agentleFS
kiku-jwkiku-jw/codex-skills/idea-validation/SKILL.md

idea-validation

Skill0 starsChanged 4 months agoMITView on GitHub

Validate a raw product idea before PRD or implementation: buyer, pain, workaround, promised outcome, smallest wedge, distribution path, proof sought, kill criteria, and the next honest lane. Use when an idea still needs market or wedge truth.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 4

    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:

    Do not use when: the work already has believable validation signal and the next blocker is product shaping or implementation detail.

    line 10
  2. Distinctive:

    Run the contract-clean gate first whenever the idea may touch client work, sensitive exports, ambiguous rights, shared accounts, or …

    line 17
  3. Distinctive:

    Do not let a detailed spec pretend to be validation signal.

    line 22
  4. Distinctive:

    If the fastest proof path is manual service or concierge work, say so directly.

    line 23

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

Idea Validation

Metadata

  • Trigger when: the idea is interesting enough to examine, but buyer, pain, signal, or wedge truth is still uncertain.
  • Do not use when: the work already has believable validation signal and the next blocker is product shaping or implementation detail.

Skill Purpose

Pressure-test an idea before it turns into PRD theater by forcing clarity on buyer, pain, workaround, outcome, wedge, proof, and kill criteria.

Instructions

  1. Run the contract-clean gate first whenever the idea may touch client work, sensitive exports, ambiguous rights, shared accounts, or gray-source access. Use ~/.codex/skills/idea-validation/references/contract-clean-gate.md when you need the exact hard-reject surface.
  2. Build one lean validation brief with these fields: buyer/operator, painful recurring job, current workaround, promised outcome, smallest wedge, first distribution path, proof sought, and kill criteria. Default to one function, one buyer, and one painful problem in the first pass.
  3. Choose the next honest lane explicitly: stay in validation, move to $product-shaping, move to a short execution brief, or move to $spec-bundle when implementation ambiguity or architecture risk is now the real blocker. If another skill is needed, name it explicitly with a one-line reason. Use ~/.codex/skills/idea-validation/references/playbook.md only when you need fuller heuristics.

Non-Negotiable Acceptance Criteria

  • Do not let a detailed spec pretend to be validation signal.
  • If the fastest proof path is manual service or concierge work, say so directly.
  • Contract-gray or rights-dirty ideas are parked, not rescued with clever framing.
  • The output names a next lane; it does not end with vague “more research later” filler.

Output

  • A compact validation brief covering buyer, pain, workaround, outcome, wedge, distribution, proof, and kill criteria.
  • An explicit statement of the current signal strength and the main red flag, if any.
  • One next lane: stay in validation, move to product shaping, or move toward execution/spec work.
  • Next skill options (only if needed): $product-shaping — structure the next product decision after basic validation; $spec-bundle — turn the validated direction into implementation-ready artifacts; $work-shaping — decide how much process or tracking the work now deserves.

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.