| name | agent-creator |
| description | Create, configure, and orchestrate Claude Code subagents — specialized Claude instances with focused roles and limited tool access. Covers YAML frontmatter (name, description, tools, model, permissions, hooks, MCP servers), system prompt design, tool restriction patterns, background execution, and multi-agent orchestration. Use whenever the user mentions subagents, delegation, specialists, agent configs, `.claude/agents/`, the `/agents` command, or wants to parallelize work — even when they just say "background agent" or "delegate this". |
| when_to_use | When the user wants to create, edit, configure, or orchestrate a Claude Code subagent. Keywords — subagent, agent, delegate, specialist, `/agents`, `.claude/agents/`, agent config, background agent, parallel agents, orchestration, multi-agent workflow. Also trigger when the user asks how subagents work, which tools/models to choose, or how to restrict agent permissions. Skip when the user is working on a non-delegating skill or an API-level tool that has no subagent primitive. |
| license | MIT |
| compatibility | Optimized for Claude Code; degrades gracefully on any agent implementing the Agent Skills standard. |
| metadata | {"author":"coroboros","sources":["code.claude.com/docs/en/sub-agents","github.com/Melvynx/aiblueprint"]} |
Agent Creator
Important — Writing rules
These rules govern every prose artifact this skill emits — READMEs, CHANGELOGs, commit messages, PR bodies, release notes, doc paragraphs, non-trivial comments. Apply them at draft time, verify before output.
- Match the surrounding style — punctuation, capitalization, backtick conventions, em-dash vs parens, bullet style.
- Every sentence changes the reader's understanding. Cut it otherwise.
- Front-load the verb — "Creates", not "This helps you create".
- Concrete over abstract. Lists for ≥3 enumerable items.
- Assert positively. Reserve negation for real constraints (
NEVER commit secrets).
- No marketing words: powerful, robust, seamlessly, leverage, unlock, comprehensive, delightful.
- No AI tells: delve, tapestry, intricate, pivotal, testament, underscore, crucial, garner, showcase, additionally, moreover, furthermore, indeed.
- After drafting English prose, invoke
/humanize-en if installed.
Subagents are specialized Claude instances that run in isolated contexts with focused roles and limited tool access. This skill covers how to create effective subagents, write strong system prompts, configure tool access, and orchestrate multi-agent workflows.
Subagents enable delegation of complex tasks to specialized agents that operate autonomously without user interaction, returning their final output to the main conversation.
Capture Intent
Before drafting an agent, surface the four contract questions. If the user's spec is vague, ask these via AskUserQuestion rather than fabricating answers:
- What should this agent do? — the specific task and role (e.g., "review TypeScript PRs for security regressions"), not a generic description.
- When should it be invoked? — trigger conditions, keywords, file patterns. Goes into the
description field for routing.
- Which tools does it need? — least-privilege allowlist. Read-only analysis vs write-capable.
- What's the expected output format? — structured report, file edits, list of findings, etc.
The description field carries triggers; the system prompt body carries workflow + output format. Both are derived from these answers.
Quick Start
- Run
/agents command
- Select "Create New Agent"
- Choose project-level (
.claude/agents/) or user-level (~/.claude/agents/)
- Define the agent:
