AgentStack
SKILL verified MIT Self-run

Asset Audit

skill-avelrl-skills-asset-audit · by avelrl

Audit game assets against naming, size, format, and reference integrity rules.

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-avelrl-skills-asset-audit

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Asset Audit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Purpose: Audit game assets for convention drift, reference integrity, and obvious budget problems.

Use when:

  • a project needs a quick asset health check by category or across the whole tree
  • you need evidence before cleanup or pipeline fixes

Do not use for:

  • generating assets
  • deleting or renaming files without confirmation
  • localization table validation

Inputs / Required Context:

  • required: one category or all
  • read project rules first from docs/technical-preferences.md when available
  • read design/gdd/asset-registry.md when present
  • fall back to gamedev/standards/data-files.md and any relevant art or audio bible already present

Outputs / Owned Artifacts:

  • no file output by default
  • returns an inline audit report using Summary -> Findings -> Risks -> Recommended Next Step

Modes or Arguments:

  • [category]: audit one asset class
  • all: audit standard asset directories together

Execution Rules:

  1. Resolve the requested asset scope and load project conventions or fallback assumptions.
  2. When design/gdd/asset-registry.md exists, compare the current tree against it and call out registry drift, missing registered assets, and untracked high-impact assets.
  3. Check naming, format, size or dimension budgets, broken references, orphaned assets, and missing expected assets.
  4. Group findings as violations, registry drift, missing references, orphans, and missing expected assets.
  5. If nothing is wrong, return an explicit zero-findings summary instead of a silent success.

Failure / Stop Conditions:

  • stop if the requested category cannot be mapped to a real project area
  • stop if no relevant asset directories exist
  • never assume unused means safe to delete; report it as orphaned unless confirmed otherwise

Return Format:

  • Summary
  • Findings
  • Risks
  • Recommended Next Step

Example Invocation:

  • /asset-audit textures

Related Skills / Boundary:

  • use localize for string tables and locale coverage
  • do not turn this skill into an automatic cleanup workflow

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.