agentleFS
the-abraham-brandthe-abraham-brand/my-business-brain/skills/setup/SKILL.md

setup

Skill0 starsChanged 51 days agoMITView on GitHub

My Business Brain setup. Creates the business knowledge bank (the brain folder, its profile, system files and index) in a folder the user chooses, then offers to load the first documents. Use when the user runs /my-business-brain:setup, or asks to set up, start or create their business brain or business knowledge base.

192 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, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 1

    Distinctive

    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. Distinctive:

    Create the brain and get the first knowledge into it.

    line 8
  2. Very specific:

    Run scripts/brain_index.py and scripts/brain_health.py on the new brain (from the core skill folder).

    line 22
  3. Very specific:

    If a pack was applied, work through _system/pack-questions.md with the owner: a few questions at a time, each answer becomes an entry.

    line 23
  4. Very specific:

    After the first load, propose 5 to 10 golden questions the business relies on (headline prices, refund and payment terms, key contract …

    line 26

“Common” is measured: kept by at least 6 in 10 of the 169 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

/my-business-brain:setup

Create the brain and get the first knowledge into it.

  1. Load the my-business-brain skill from this plugin (via the Skill tool). If it cannot be loaded, read ../my-business-brain/SKILL.md and ../my-business-brain/references/knowledge-model.md directly.
  2. Choose the folder. Use the folder the user names or has connected. If a BRAIN.md already exists there, stop and say the brain is already set up; offer a health check instead. With no writable folder, explain that the brain needs a folder (in the desktop app, a connected folder) and offer to build the files for them to save.
  3. Read the plugin settings first (brain folder ${user_config.brain_folder}, calendar ${user_config.calendar}, currency ${user_config.currency}, time zone ${user_config.timezone}, weekend ${user_config.weekend}, capture mode ${user_config.capture_mode}); tell the user they can change them any time in the plugin's settings. Then ask in one message only for what is still unknown: business name and what it does; where it operates (country, city) and its currency; the owner or main contact; how the brain should capture facts from conversation (ask first, or remember automatically). Also ask which calendar they use (Google, Outlook, Apple, or another), for Contract Clocks. Offer an industry pack if the business fits one (scripts/pack.py list: clinic, agency or consultancy, trading, law firm, real estate, restaurant). Applying it (pack.py apply <brain> <id>) files facts in the right areas, marks trade-specific details confidential, adds decision types for that trade and a list of starting questions. If none fits, offer to build one with the owner (references/industry-packs.md). Ask which language they want journals and reports in if the setting is empty.
  4. Create the structure from knowledge-model.md: business-brain/ with entries/<domain>/ for the starting domains, contracts/calendar/, analytics/, sources/, _system/archive/.
  5. Give the brain its identity. Ask the owner what to call their Chief of Staff (suggest a name or two, or keep "Chief of Staff"), and confirm the defaults in one line: it prepares and delegates; anything that sends, pays, books, promises or changes a fact waits for the owner's yes. Once the starting files below are written, run scripts/identity.py <brain> init --name "..." --owner "..." --language <english|arabic|both>, and speak as it from then on. Offer people profiles for the key colleagues (scripts/adapter.py <brain> profile add ...).
  6. Write the starting files:
    • BRAIN.md: business profile (name, what it does, location, currency, fiscal year, owner), the domain list, and a short "How this brain works" note (one fact per entry, sources, supersede don't delete, where decisions wait).
    • _system/preferences.md: capture mode, currency, time zone, weekend days, date format, preferred calendar and its reminders (7 days, 3 days, 24 hours).
    • Label the company entries' sensitivity (public for what is published, otherwise internal).
    • Empty _system/changelog.md (with a "Brain created" line), decisions-needed.md, lessons.md, questions.md.
    • Company entries for the profile facts, each with source_type: user-stated and source: <user> (setup, <date>).
  7. Run scripts/brain_index.py and scripts/brain_health.py on the new brain (from the core skill folder). If a pack was applied, work through _system/pack-questions.md with the owner: a few questions at a time, each answer becomes an entry. Then initialise the research toolkit: scripts/toolkit.py <brain> detect (add --probe if Agent Reach is installed). Tell the user in two lines what the brain found it can use (research skills, document converters, Agent Reach, connectors), and that optional helpers are theirs to install; the brain never installs anything.
  8. Suggest the first load, in order of value: price list, contracts, policies and terms, product or service descriptions, key customers and suppliers, SOPs. Offer to process any documents the user attaches right away (/my-business-brain:learn).
  9. After the first load, propose 5 to 10 golden questions the business relies on (headline prices, refund and payment terms, key contract dates, VAT rate) and add the ones the user agrees to with scripts/golden.py add (references/knowledge-regression.md). Save a first snapshot: scripts/brain_diff.py snapshot <brain>, and build the lexicon: scripts/lexicon.py <brain> build.
  10. Offer a watch list for the official pages and supplier prices the brain depends on (scripts/watch.py <brain> add URL ..., references/research-and-watch.md). Then offer four scheduled tasks, created only if the user says yes: the morning brief on working days before the owner's day starts (/my-business-brain:chief), the Sunday evening review (/my-business-brain:review, Sunday evening in their time zone, or the evening before their first working day), a monthly brain review with the next 90 days of contract dates, and the monthly journal.
  11. Tell the user in one line that the brain lives in their folder as plain files, that every change is logged, and that they can back the folder up however they like (references/security-and-privacy.md).

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.