agentleFS
pobstetapobsteta/aigora/.claude/skills/business-setup/SKILL.md

business-setup

Skill0 starsChanged 46 days agoMITView on GitHub

Initial business configuration wizard. Runs on first use to configure the AIGORA for your specific business. Use when context/my-business.md is empty, user says "set up my business", "configure", "initialize", or "start fresh".

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Run the phases below conversationally — ask a batch of questions, wait for answers, then move to the next phase.

    line 19
  2. Distinctive:

    Ask these questions (one batch):

    line 23
  3. Distinctive:

    Do you create content? If so, what platforms?

    line 47
  4. Very specific:

    Do you use kSuite (Infomaniak) for mail, calendar, kDrive or kChat?

    line 49
  5. Distinctive:

    After collecting all answers:

    line 62
  6. Very specific:

    Use scripts/init_business.py for writing the context files in a consistent format.

    line 91
  7. Distinctive:

    If user wants to skip a phase, that's fine — write what you have

    line 95
  8. Distinctive:

    If user gives very short answers, ask one follow-up for the most critical info

    line 96
  9. Very specific:

    If reconfiguring, back up existing files to .tmp/ before overwriting

    line 97
  10. Distinctive:

    If user pastes a very long voice sample, extract the key patterns (don't store the full text)

    line 98

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Business Setup Wizard

Configure the entire AIGORA for a specific business through a conversational questionnaire.

When to Trigger

  • context/my-business.md contains placeholder text
  • User says "set up my business", "configure", "initialize", or "start fresh"
  • User wants to reconfigure from scratch

Process

Run the phases below conversationally — ask a batch of questions, wait for answers, then move to the next phase. Do NOT dump all questions at once.

Phase 1: Your Business

Ask these questions (one batch):

  1. What does your business do? (one sentence)
  2. Who are your customers? (industry, size, role they talk to)
  3. What's your main offer? (service/product, rough price range)
  4. Where do most of your leads come from? (referrals, LinkedIn, ads, content, etc.)
  5. What's your biggest business challenge right now?

Phase 2: Your Voice

Ask these questions:

  1. How would you describe your communication style? (e.g., direct and no-BS, warm and approachable, technical and precise)
  2. Paste a message, email, or post you've written that sounds like "you" — something you'd actually send
  3. What words or phrases do you use often?
  4. What tone do you NEVER want to sound like? (e.g., corporate, salesy, overly casual)

Phase 3: Your Tools & Integrations

Ask these questions:

  1. What language would you like me to communicate in? (default: French)
  2. What timezone are you in? (e.g., America/New_York, Europe/London, Asia/Tokyo)
  3. What tools do you use daily? (CRM, email platform, project management, calendar)
  4. Do you create content? If so, what platforms? (LinkedIn, YouTube, blog, newsletter, etc.)
  5. What tasks do you wish were automated?
  6. Do you use kSuite (Infomaniak) for mail, calendar, kDrive or kChat? If yes, offer to connect it now or later with the ksuite-setup skill (docs/KSUITE.md).
  7. (Optional) Do you want the advanced semantic memory? It runs 100% locally (Ollama + Qdrant, no key, nothing leaves the computer) but needs a one-time install. If yes, note the user's preferred name (memory user ID); if no, it's available later, see docs/MEMORY-UPGRADE.md

Phase 4: Your Goals

Ask these questions:

  1. What are your top 3 priorities for the next 90 days?
  2. What does success look like for this quarter?
  3. What tasks drain your energy and you want off your plate?

Phase 5: Auto-Configure

After collecting all answers:

  1. Write context/my-business.md — Structured business profile from Phase 1 answers. Include: business description, target customer, main offer, lead sources, current challenge.
  2. Write context/my-voice.md — Voice guide from Phase 2 answers. Include: communication style description, sample text, characteristic phrases, anti-patterns (what to avoid).
  3. Update config/preferences.yaml — Set language, timezone, content platform preferences, and assistant_name (if provided) from Phase 3.
  4. Capture stable facts to memory. Add the durable facts (user preferences from Phase 3, business facts and goals from Phase 4) to Claude Code's native auto-memory (its project memory folder) and add a short curated line or two to memory/MEMORY.md so the always-loaded index reflects them. Use the Write tool. See .claude/rules/memory-protocol.md for the protocol.
  5. (Optional) Connections and advanced memory — If the user uses kSuite, hand off to ksuite-setup after this wizard. If they want the advanced memory, add MEM0_USER_ID to .env and walk through docs/MEMORY-UPGRADE.md. Otherwise mention both are available later.
  6. Validation test — Write a 2-sentence introduction of the user's business in their voice. Ask: "Does this sound like you?" If not, refine the voice guide.
  7. Print capabilities — Show the user what they can now do:
    You're set up! Here's what you can do now:
    
    - "Research [company/person/topic]" — Deep research on anything
    - "Write a LinkedIn post about [topic]" — Content in your voice
    - "Prep for my meeting with [person]" — Research + talking points
    - "Help with this email: [paste]" — Triage, draft replies
    - "Add a task: [description]" — Track tasks and projects
    - "Weekly review" — Review your week and plan the next
    - "Create a skill for [workflow]" — Build new reusable workflows

Script

Use scripts/init_business.py for writing the context files in a consistent format. Pass collected answers as JSON.

Edge Cases

  • If user wants to skip a phase, that's fine — write what you have
  • If user gives very short answers, ask one follow-up for the most critical info
  • If reconfiguring, back up existing files to .tmp/ before overwriting
  • If user pastes a very long voice sample, extract the key patterns (don't store the full text)

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.