asset-gen

Generate visual assets from text prompts: PNG images (Gemini / xAI Grok), GLB 3D models (Tripo3D), rigged biped characters, retargeted animations, and frame-by-frame animated sprites, plus background removal. Use whenever a game needs generated art.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is excellent on conciseness, actionability, and workflow clarity — dense with executable commands, operational pitfalls, and explicit cost/feedback-loop safeguards. Progressive disclosure is the only weaker dimension: it relies on a single offloaded reference and keeps a large presets catalog inline.

Suggestions

Move the biped retarget presets catalog out of SKILL.md into a dedicated reference file (e.g. references/biped_presets.md) and link to it, keeping the skill body as a concise overview that signals where the full list lives.

Add a small references/ directory and consolidate the rembg guidance and any long flag/option tables into linked reference files so SKILL.md stays a navigable overview pointing one level deep.

Surface the referenced bundle files explicitly (e.g. a 'References' list naming rembg.md, the tools/ scripts) so the offloaded material is clearly signaled and easy to discover.

Dimension	Reasoning	Score
Conciseness	Every section delivers domain-specific operational knowledge Claude would not already know (e.g. 'never prompt for a transparent background — the generator bakes a checkerboard') with no padding or re-explanation of basics, matching the 'lean and efficient; every token earns its place' anchor rather than the 'mostly efficient but could be tightened' level.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout — 'python3 .../asset_gen.py image --prompt ... -o ...', 'ffmpeg -i walk.mp4 -vsync 0 frames/%04d.png', 'tools/grid_slice.py ... --grid 2x2 --names "a,b,c,d"' — with concrete flags and costs, matching the 'fully executable code/commands' anchor rather than the pseudocode of score 2.	3 / 3
Workflow Clarity	The animated-sprites section gives a clear six-step sequence with a review checkpoint ('Review every PNG before any GLB conversion'), and the Tripo3D section has an explicit error-recovery feedback loop (timeout → do not resubmit, it double-charges → resume for free → safe to re-run, no-ops when done), matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	The body is cleanly sectioned and offloads one topic to a one-level-deep reference ('Read ${ASSET_GEN_SKILL_DIR}/rembg.md'), but no bundle directories (references/scripts/assets) are present to verify referenced paths and large reference material — notably the multi-line biped retarget presets catalog — is kept inline rather than split into a separate file, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all four dimensions: it enumerates concrete capabilities with their tools, states an explicit 'Use whenever...' trigger, and carves out a distinct game-asset niche. No suggestions warranted.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities with named tools — 'PNG images (Gemini / xAI Grok), GLB 3D models (Tripo3D), rigged biped characters, retargeted animations, and frame-by-frame animated sprites, plus background removal' — matching the 'lists multiple specific concrete actions' anchor rather than the partial coverage of score 2.	3 / 3
Completeness	Explicitly answers both 'what' (the enumerated asset types) and 'when' via 'Use whenever a game needs generated art', satisfying the 'both what AND when with explicit triggers' anchor rather than the implied-when of score 2.	3 / 3
Trigger Term Quality	Natural terms users would actually say — 'images', '3D models', 'characters', 'animations', 'animated sprites', 'game needs generated art' — are well covered; the tool names (Gemini, Grok, Tripo3D) appear as attribution rather than as the trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	The game-art-generation niche with rigged characters and retargeted animations is distinct and unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor rather than the overlapping 'works with document files' level.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: htdt/godogen
Path: asset-gen/SKILL.md
Commit: 05cebff

Reviewed: ~1 month ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.