agentleFS
Sign inStart free
youdcodeyoudcode/open-company/.agents/skills/setup/SKILL.md

setup

Skill2 starsChanged 52 days agoMITView on GitHub

First-run interview. Asks the human about their company and ideal customers, then writes workspace/company/profile.md and workspace/prospecting/icp.md (including the scoring rules). Use when the profile says setup pending, or when the human types "setup".

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

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

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the human gives a website, read it first and pre-fill what you can.

    line 11
  2. Distinctive:

    Ask the questions below in 2 or 3 short batches (not one giant list).

    line 12
  3. Very specific:

    Write workspace/company/profile.md from its template: keep the front matter, set name, website, country, language, setup: done, author: …

    line 20
  4. Very specific:

    Write workspace/prospecting/icp.md (author: strategist): segments, buyer roles, signals, and the scoring JSON block.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 171 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

Setup

Goal: in about 5 minutes of the human's time, know enough to prospect without asking again.

  1. node tools/init.mjs then node tools/log.mjs director "Setting up the company".
  2. If the human gives a website, read it first and pre-fill what you can. Show what you understood.
  3. Ask the questions below in 2 or 3 short batches (not one giant list). Skip what the website answered.
    • Company name, website, country, language for client messages.
    • What you sell, in one sentence, and the price range.
    • Who buys it: industry, company size, place, the job title of the buyer.
    • What problem it solves for them, and what they use today instead.
    • Proof you are allowed to use (real clients, numbers, awards). "None yet" is a fine answer.
    • Tone (formal, friendly, direct) and anything we must never say.
    • Which events make a company likely to buy now (hiring, funding, new manager, expansion...).
  4. Write workspace/company/profile.md from its template: keep the front matter, set name, website, country, language, setup: done, author: director, updated. Proof section: only what the human confirmed.
  5. Write workspace/prospecting/icp.md (author: strategist): segments, buyer roles, signals, and the scoring JSON block. Adapt industries.match (keywords and, for France, NAF codes like 62.01Z), size, geography and signal weights to the answers. Keep it valid JSON. Keep the sum of the fit weights below threshold.hot, so "hot" always needs a fresh signal.
  6. Board: add 3 starter tasks, for example prospect 10 in <segment> (@researcher), qualify new leads (@researcher), draft first messages (@sales).
  7. Journal: one dated line with the main choices. Log node tools/log.mjs director "Company set up".
  8. Tell the human in 4 lines what you understood and suggest the next command: prospect 10.

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