices" <commentary>New agent creation requires the agent-creator skill to ensure proper structure and YAML frontmatter.</commentary></example> <example>Context: Existing agent file is too verbose and needs refactoring user: "The architect agent is 2000 lines, refactor it to minimal structure" assistant: "I'll use the agent-creator skill to refactor this into a minimal ~150 line agent with a separate skill file" <commentary>Agent refactoring requires the agent-creator skill to separate identity from technical procedures.</commentary></example> color: orange --- # Agent Creator Skill **Purpose**: Guide creation of Claude Code agents following Anthropic offici

What's inside
Steps it walks through
  1. 🎯 Core Principles
  2. Agent Structure Philosophy
  3. Separation of Concerns
  4. 📋 6-PHASE WORKFLOW
  5. PHASE 1: Discovery & Analysis
  6. PHASE 2: Context7 Research (MANDATORY)
  7. PHASE 3: YAML Frontmatter Design
  8. PHASE 4: Agent Body Structure
  9. PHASE 5: Validation & Testing
  10. PHASE 6: Skill Scaffold Creation
  11. 🎯 AUTOMATIC HANDOFF TO SKILL-CREATOR
  12. 🛠️ UTILITIES & HELPERS
  13. Quick Start: New Agent from Scratch
  14. Quick Start: Refactor Existing Agent
Ships with 1 file
  • metadata.json
Commands it runs
Query 1: General agent best practices
mcp__context7__resolve-library-id "claude code"
mcp__context7__get-library-docs "/anthropics/claude-code" topic="custom agents creation best practices"
Query 2: Agent templates and examples
mcp__context7__resolve-library-id "claude code templates"
mcp__context7__get-library-docs "/davila7/claude-code-templates" topic="agent creation yaml structure examples"
Query 3: YAML frontmatter validation (if uncertain)
mcp__context7__get-library-docs "/anthropics/claude-code" topic="yaml frontmatter agent configuration"
Run validation script
More from claude-skill-registry
All skills →
About this skill
What does the fercracix33-poli2-clean-architecture-claude-skills-agent-creator skill do?

Purpose: Guide creation of Claude Code agents following Anthropic official best practices.'

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill fercracix33-poli2-clean-architecture-claude-skills-agent-creator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going