agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/asset-audit/SKILL.md

asset-audit

Skill9 starsChanged 7 months agoMITView on GitHub

Review assets — naming conventions, file sizes, unused assets, and organization. Flags assets that violate naming standards or exceed size limits.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops 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

    soak-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 5 projects that use this

  • lilangMaxSkill

    team-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 5 projects that use this

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    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:

    Check which assets are referenced in code:

    line 45

“Common” is measured: kept by at least 6 in 10 of the 13 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

/asset-audit — Asset Review

Delegate to: art-director (with technical-artist for optimization review)

Steps

1. Scan Asset Directories

find assets/ -type f | sort

Categorize by type: images, audio, models, data.

2. Naming Convention Check

Standard: lowercase-kebab-case.ext

Good: wooden-crate.fbx, sword-swing-01.mp3, ui-button-bg.png Bad: Wooden Crate.fbx, swordswing1.mp3, UI_Button_BG.png

# Find files with spaces (violation)
find assets/ -type f -name "* *"

# Find files with uppercase (violation — except extensions)
find assets/ -type f | grep -v "/[a-z0-9-]*\.[a-zA-Z0-9]*$"

3. File Size Check

Flag large files:

  • Images > 1MB (warning), > 5MB (critical)
  • Audio > 1MB short SFX (warning), > 10MB music (normal)
  • Models > 5MB (warning), > 20MB (critical)
find assets/images -type f -size +1M
find assets/audio -type f -size +10M
find assets/models -type f -size +5M

4. Unused Asset Detection

Check which assets are referenced in code:

# For each asset, grep for its name in src/
for asset in $(find assets/ -type f -name "*.png" -o -name "*.jpg"); do
    name=$(basename "$asset")
    if ! grep -r "$name" src/ > /dev/null; then
        echo "POTENTIALLY UNUSED: $asset"
    fi
done

Note: Some assets may be referenced by ID (Roblox asset ID), not by filename. Manual verification needed.

5. Organization Check

  • All images in assets/images/
  • All audio in assets/audio/
  • All models in assets/models/
  • All data (JSON) in assets/data/
  • Sub-categorized if > 20 files in a folder (e.g., assets/images/ui/, assets/images/icons/)

6. Roblox Limit Check

  • Mesh triangles: Flag models > 10,000 tris (need DCC tool inspection)
  • Texture resolution: Flag images > 1024×1024
  • Audio duration: Flag audio > 60 seconds that isn't music

7. Generate Report

# Asset Audit

## Summary
- Total assets: X
- Images: X
- Audio: X
- Models: X
- Data files: X

## Violations
### Naming (must fix)
- [path] — violates kebab-case

### Oversized (should fix)
- [path] — [size] exceeds [limit]

### Potentially Unused (investigate)
- [path] — no references found in src/

### Organization (nice to have)
- [suggestion]

## Statistics
- Largest asset: [path, size]
- Most referenced: [path, count]
- Total asset size: XX MB

## Recommendations
1. [Specific cleanup action]
2. [Optimization opportunity]

Present to user. Offer to delegate cleanup to art-director.

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.