agentleFS
elvismuslielvismusli/business-validator/skills/idea-intake/SKILL.md

idea-intake

Skill1 starsChanged 9 months agoMITView on GitHub

Use when a user wants to validate a business idea — collects all required information through interactive questions and generates a run_id before research begins

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. DITlieD/ELAI-archive★ 24same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Do NOT proceed to market research, competitor analysis, or any other analysis skill until the business brief is complete and saved.

    line 15
  2. Very specific:

    Ask questions ONE AT A TIME via AskUserQuestion.

    line 30
  3. Distinctive:

    Ask for a short name (2-4 words) and a 1-2 sentence description

    line 60
  4. Distinctive:

    Follow up: estimated willingness to pay

    line 70
  5. Distinctive:

    Ask if the user already knows any competitors

    line 83
  6. Distinctive:

    Ask for confirmation that everything looks correct

    line 131
  7. Very specific:

    Create the report directory: docs/reports/<run_id>/

    line 132

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 Idea Intake

Overview

Collect all information needed to validate a business idea through a structured series of questions. The output is a business brief saved to docs/business-briefs/<run_id>.md where run_id is generated as YYYY-MM-DD-<slug>-<hhmm>.

<HARD-GATE> The brainstorming skill MUST have been completed before this skill runs. If there is no evidence of a completed brainstorming session in the conversation, STOP and tell the user to run brainstorming first. Do NOT invoke brainstorming from here — the commands and pipeline handle ordering.

Do NOT proceed to market research, competitor analysis, or any other analysis skill until the business brief is complete and saved. Every field in the brief must be filled. The run_id must be generated and communicated to the user. </HARD-GATE>

Run ID Generation

Generate the run_id as: YYYY-MM-DD-<slug>-<hhmm> where:

  • YYYY-MM-DD is today's date
  • <slug> is the idea name lowercased, spaces replaced with hyphens, max 30 chars
  • <hhmm> is the current time in hours and minutes (24h format) to ensure uniqueness
  • Example: 2026-02-19-ai-tutor-platform-1435

The run_id is used by ALL subsequent skills. Pass it explicitly when invoking them.

Process

Ask questions ONE AT A TIME via AskUserQuestion. Use multiple-choice options where possible.

digraph intake {
    "Ask idea name and description" [shape=box];
    "Ask problem being solved" [shape=box];
    "Ask target audience" [shape=box];
    "Ask business model" [shape=box];
    "Ask geographic focus" [shape=box];
    "Ask budget range" [shape=box];
    "Ask known competitors" [shape=box];
    "Generate run_id" [shape=box, style=filled, fillcolor="#fff3e0"];
    "Save business brief" [shape=box, style=filled, fillcolor="#e8f5e9"];
    "Invoke next skills" [shape=doublecircle];

    "Ask idea name and description" -> "Ask problem being solved";
    "Ask problem being solved" -> "Ask target audience";
    "Ask target audience" -> "Ask business model";
    "Ask business model" -> "Ask geographic focus";
    "Ask geographic focus" -> "Ask budget range";
    "Ask budget range" -> "Ask known competitors";
    "Ask known competitors" -> "Generate run_id";
    "Generate run_id" -> "Save business brief";
    "Save business brief" -> "Invoke next skills";
}

Questions to Ask

1. Idea Name and Description

  • Ask for a short name (2-4 words) and a 1-2 sentence description
  • Open-ended question

2. Problem Being Solved

  • What specific problem or pain point does this solve?
  • Open-ended question

3. Target Audience

  • Who is the primary customer?
  • Options: B2B (Small Business), B2B (Enterprise), B2C (Mass Market), B2C (Niche/Premium), B2B2C, Other
  • Follow up: estimated willingness to pay

4. Business Model

  • How will this make money?
  • Options: SaaS/Subscription, One-time Purchase, Freemium, Marketplace/Commission, Advertising, Services/Consulting, Other

5. Geographic Focus

  • Options: Local/City, National, Regional (e.g. Europe, MENA), Global, Online-only (no geo limit)

6. Starting Budget

  • Options: Bootstrapped (less than $5K), Seed ($5K-$50K), Pre-seed ($50K-$500K), Series A+ ($500K+), Not yet determined

7. Known Competitors

  • Ask if the user already knows any competitors
  • Open-ended (can be "none" or a list)

Business Brief Template

Save to docs/business-briefs/<run_id>.md:

# Business Brief: [Idea Name]

**Run ID:** <run_id>
**Date:** YYYY-MM-DD
**Status:** Ready for Analysis

## Idea
**Name:** [name]
**Description:** [1-2 sentences]

## Problem
[What problem does this solve]

## Target Audience
**Segment:** [B2B/B2C/etc.]
**Customer Profile:** [description]
**Willingness to Pay:** [estimate]

## Business Model
**Type:** [subscription/etc.]
**Details:** [additional context]

## Market
**Geographic Focus:** [scope]
**Starting Budget:** [range]

## Known Competitors
[List or "None identified"]

## Analysis Queue
- [ ] Market Research
- [ ] Competitor Analysis
- [ ] Financial Model
- [ ] Risk Assessment
- [ ] Final Report

After Saving the Brief

  1. Show the user a summary of the brief and the run_id
  2. Ask for confirmation that everything looks correct
  3. Create the report directory: docs/reports/<run_id>/
  4. Dispatch business-validator:market-research and business-validator:competitor-analysis in parallel using the Task tool with subagents, passing the run_id to both

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.