agentleFS
Aquarius-muAquarius-mu/skillManager/skills/gameserver-agent-skills/prototype/SKILL.md

prototype

Skill1 starsChanged 51 days agoMITView on GitHub

Build a throwaway prototype to answer a design question before committing to an implementation. Use when sanity-checking a data model, state machine, or design approach.

194 other projects use a version of this.

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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 4

    Distinctive

    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. Distinctive:

    If genuinely ambiguous, default to whichever branch matches the surrounding code.

    line 17
  2. Very specific:

    One command to build: Use ./build.sh. The result must compile and run without thinking

    line 22
  3. Distinctive:

    Skip the polish: No full error handling beyond what makes it runnable.

    line 24
  4. Distinctive:

    Surface the state: After every operation, log the full relevant state so the question can be answered

    line 25
  5. Distinctive:

    Delete or absorb when done: Never leave prototype code rotting in the codebase

    line 26

“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.

Pick a Branch

Identify the question being answered:

  • "Does this data model / state machine feel right?" → Build a minimal C++ harness that exercises the key state transitions or data operations
  • "What should this protocol look like?" → Sketch the sdp struct definitions and walk through the request/response flow

If genuinely ambiguous, default to whichever branch matches the surrounding code.

Rules

  1. Throwaway from day one, clearly marked. Name the file or directory so a reader instantly knows it's a prototype: proto_xxx.cpp, scratch_xxx.sdp
  2. One command to build. Use ./build.sh. The result must compile and run without thinking
  3. No persistence by default. State lives in memory unless persistence is the question being answered
  4. Skip the polish. No full error handling beyond what makes it runnable. The point is to learn fast and delete
  5. Surface the state. After every operation, log the full relevant state so the question can be answered
  6. Delete or absorb when done. Never leave prototype code rotting in the codebase

Capture the Answer

The answer is the only thing worth keeping. Capture it in a NOTES.md next to the prototype, or in an SVN commit message, or as an ADR:

## Question
[What were we trying to learn?]

## Answer
[What did we find out?]

## Decision
[What will we do as a result?]

Then delete the prototype and invoke /plan to begin the real implementation.

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.