project-stage-detect
Analyze project state — code volume, doc coverage, asset count. Determine if the project is in pre-production, production, polish, or live.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Analyze project state — code volume, doc coverage, asset count. Determine if the project is in pre-production, production, polish, or live.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run a comprehensive health check on the repo. Verifies README counts match reality, promised files exist, no unresolved placeholders, wiki index is synced, toolchain configs are valid, and agent roster is accurate. Use after making structural changes or before publishing.
Begin a new Roblox game project or onboard to an existing one. Use when starting a fresh session with no context, or when the user says "let's start" or "new project".
Generate a 3D asset from a reference image using Blender MCP's image-to-3D AI (Hyper3D). Optimizes for Roblox and exports FBX.
Generate a 3D asset for Roblox using Blender MCP. Creates models from text descriptions via AI (Hyper3D/Hunyuan3D) or downloads from PolyHaven/Sketchfab, optimizes for Roblox constraints, and exports FBX.
Inspect the current Roblox Studio state via MCP. Verifies instance hierarchy, checks for common structural issues, and reports findings.
Capture a screenshot of the current Roblox Studio viewport and analyze it. Use for visual verification of UI, lighting, level layout, and general game appearance.
| name | project-stage-detect |
| description | Analyze project state — code volume, doc coverage, asset count. Determine if the project is in pre-production, production, polish, or live. |
# 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
# 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"
# 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
find tests -name "*.spec.lua" -o -name "*.spec.luau" 2>/dev/null | wc -l
ls production/sprints/*.md 2>/dev/null | wc -l
ls production/milestones/*.md 2>/dev/null | wc -l
git log --oneline | wc -l # total commits
git log --since="1 month ago" --oneline | wc -l # recent activity
| Stage | Signals |
|---|---|
| Pre-production | No master GDD, <5 GDDs, <1000 LOC, minimal assets |
| Production | Master GDD exists, systems being built, code growing fast, sprints active |
| Polish | All core systems implemented, bug triage focused, perf work happening |
| Live | Published, version tags exist, patch notes history, active retro cadence |
For each stage, identify what's missing:
/exploit-check run?# 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.