agentleFS
InfiniteRoomLabsInfiniteRoomLabs/agent-ops/skills/new-agent/SKILL.md

new-agent

Skill0 starsChanged 5 months agoMITView on GitHub

Use when creating a new agent, skill, or command in the agent-ops marketplace

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill when someone needs to create a new agent, skill, or command in the agent-ops marketplace.

    line 13
  2. Distinctive:

    Ask which division it belongs in: core, engineering, design, marketing, sales, paid-media, product, project-management, testing, support, …

    line 17
  3. Distinctive:

    Ask what type: agent, skill, or command

    line 18
  4. Distinctive:

    Ask for a name (kebab-case) and brief description

    line 19

“Common” is measured: kept by at least 6 in 10 of the 5 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

Create New Agent/Skill/Command

Use this skill when someone needs to create a new agent, skill, or command in the agent-ops marketplace.

Process

  1. Ask which division it belongs in: core, engineering, design, marketing, sales, paid-media, product, project-management, testing, support, research, spatial-computing, game-development, specialized
  2. Ask what type: agent, skill, or command
  3. Ask for a name (kebab-case) and brief description
  4. Ask for tags:
    • function: business functions that use this (engineering, operations, finance, research, executive)
    • scenario: workflows where this applies (e.g., domain-onboarding, vendor-evaluation)
    • custom: freeform labels
  5. Scaffold the component using the templates below

Agent Template

Create agents/{division}/{name}.md:

---
description: {description}
tags:
  function: [{functions}]
  scenario: [{scenarios}]
  custom: [{custom}]
---

{System prompt and instructions}

Skill Template

Create skills/{name}/SKILL.md:

---
name: {name}
description: {description}
tags:
  function: [{functions}]
  scenario: [{scenarios}]
  custom: [{custom}]
---

{Skill instructions}

Command Template

Create commands/{name}.md:

---
name: {name}
description: {description}
tags:
  function: [{functions}]
  scenario: [{scenarios}]
  custom: [{custom}]
---

{Command instructions}

After Scaffolding

Remind the user to update registry.yaml at the repo root if it exists.

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.

Reviews can't be read right now.

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.