agentleFS
Sign inStart free
elvismuslielvismusli/business-validator/skills/using-business-validator/SKILL.md

using-business-validator

Skill1 starsChanged 9 months agoMITView on GitHub

Use when starting a conversation about business ideas, market research, or business validation - establishes available business validation skills

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Every validation session has a run_id in the format YYYY-MM-DD-<slug>-<hhmm> (e.g.

    line 31
  2. Distinctive:

    All subsequent skills receive the run_id as context

    line 34
  3. Very specific:

    All data is stored in the project's docs/ directory:

    line 39

≈ “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

Using Business Validator

Overview

Business Validator provides a pipeline of skills for validating business ideas. Each skill handles one aspect of the analysis and produces a section of the final report.

Available Skills

SkillPurposeWhen to Use
business-validator:brainstormingRefine raw idea through dialogueFirst step — always start here
business-validator:idea-intakeCollect structured business detailsAfter brainstorming
business-validator:market-researchTAM/SAM/SOM, trends, regulationAfter idea intake
business-validator:competitor-analysisFind and compare competitorsAfter idea intake (parallel with market-research)
business-validator:financial-modelingUnit economics, revenue forecastAfter market research
business-validator:risk-assessmentSWOT, risks, mitigationAfter all research is done
business-validator:report-generationAssemble final report + PDFLast step — after all sections ready

Commands

  • /validate-idea — Run the full pipeline from intake to report
  • /market-report — Run only market-research + competitor-analysis

Run ID

Every validation session has a run_id in the format YYYY-MM-DD-<slug>-<hhmm> (e.g. 2026-02-19-ai-tutor-1435).

  • idea-intake generates the run_id from the date and idea name
  • All subsequent skills receive the run_id as context
  • File paths use the run_id explicitly — never glob for "most recent"

Data Flow

All data is stored in the project's docs/ directory:

  • Business briefs: docs/business-briefs/<run_id>.md
  • Report sections: docs/reports/<run_id>/01-market-research.md etc.
  • Final report: docs/reports/<run_id>/REPORT.md and REPORT.pdf

Pipeline Flow

digraph pipeline {
    "brainstorming" [shape=box, style=filled, fillcolor="#fff3e0"];
    "idea-intake" [shape=box, style=filled, fillcolor="#e8f5e9"];
    "market-research" [shape=box];
    "competitor-analysis" [shape=box];
    "financial-modeling" [shape=box];
    "risk-assessment" [shape=box];
    "report-generation" [shape=box, style=filled, fillcolor="#e3f2fd"];

    "brainstorming" -> "idea-intake";
    "idea-intake" -> "market-research";
    "idea-intake" -> "competitor-analysis";
    "market-research" -> "financial-modeling";
    "competitor-analysis" -> "financial-modeling";
    "financial-modeling" -> "risk-assessment";
    "risk-assessment" -> "report-generation";
}

Key Rules

  1. Always start with brainstorming — refines the raw idea before structured intake
  2. Then idea-intake — other skills need the business brief and run_id
  3. market-research and competitor-analysis can run in parallel — both depend only on the brief
  4. financial-modeling needs market data — wait for market-research to complete
  5. risk-assessment synthesizes everything — needs all prior sections
  6. report-generation is always last — assembles all sections into one report
  7. Always pass run_id explicitly — never use wildcards or "most recent" to find files

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