agentleFS
Future-CXFuture-CX/AI-Architecture-Toolkit/skills/create-an-agent/SKILL.md

create-an-agent

Skill8 starsChanged 6 months agoMITView on GitHub

Create repository-local architecture agent definitions from a standard template. Use when the user asks to create, draft, scaffold, or add an agent under the agents folder.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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. Very specific:

    Create agent definitions under agents/ using the preset template in templates/agent-template.md.

    line 10
  2. Distinctive:

    Use the helper script when the requested agent has a clear name, purpose, and responsibilities:

    line 12
  3. Distinctive:

    Do not overwrite an existing agent file unless the user explicitly asks.

    line 30
  4. Very specific:

    Keep the style consistent with the existing files in agents/.

    line 31
  5. Distinctive:

    Update the Agents table in the top-level README.md whenever an agent is created or updated.

    line 32
  6. Very specific:

    Use templates/agent-template.md as the source template for generated agent files.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Create An Agent

Quick Start

Create agent definitions under agents/ using the preset template in templates/agent-template.md.

Use the helper script when the requested agent has a clear name, purpose, and responsibilities:

python3 skills/create-an-agent/scripts/create-agent.py "Data Architect" \
  --purpose "Support data architecture decisions across platforms, ownership, quality, and governance." \
  --responsibility "Clarify data ownership, domains, and critical data flows." \
  --responsibility "Assess data quality, privacy, retention, and lineage needs." \
  --responsibility "Review analytics, integration, and operational data implications."

This creates agents/data-architect-agent.md.

Workflow

  1. Determine the agent name and convert it to <slug>-agent.md.
  2. Capture a one-sentence purpose.
  3. Capture 3-7 concrete responsibilities.
  4. Generate the file under agents/ using the preset template.
  5. Do not overwrite an existing agent file unless the user explicitly asks.
  6. Keep the style consistent with the existing files in agents/.
  7. Update the Agents table in the top-level README.md whenever an agent is created or updated.

Output Standard

Each agent file must use this structure:

# Agent Name

## Purpose

One-sentence purpose.

## Recommended Model

Use a frontier reasoning model for complex architecture decisions, tradeoff analysis, and review preparation. Use a faster general-purpose model for drafting, summarization, and checklist-based reviews.

## Responsibilities

- Responsibility one.
- Responsibility two.
- Responsibility three.

Template

Use templates/agent-template.md as the source template for generated agent files.

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.