agentleFS
lukashouthoofdlukashouthoofd/cenekathon/.claude/skills/rapid-prototype/SKILL.md

rapid-prototype

Skill1 starsChanged 14 days agoMITView on GitHub

Use when building the product under time pressure — walking skeleton, thin vertical slices, mock-then-real, and keeping main demoable.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Boring tech: Use what the team already knows.

    line 11
  2. Distinctive:

    Seed data: commit a fixture so the demo works offline and after a fresh clone.

    line 13
  3. Distinctive:

    Commit + push after every working step.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Rapid prototype

  • Walking skeleton: one input → one real processing step → one visible output, deployed. Do this before any feature.
  • Vertical slice = user-visible. Each slice ends with something you can click or run in the demo. No "backend done, frontend later".
  • Mock → real: stub external or slow parts with clearly labelled fixtures (MOCK in the UI); wire the real thing after the slice works. Never present mocks as real.
  • Boring tech. Use what the team already knows. E.g. Next.js/Vite + a serverless function, or FastAPI + a simple page. SQLite / JSON file / Supabase over self-run Postgres. One repo, one deploy.
  • Hardcode first, generalize only if the demo needs it. No auth unless the brief demands it (use a fake user switch).
  • Seed data: commit a fixture so the demo works offline and after a fresh clone.
  • Happy-path polish > edge cases. The demo path must be flawless; everything else may fail gracefully.
  • Timebox: a slice not working after 45 min → cut scope, don't push on.
  • Commit + push after every working step. main must always run.

Done when: the slice runs from a clean clone with the documented command and shows its result.

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.