agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/project-stage-detect/SKILL.md

project-stage-detect

Skill9 starsChanged 7 months agoMITView on GitHub

Analyze project state — code volume, doc coverage, asset count. Determine if the project is in pre-production, production, polish, or live.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use asset-spec, create-control-manifest 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.
  • 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

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 2

    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:

    No target audience defined?

    line 76
  2. Distinctive:

    No live ops plan?

    line 92

“Common” is measured: kept by at least 6 in 10 of the 15 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

/project-stage-detect — Project Stage Analysis

Delegate to: producer (with technical-director for code analysis)

Steps

1. Scan Code

# Count Luau files
find src/ -name "*.lua" -o -name "*.luau" | wc -l

# Count total lines of code
find src/ -name "*.lua" -o -name "*.luau" -exec wc -l {} + | tail -1

# Look for major systems (directories or modules)
ls src/ServerScriptService src/ServerStorage src/ReplicatedStorage 2>/dev/null

2. Scan Design Docs

# Count GDDs
find design/gdd -name "*.md" | wc -l

# Check for master GDD
ls design/gdd/master-gdd.md 2>/dev/null && echo "EXISTS" || echo "MISSING"

# Check for systems index
ls design/gdd/systems-index.md 2>/dev/null && echo "EXISTS" || echo "MISSING"

3. Scan Assets

# Count assets by type
find assets/images -type f 2>/dev/null | wc -l
find assets/audio -type f 2>/dev/null | wc -l
find assets/models -type f 2>/dev/null | wc -l

4. Check Testing

find tests -name "*.spec.lua" -o -name "*.spec.luau" 2>/dev/null | wc -l

5. Check Production Artifacts

ls production/sprints/*.md 2>/dev/null | wc -l
ls production/milestones/*.md 2>/dev/null | wc -l

6. Check Git History

git log --oneline | wc -l  # total commits
git log --since="1 month ago" --oneline | wc -l  # recent activity

7. Classify Stage

StageSignals
Pre-productionNo master GDD, <5 GDDs, <1000 LOC, minimal assets
ProductionMaster GDD exists, systems being built, code growing fast, sprints active
PolishAll core systems implemented, bug triage focused, perf work happening
LivePublished, version tags exist, patch notes history, active retro cadence

8. Identify Gaps

For each stage, identify what's missing:

Pre-production gaps

  • No game concept?
  • No creative pillars?
  • No target audience defined?

Production gaps

  • No systems-index?
  • GDDs without corresponding code?
  • Code without corresponding GDDs?
  • No tests?
  • No CI?

Polish gaps

  • No /exploit-check run?
  • No performance benchmarks?
  • No accessibility review?

Live gaps

  • No analytics events?
  • No live ops plan?
  • No community structure?

9. Output

# Project Stage Detection

**Date**: YYYY-MM-DD

## Metrics
- Source files: X
- Lines of code: X
- GDDs: X
- Total assets: X
- Tests: X
- Commits: X (total), Y (last 30 days)
- Sprints: X
- Milestones: X

## Detected Stage
**[Pre-production / Production / Polish / Live]**

## Confidence
- High / Medium / Low

## Reasoning
[Why this classification]

## Gaps for Current Stage
1. [Gap 1]
2. [Gap 2]
3. [Gap 3]

## Recommended Next Steps
1. [Action 1]
2. [Action 2]

## Readiness for Next Stage
- [What's needed to advance]

Present the analysis for user confirmation. The classification is a proposal — the user may disagree based on context you don't have.

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.