agentleFS
Sign inStart free
haintbotasthaintbotast/coding-agent-instructions/skills/prototype/SKILL.md

prototype

Skill0 starsChanged 22 days agoMITView on GitHub

Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like, before committing to a real implementation. NOT for building the real thing, that is writing-plans then test-driven-development.

194 other projects use a version of this, 80 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 14 projects that use this

  • +5 more from lilangMax
  • +3 more from CoralGame

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 3

    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:

    Throwaway from day one, clearly marked: Place near where it'll be used, named so a casual reader sees it's a prototype.

    line 17
  2. Distinctive:

    Skip the polish: No tests, no error handling beyond runnable, no abstractions.

    line 20
  3. Distinctive:

    Surface the state: after every action / variant switch so the user sees what changed.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 179 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

A prototype is throwaway code that answers a question. The question decides the shape:

  • "Does this logic/state model feel right?" → a single shareable HTML file — free-play buttons plus tabbed guided walkthroughs — that pushes the state machine through cases hard to reason about on paper, and that a non-developer can drive.
  • "What should this look like?" → several radically different UI variations on one route, switchable via URL param.

Ambiguous and user unreachable? Default by surrounding code (backend module → logic; page/component → UI) and state the assumption at the top.

Rules

  1. Throwaway from day one, clearly marked. Place near where it'll be used, named so a casual reader sees it's a prototype. Follow existing routing conventions for UI routes.
  2. Trivial to run. A UI prototype starts from one command in the project's existing task runner; a logic demo is a single HTML file the user double-clicks. Either way, no thinking required to start it.
  3. No persistence by default — state in memory. If the question IS persistence, use a scratch DB/file named "PROTOTYPE — wipe me".
  4. Skip the polish. No tests, no error handling beyond runnable, no abstractions.
  5. Surface the state after every action / variant switch so the user sees what changed.
  6. Capture when done. Fold the validated decision into real code — main keeps only that. Then commit the prototype itself to a throwaway branch (out of main) as a primary source, with a pointer to the branch from the implementation issue/commit. Capture the answer too — verdict + the question it settled — durably (issue, commit message, ADR). For UI variants: the winner folds into the real page/route; the full variant set + switcher ride the throwaway branch, never main.

Recovery

StateWay out
Prototype code leaked into mainIt was never meant to ship: git revert the commit that brought it, then put it on the throwaway branch where rule 6 says it belongs. Check the routing config too — a prototype route left registered is the part that survives a partial revert.
Scratch DB/file from rule 3 still aroundDelete it. It is named "PROTOTYPE — wipe me" precisely so this is a one-line decision, not an investigation.
Throwaway branch deleted before the answer was capturedThe verdict matters, the code does not. If the answer was never written to an issue/commit/ADR, it is gone — re-run the prototype rather than reconstruct it from memory. Capture first next time; that is what rule 6 is for.
Prototype grew tests, error handling, abstractionsIt stopped being a prototype and became unreviewed production code. Stop. Either throw it away and implement properly, or put it through the normal pipeline from writing-plans onward. Do not merge it because it "already works".
Cannot tell whether the prototype answered the questionIt did not. An inconclusive prototype is a cheap failure — say so, name what stayed ambiguous, and either sharpen the question or move to a real spike. Do not report a guess as a finding.

Distilled from mattpocock/skills (MIT © Matt Pocock), snapshot 068b6e0 (2026-08-17). See SOURCES.md.

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