agentleFS
markoblogomarkoblogo/abvx-agent-skills/skills/prototype-lab/SKILL.md

prototype-lab

Skill16 starsChanged 5 months agoMITView on GitHub

Build throwaway prototypes to answer a specific product, UI, state-machine, data-model, or workflow question before committing production code. Use when the user asks to prototype, explore variants, sanity-check logic, try designs, make a playable mock, or learn quickly with code that will be deleted or absorbed.

3 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

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 9

    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:

    If ambiguous, state the assumption and keep the artifact easy to delete.

    line 22
  2. Distinctive:

    Use one command to run.

    line 27
  3. Distinctive:

    Keep state in memory unless persistence is the thing being tested.

    line 28
  4. Distinctive:

    Avoid broad abstractions, production plumbing, and hidden dependencies.

    line 29
  5. Distinctive:

    Do not leave prototype code mixed with production code without a decision.

    line 31
  6. Distinctive:

    When exploring design, create 2-4 meaningfully different variants.

    line 35
  7. Distinctive:

    When exploring state, make a terminal or local web harness that can run scripted cases and manual interactions.

    line 39
  8. Distinctive:

    When the prototype answers the question:

    line 43
  9. Distinctive:

    delete the prototype or identify exactly what will be absorbed into production.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 3 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

Prototype Lab

A prototype answers one question. It is not production code with fewer tests.

Pick The Prototype Question

Choose the branch:

  • Logic prototype: state model, workflow, parser, scoring, queue, rules, or business logic.
  • UI prototype: layout direction, interaction model, variants, motion, or product feel.
  • Integration prototype: unknown API/tool behavior, deployment constraint, or browser capability.

If ambiguous, state the assumption and keep the artifact easy to delete.

Rules

  • Mark it as prototype/throwaway in path, UI, comments, or README.
  • Use one command to run.
  • Keep state in memory unless persistence is the thing being tested.
  • Avoid broad abstractions, production plumbing, and hidden dependencies.
  • Surface state after actions so learning is visible.
  • Do not leave prototype code mixed with production code without a decision.

UI Variant Pattern

When exploring design, create 2-4 meaningfully different variants. Let the user switch via route, query param, segmented control, or small debug toolbar. Do not make tiny color-only variations.

Logic Pattern

When exploring state, make a terminal or local web harness that can run scripted cases and manual interactions. Print current state, event, output, and invariant violations.

Closeout

When the prototype answers the question:

  • capture the decision in an issue, ADR, notes file, commit message, or final report;
  • delete the prototype or identify exactly what will be absorbed into production;
  • list what remains unproven.

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.