agentleFS
kiku-jwkiku-jw/codex-skills/product-shaping/SKILL.md

product-shaping

Skill0 starsChanged 4 months agoMITView on GitHub

Shape product work with the minimum useful framework after an idea clears basic validation. Use for assumptions, experiments, opportunity-solution trees, strategy, value proposition, or pre-mortems when the next product decision is still fuzzy.

4 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

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    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 still needs basic validation or already has a clear implementation-ready direction.

    line 10
  2. Distinctive:

    No generic PM ceremony, roadmap theater, or silent handoff vagueness.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 4 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

Product Shaping

Metadata

  • Trigger when: validation exists, but the next product decision still needs structure before implementation or spec work.
  • Do not use when: the work still needs basic validation or already has a clear implementation-ready direction.

Skill Purpose

Choose one compact product-thinking frame that reduces ambiguity without drifting into PM theater or bloated process.

Instructions

  1. Gate the lane first. If the real question is still build or not, route back to $idea-validation. If the spec is already clear and the next blocker is implementation, route to $spec-bundle or execution instead.
  2. Choose the smallest framework that fits the actual uncertainty: assumptions, experiment design, opportunity-solution tree, product strategy, value proposition, or pre-mortem. Use ~/.codex/skills/product-shaping/references/patterns.md when you need the compact templates.
  3. Produce one decision-ready output tied to the current task and end with an explicit next lane: stay in product shaping, return to validation, move to a short execution brief, or move to the appropriate level of $spec-bundle. If another skill is needed, name it explicitly with a one-line reason.

Non-Negotiable Acceptance Criteria

  • One framework by default; chain only when one output clearly feeds the next.
  • Trade-offs, risky assumptions, and the next concrete move are explicit.
  • No generic PM ceremony, roadmap theater, or silent handoff vagueness.
  • The output names the next lane instead of leaving routing implicit.

Output

  • A compact framework result anchored to the current product question.
  • An explicit next lane.
  • The smallest next action or experiment that would reduce uncertainty fastest.
  • Next skill options (only if needed): $idea-validation — go back and validate buyer/pain/signal; $spec-bundle — convert the chosen direction into contracts, schema, and gates; $product-council — run a multi-lens check on a fuzzy or risky decision.

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.