roblox-to-issues
Skill5 starsChanged 5 months agoMITView on GitHub
Break a Roblox game PRD, roadmap, or plan into small independently-playtestable vertical slices instead of building the whole game at once. Use when the user wants to turn a concept or PRD into buildable tickets, split work into slices, plan what to build next, or stop Claude from trying to build an entire game in one pass. Each slice cuts through client, server, remotes, data, and UI for one small player-facing capability, verified with a Studio playtest.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- rodrigo-guerraa/roblox-hubedited, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- rodrigo-guerraa/roblox-hub★ 233% same
Wrote their own version · 0
None found.
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 repository39 other files it gives its agents.
- handoffSkill
- roblox-admin-tools-observabilitySkill
- roblox-analytics-instrumentationSkill
- roblox-animation-audio-feedbackSkill
- roblox-asset-pipelineSkill
- roblox-code-maintenance-refactorSkill
- roblox-combat-systemsSkill
- roblox-community-opsSkill
- roblox-creator-store-security-auditSkill
- roblox-datastore-persistenceSkill
- roblox-debugging-bugfixSkill
- roblox-economy-balancingSkill
- roblox-game-development-lifecycleSkill
- roblox-game-ideasSkill
- roblox-game-uxSkill
- roblox-genre-patternsSkill
- roblox-growth-marketingSkill
- roblox-liveops-roadmapSkill
- roblox-localization-accessibilitySkill
- roblox-luau-architectureSkill
- roblox-mobile-playtestSkill
- roblox-monetization-optimizationSkill
- roblox-performance-optimizationSkill
- roblox-playtest-qaSkill
- roblox-policy-complianceSkill
- roblox-publishing-discoverySkill
- roblox-quest-progression-systemsSkill
- roblox-release-operationsSkill
- roblox-retention-monetizationSkill
- roblox-security-economySkill
- roblox-social-systemsSkill
- roblox-studio-workflowSkill
- roblox-to-prdSkill
- roblox-triageSkill
- roblox-ui-implementationSkill
- roblox-world-level-designSkill
- setup-roblox-skillsSkill
- write-a-skillSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 23
Prefer many thin slices over a few thick ones.
- Distinctive: line 52
Ask: is the granularity right (too coarse / too fine)?
- Distinctive: line 87
Do NOT close or modify a parent PRD/issue.
- Very specific: line 91
Run roblox-triage to sort the slices and mark which are ready to build, then build each slice with its phase specialist (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Roblox → Issues (Vertical Slices)
Break a plan into small issues that are each buildable and playtestable on their own. This is the antidote to "build the whole game in one go, everything half-broken."
The tracker location and label vocabulary should have been provided to you in CLAUDE.md / docs/agents/. If not, run setup-roblox-skills. Slices publish either as GitHub issues (gh) or as markdown files under roadmap/<feature-slug>/slices/ — whichever the setup configured. In all cases, keep ROADMAP.md as the human-readable index.
What a Roblox vertical slice is
A tracer bullet: the thinnest end-to-end path that a player can actually feel, cutting through every layer it touches — client input, server authority, remotes, DataStore, and UI — not one horizontal layer.
- Right (vertical): "Player taps the ore, server grants 1 coin, HUD shows the new balance, balance survives rejoin." Touches input + remote + server + data + UI. Playable.
- Wrong (horizontal): "Build the entire economy module." / "Build all the UI." Nothing is playable until everything is done — exactly the failure we are avoiding.
Slice rules
- Each slice delivers one narrow but complete player-facing capability.
- Each slice is verifiable in a Studio playtest on its own (this is the acceptance signal).
- Prefer many thin slices over a few thick ones. If a slice can't be playtested in isolation, split it.
- Valuable state (currency, inventory, purchases, rewards, progression) is server-authoritative from the first slice — never a client-trust shortcut you plan to fix later.
- The first slice is the tracer bullet: the smallest thing that proves the core loop end-to-end (one action → one reward → one visible next goal). Build it before anything else.
Slice types
- AFK — can be built and verified without a human decision. Prefer these.
- HITL — needs a human: a design approval, a balance judgment call, a Studio action only the user can take. UI slices are HITL until an approved UI design artifact exists (see
roblox-game-ux); if UI design is missing, create a design-approval slice first and block the UI slice on it.
Process
1. Gather context
Work from the PRD / conversation. If the user passes a reference (issue number, ROADMAP.md line, or file path), read it fully. Connect via roblox-studio-workflow if you need to see current place state. Use the game's own vocabulary.
2. Draft the slices
Order them so the core loop tracer bullet is slice 1, then layer capability outward (persistence → progression → social → monetization → polish). Each later slice should build on a slice that is already playable.
3. Quiz the user
Present the breakdown as a numbered list. For each slice show:
- Title — short, player-facing.
- Type — AFK / HITL.
- Blocked by — which slices must ship first.
- Playtest check — the exact in-Studio action that proves it works.
- Server-authoritative? — yes/no and which state it protects.
Ask: is the granularity right (too coarse / too fine)? Are dependencies correct? Should any slice split further? Are HITL/AFK correct? Iterate until approved.
4. Publish
Publish each approved slice to the configured tracker with the needs-triage label/status, blockers first so you can reference real IDs. Mirror each slice as a checkbox in ROADMAP.md using the pack's convention: [ ] not started, [~] built and tested but awaiting approval, [x] only after build + playtest + explicit human approval.
<slice-template>
## What to buildThe end-to-end player-facing behavior for this slice. Describe what the player does and what the server does — not a layer-by-layer implementation.
Layers touched
- Client: ...
- Server (authoritative): ...
- Remotes: ...
- Data / persistence: ...
- UI: ...
Playtest check (acceptance)
- In a Studio playtest,
<exact action>produces<exact result>. - Valuable state is server-validated and survives rejoin (if applicable).
- No new console errors.
- Mobile: readable and tappable on a phone-sized viewport (if UI).
UI design artifact
For UI slices: link the approved artifact (see roblox-game-ux) or "blocked on UI design approval".
Blocked by
Reference the blocking slice, or "None — can start immediately".
</slice-template>
Do NOT close or modify a parent PRD/issue.
Next
Run roblox-triage to sort the slices and mark which are ready to build, then build each slice with its phase specialist (e.g. roblox-luau-architecture, roblox-combat-systems, roblox-ui-implementation, roblox-datastore-persistence) and verify with roblox-playtest-qa. Keep roblox-game-development-lifecycle as the umbrella that decides slice order.
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.

