agentleFS
piotrmechlinskipiotrmechlinski/executive-brain/.claude/skills/setup/SKILL.md

setup

Skill0 starsChanged 24 days agoMITView on GitHub

The first session in a new vault. Ask a few questions, write the first project cards and show Home and the project map within minutes, then offer to fill in people, decisions, risks and dates. Use when the user types /setup, or when "About me" in CLAUDE.md still says "(not set)".

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

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

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read CLAUDE.md. If "About me" is already filled in, ask whether to start again or only add to it.

    line 10
  2. Distinctive:

    Write round one at once:

    line 17
  3. Distinctive:

    Round two,: when they want it, a few questions at a time:

    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

Setup

Two rounds. The first ends with something to look at: Home and the project map. The second is offered, never forced.

  1. Read CLAUDE.md. If "About me" is already filled in, ask whether to start again or only add to it.
  2. Round one. Take what the message with the command already gives, and ask only for the rest, in one message and in the executive's language. Say that a dictated answer is fine.
    • their name, role and organisation;
    • the city they work from, for the time zone;
    • each project they run or own, in one line: a name, who owns it, the next step. Three to seven is usual;
    • one line on their company's rules for AI tools, recordings or what may be written down, or "none I know of".
  3. Write round one at once:
    • "About me" in CLAUDE.md, the company's rules included; in settings.json, title and footer (for example "Alex Morgan · COO · Brightwater" and "Brightwater · internal") and timezone, an IANA name such as "Europe/Warsaw";
    • Meetings/YYYY-MM-DD Setup.md from Templates/Meeting.md, with source: debrief: what they said;
    • one card per project in Projects/ from Templates/Project.md, each with the next ID from python3 tools/vault.py next P, its owner and next step, its goal if they gave one ("not set yet" if not), and a first map of three boxes: today, the next step, the goal, a few words each;
    • each next step as an action in Knowledge/Actions.md, with its owner and its date if it has one, the setup note as its source;
    • README.md replaced with this page, filled in, so that GitHub opens their vault and not the product:

      # <Name>'s vault
      
      Kept by Claude Code. Start at [Home](Home.md): the projects, what is open and what is overdue.
      
      The rules Claude follows are in [CLAUDE.md](CLAUDE.md), the setup in [SETUP.md](SETUP.md). Made with
      [Executive Brain](https://github.com/piotrmechlinski/executive-brain).
    • examples/ removed with git rm -r -q examples, if it is there: it is a fictional vault, and its facts must never be taken for theirs.
  4. python3 tools/vault.py refresh, python3 tools/vault.py check, then python3 tools/build_map.py and copy build/Project map.pdf to Outputs/YYYY-MM-DD Project map.pdf. Commit as Setup, then pull and push main as CLAUDE.md says under "Git".
  5. Show the result in a few lines: the projects as Home lists them, with links to Home.md and the map's PDF on GitHub. Then offer round two: "Shall we add the people, the decisions, the risks and the dates now? Or drop a strategy, an organisation chart or a board pack into Inbox/ and I start from it."
  6. Round two, when they want it, a few questions at a time:

    • the people who matter: name, role, and what they need from the executive;
    • decisions, commitments, risks and dates already known;
    • the language for notes, and anything about style;
    • for each project, the goal in one line and what it is worth, if not given yet.

    File it as CLAUDE.md says under "What goes where", with the setup note as the source. If Inbox/ holds material, file it as /ingest does. Refresh, check, build the map again, commit as Setup: round two, then pull and push main.

  7. Tell them how to work from now on, in four lines: /debrief after a meeting, material into Inbox/ and /ingest, /brief before a meeting, /review once a week.

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.