agentleFS
Sign inStart free
fxmartinfxmartin/claude-code-config/skills/create-agent/SKILL.md

create-agent

Skill2 starsChanged 12 days agoMITView on GitHub

Use when you want to create a new sub-agent that Claude can delegate tasks to. Generates an agents/<name>.md definition.

38 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use deploy-platform, setup-platform and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agno-agiSkill

    deploy-platform

    Deploy this AgentOS using its own provider instructions, configure JWT verification, and verify the public service. Use for first deployment, redeployment, or production configuration changes.

    Also in 5 projects that use this

  • agno-agiSkill

    setup-platform

    Set up this AgentOS from a fresh clone — confirm Docker, configure .env, boot the containers, prove the MCP endpoint live, connect the AgentOS UI, then build the user's first agent. Use when the user asks to set up the platform, get started, or bring this repo up on a new machine.

    Also in 5 projects that use this

  • ElasticSkill

    create-integration

    Use when creating a new Elastic integration package, scaffolding data streams, answering package layout or structure questions, or running the end-to-end integration build workflow. Covers package topology, scaffold commands, post-scaffold edits, and full orchestration of CEL/pipeline/test subagents.

    Also in 3 projects that use this

  • MicrosoftSkill

    create-hook

    Create a hook (.json) to enforce policy or automate agent lifecycle events.

    Also in 5 projects that use this

  • AnasX7Skill

    improve

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

    Also in 5 projects that use this

  • SentrySkill

    create-pr

    Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.

    Also in 3 projects that use this

  • +3 more from agno-agi

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After gathering requirements (or parsing arguments), ask:

    line 37
  2. Very specific:

    Read the shared template: ${CLAUDE_SKILL_DIR}/../../templates/agent-template.md

    line 44
  3. Distinctive:

    Read 2-3 existing agents for style matching (pick ones closest to the target domain)

    line 45
  4. Very specific:

    Critical: ensure the description field includes <example> blocks for reliable auto-delegation

    line 47
  5. Distinctive:

    Ask: "Approve, edit, or cancel?"

    line 49
  6. Very specific:

    Always include at least one <example> block in the description

    line 57
  7. Distinctive:

    Keep the agent focused on a single domain

    line 61

“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are an agent generator for Claude Code. You create well-structured agent definitions with proper frontmatter, delegation descriptions, and domain-specific instructions.

Mode Detection

Detect the invocation mode from $ARGUMENTS:

Scaffold mode — $ARGUMENTS starts with --scaffold: → Read ${CLAUDE_SKILL_DIR}/generation-rules.md for scaffold instructions → Generate minimal agent file with TODO placeholders → If text follows --scaffold, use it as the agent name/description

Direct mode — $ARGUMENTS is provided (no --scaffold): → Read ${CLAUDE_SKILL_DIR}/generation-rules.md for full generation instructions → Use ultrathink to generate a complete agent definition from the description

Interactive mode — No $ARGUMENTS: → Read ${CLAUDE_SKILL_DIR}/interactive-questions.md for the Q&A flow → Ask questions one at a time to gather requirements → Then proceed to generation

Context

Existing agents: !ls ${CLAUDE_SKILL_DIR}/../../agents/

Install Location

After gathering requirements (or parsing arguments), ask:

Install globally (this config repo) or locally (current project's .claude/)?

  • Global: writes to ${CLAUDE_SKILL_DIR}/../../agents/
  • Local: writes to .claude/agents/

Generation Flow

  1. Read the shared template: ${CLAUDE_SKILL_DIR}/../../templates/agent-template.md
  2. Read 2-3 existing agents for style matching (pick ones closest to the target domain)
  3. Generate the agent definition with proper frontmatter and body
  4. Critical: ensure the description field includes <example> blocks for reliable auto-delegation
  5. Display the complete generated file content for review
  6. Ask: "Approve, edit, or cancel?"
  7. On approve: write the file to the chosen location, confirm the path
  8. On edit: ask what to change, regenerate, and display again
  9. On cancel: abort without writing

Important Rules

  • The description field is the most important part — it controls auto-delegation
  • Always include at least one <example> block in the description
  • Choose the minimal tool set needed for the agent's purpose
  • Select a color that doesn't conflict with existing agents
  • Body must follow: # Purpose → ## Instructions (numbered) → ## Best Practices → ## Report / Response
  • Keep the agent focused on a single domain

$ARGUMENTS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free