agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/gate-check/SKILL.md

gate-check

Skill9 starsChanged 7 months agoMITView on GitHub

Stage gate check — does the project meet criteria to advance to the next production phase (pre-prod → prod → polish → live)?

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-level and 8 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

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +1 more from CoralGame
  • +5 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 3

    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. Very specific:

    Run /project-stage-detect if unclear.

    line 66
  2. Distinctive:

    If ALL criteria met → Go

    line 78
  3. Distinctive:

    If some criteria missed → No-go with blockers listed

    line 79
  4. Distinctive:

    If close but not complete → "Go with caveats" (user decides risk tolerance)

    line 80

“Common” is measured: kept by at least 6 in 10 of the 20 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

/gate-check — Stage Gate Review

Delegate to: producer (with technical-director, qa-lead, creative-director for respective areas)

Purpose

Stage gates force a deliberate decision about whether to move to the next production phase. Without gates, projects drift — always "almost ready" to start production, or "almost ready" to ship.

Stages

Pre-production → Production

Gate criteria:

  • Master GDD exists and reviewed
  • Creative pillars defined (3-5, 1 phrase each)
  • Core loop defined (30s / 5min / session / meta)
  • Target audience identified
  • Monetization strategy drafted
  • Target metrics set (retention, session, revenue if applicable)
  • Tech stack decided (sync tool, UI framework, packages)
  • Systems-index exists with priority
  • 2-3 top systems have detailed GDDs
  • Prototype or proof-of-concept validates core loop
  • Team capacity matches estimated scope (or scope cut accordingly)

Production → Polish

Gate criteria:

  • All core systems implemented (from systems-index P0/P1)
  • Game is playable end-to-end (intro → core loop → meta)
  • No S0 bugs open
  • All planned features either done or explicitly cut
  • Basic performance targets met (30 FPS mobile, server heartbeat < 33ms)
  • Security audit has been run at least once
  • DataStore schema is frozen (no more breaking changes)
  • Analytics events implemented
  • At least one external playtest (not just devs) completed

Polish → Live (Launch Ready)

Gate criteria:

  • Zero S0 bugs
  • Zero S1 bugs in critical paths
  • Performance targets exceeded on target devices
  • Security audit passed with no Critical findings
  • Content policy review passed
  • All launch marketing materials ready
  • Community channels active
  • Rollback plan tested
  • Soft launch retention > target (D1 > 20%, ideally > 25%)
  • Server costs projected and manageable
  • Team ready for launch support

Live → Live Service Optimization

Gate criteria (do we continue investing?):

  • Retention trending up or stable
  • Revenue meets minimum threshold
  • Community engaged (growing Discord, positive reviews)
  • Technical debt manageable
  • Team has capacity for sustained live-ops

Steps

1. Current Stage

Run /project-stage-detect if unclear. Get the current stage.

2. Target Stage

"What stage are you trying to advance to?"

3. Run the Checklist

For the target transition, go through each criterion:

  • Verify each item
  • Delegate to the relevant specialist for verification (e.g., security criteria → exploit-security-specialist)
  • Record pass/fail/partial

4. Assess Readiness

  • If ALL criteria met → Go
  • If some criteria missed → No-go with blockers listed
  • If close but not complete → "Go with caveats" (user decides risk tolerance)

5. Generate Gate Report

# Gate Check: [Current Stage] → [Target Stage]

**Date**: YYYY-MM-DD
**Reviewer**: [user]

## Current Status
[Summary of current state]

## Criteria
| Criterion | Status | Notes |
|-----------|--------|-------|
| Master GDD exists | ✅ | |
| Core loop defined | ⚠️ Partial | Meta loop undefined |
| Creative pillars | ✅ | |
| ... | ... | ... |

## Met
[List of passing criteria]

## Not Met / Blockers
1. [Blocker with specific remediation]
2. [Blocker with specific remediation]

## Recommendation
[ ] **PASS** — advance to next stage
[X] **HOLD** — address blockers first
[ ] **PASS WITH CAVEATS** — advance accepting documented risks

## Next Steps (if HOLD)
1. [Action item]
2. [Action item]

## Target Re-review Date
YYYY-MM-DD

Save to production/gates/gate-<stage>-<date>.md on approval.

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.