agentleFS
mategogmategog/dev-team/skills/setup/SKILL.md

setup

Skill2 starsChanged 7 days agoMITView on GitHub

Set up the dev-team for this project — interview the owner and write company/profile.md, which every dev-team agent reads first.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    If company/profile.md exists, show it and ask what to change instead of starting over.

    line 10
  2. Very specific:

    Look around first so you only ask what you can't find: README, CLAUDE.md, package.json / Cargo.toml / pyproject, existing design tokens or …

    line 11
  3. Distinctive:

    Ask the owner (AskUserQuestion, at most 4 questions per round, two rounds max) only what's still unknown:

    line 12
  4. Distinctive:

    Should the owner approve each design before code is written?

    line 17
  5. Very specific:

    Write company/profile.md with these sections, filling in what you found and heard, and marking guesses [unconfirmed]:

    line 18
  6. Very specific:

    Create an empty company/decisions.md with a header line (# Decisions — date · decision · why) and an empty company/briefs/ folder.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 168 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

/dev-team:setup

  1. Work only in the current project's root (the folder this command was run in). Never edit a parent project's company/.
  2. If company/profile.md exists, show it and ask what to change instead of starting over.
  3. Look around first so you only ask what you can't find: README, CLAUDE.md, package.json / Cargo.toml / pyproject, existing design tokens or design-system skills, brand files.
  4. Ask the owner (AskUserQuestion, at most 4 questions per round, two rounds max) only what's still unknown:
    • What's the product, and who is it for?
    • Brand: name as shown to users, voice, words or claims to avoid.
    • Values or hard rules (e.g. budget limits, no paid tools, privacy rules).
    • Which design-system skill or tokens file is the source of truth, if any.
    • Should the owner approve each design before code is written? (Default yes.)
  5. Write company/profile.md with these sections, filling in what you found and heard, and marking guesses [unconfirmed]:
# Company profile

## Product
What it is, who it's for, the problem it solves.

## Brand
Name as shown to users, byline, voice, words/claims to avoid.

## Values and hard rules
Rules every agent follows (budget, privacy, no hype, ...).

## Stack
Languages, frameworks, how to run, build and test, where the apps live (each repo's folder, relative to this root).

## Design system
Skill name to load (e.g. `my-app-design`) or tokens file path. Fonts, colours, components to reuse.

## Gates
- Owner approves designs before code: yes

## Teams in use
Which dev-team agents this project uses and any project-specific notes for them.
  1. Create an empty company/decisions.md with a header line (# Decisions — date · decision · why) and an empty company/briefs/ folder.
  2. Show the owner the profile in a few lines and the file path.

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.