prototype
Skill9 starsChanged 7 months agoMITView on GitHub
Quick prototype workflow — minimal viable implementation, no production standards, README with hypothesis. Code goes in prototypes/, never imported from src/.
193 other projects use a version of this.
Adopted by
Most recently taken up by
- philoserf/claude-code-configtheir own version, first seen Nov 15, 2026
- raphaeltm/simple-agent-managertheir own version, first seen Nov 15, 2026
- boraoztunc/skillstheir own version, first seen Nov 15, 2026
- egagofur/ai-engineering-looptheir own version, first seen Nov 15, 2026
- geoffbremner/skillstheir own version, first seen Nov 15, 2026
- ychampion/ystacktheir own version, first seen Nov 15, 2026
Used with
Projects with it also use playtest-report, soak-test and 9 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.
CoralGameSkillplaytest-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
lilangMaxSkillsoak-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
lilangMaxSkillteam-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
CoralGameSkillteam-audio
Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
Also in 12 projects that use this
- +5 more from lilangMax
- +2 more from CoralGame
Other versions193 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 193
- mattpocock/skills★ 325ksame name
- emilkowalski/skills★ 57ksame name
- emilkowalski/skill★ 55ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- GreyDGL/PentestGPT★ 16ksame name
- spree/spree★ 16ksame name
- usekaneo/kaneo★ 9.8ksame name
- podman-desktop/podman-desktop★ 8.1ksame name
183 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- asset-auditSkill
- asset-from-imageSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- changelogSkill
- code-reviewSkill
- datastore-reviewSkill
- design-reviewSkill
- design-systemSkill
- doctorSkill
- economy-auditSkill
- estimateSkill
- exploit-checkSkill
- gate-checkSkill
- gddSkill
- generate-assetSkill
- hotfixSkill
- launch-checklistSkill
- luau-lintSkill
- map-systemsSkill
- milestone-reviewSkill
- monetization-modelSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- project-stage-detectSkill
- publish-reviewSkill
- release-checklistSkill
- remotes-auditSkill
- retention-analysisSkill
- retrospectiveSkill
- reverse-documentSkill
- scope-checkSkill
- sprint-planSkill
- startSkill
- studio-inspectSkill
- studio-screenshotSkill
- studio-testSkill
- team-combatSkill
- team-economySkill
- team-polishSkill
- team-releaseSkill
- team-uiSkill
- tech-debtSkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-querySkill
- wiki-seedSkill
- wiki-updateSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 178 edited versions we read keep these.
6
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
- Distinctive: line 30
Only build what's needed to test the hypothesis
- Distinctive: line 44
Write code that answers the question.
- Distinctive: line 45
Add type annotations (unless they help)
- Distinctive: line 52
Use clear variable names (so future-you understands)
- Distinctive: line 57
After running, update the README:
- Distinctive: line 90
Bad idea: Document learnings, archive the prototype, move on
“Common” is measured: kept by at least 6 in 10 of the 178 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.
Files
/prototype — Rapid Prototyping Workflow
Delegate to: luau-gameplay-programmer or luau-systems-programmer (depending on scope)
Purpose
Prototypes are throwaway code to test an idea quickly. They are NOT production code.
Rules
- Prototypes live in
prototypes/<prototype-name>/ - Prototypes NEVER import from
src/ - Prototype code does NOT need to meet production standards
- Prototypes require a README.md explaining the hypothesis
- Prototypes are NOT graduated directly to
src/— if the idea is good, rewrite cleanly
Steps
1. Define the Hypothesis
Ask the user:
- "What are we testing?"
- "What's the question this prototype answers?"
- "What would 'success' look like?"
- "What's the time budget?" (default: 2-4 hours)
2. Scope Ruthlessly
- Only build what's needed to test the hypothesis
- Skip: polished UI, data persistence, multiplayer (unless core to hypothesis)
- Focus: the thing that's being questioned
3. Set Up Prototype Directory
prototypes/
└── <prototype-name>/
├── README.md # Hypothesis, how to run, findings
├── src/ # Prototype Luau files
└── assets/ # Any placeholder assets4. Build the Minimum
Write code that answers the question. Do NOT:
- Add type annotations (unless they help)
- Wrap in pcall (unless necessary for the question)
- Write tests
- Worry about cleanup
- Optimize performance
DO:
- Use clear variable names (so future-you understands)
- Comment the KEY decisions
- Make it runnable (Rojo or manual Studio import)
5. Document Findings
After running, update the README:
# Prototype: [Name]
## Hypothesis
[What we were testing]
## How to Run
1. [Setup steps]
2. [Run steps]
## What We Learned
- [Finding 1]
- [Finding 2]
- [Unexpected result]
## Go / No-Go
**Verdict**: [Good idea / bad idea / needs more research]
## If Go, Next Steps
1. [How to translate this into production]
2. [What specialists are needed]
3. [What systems it affects]
## If No-Go
- [Why it didn't work]
- [Alternative approaches to consider]6. Decide
User decides:
- Good idea: Schedule proper implementation (rewrite, not copy-paste)
- Good idea with tweaks: Iterate the prototype OR move to production planning
- Bad idea: Document learnings, archive the prototype, move on
- Inconclusive: Decide if more prototyping is worth the time
Anti-Patterns
- Prototype sprawl (spending weeks on a "prototype")
- Importing prototype code into production without rewrite
- Skipping the README and losing the findings
- Testing multiple hypotheses in one prototype (hard to learn from)
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
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.

