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.

Quality

81%

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

77%

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

The content is highly actionable and well-sequenced with strong validation and error-recovery structure. Its weaknesses are conciseness (repeated protocol sections and verbose inline templates) and progressive disclosure (a long monolith that would benefit from splitting into reference files).

Suggestions

Move the large markdown templates (entity-inventory, ASSET-NNN spec, asset-manifest) and the detailed art-director/technical-artist briefs into reference files under references/ and link to them from SKILL.md.

Remove the redundant Collaborative Protocol and Recommended Next Steps sections whose rules are already embedded in the phase steps, or condense them to a brief checklist.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining known concepts but is lengthy with repeated protocol restatements (Collaborative Protocol, Recommended Next Steps) and fully-written template blocks that could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance throughout — exact file paths, a runnable Grep pattern, specific agent briefs with numbered deliverables, and complete output templates.	3 / 3
Workflow Clarity	Clear Phase 0–6 sequence with explicit validation checkpoints ('Do NOT proceed to Phase 3 without user confirmation'), conflict-surfacing rules, and a numbered error-recovery feedback loop for blocked agents.	3 / 3
Progressive Disclosure	All ~340 lines are inline in a single monolithic file with no bundle references; large templates and detailed agent briefs that could be split into separate reference files are kept inline despite the skill's length.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, complete, and distinct, clearly conveying both the skill's actions and when to run it. Its main weakness is trigger-term quality: triggers are phrased as workflow ordering rather than natural language a user would say.

Suggestions

Add a 'Use when...' clause with natural user phrasing such as 'Use when the user asks for asset specs, sprite specs, or AI art prompts for game assets' to improve trigger-term quality.

Include common variation keywords users might say (e.g., 'art assets', 'sprite sheets', 'asset list') alongside the existing domain terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate per-asset visual specifications', 'AI generation prompts', 'Produces structured spec files', and 'updates the master asset manifest' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (generate specs/prompts, produce files, update manifest) and when ('Run after art bible and GDD/level design are approved, before production begins'), which is equivalent explicit trigger guidance.	3 / 3
Trigger Term Quality	Contains relevant domain keywords ('GDDs, level docs, character profiles', 'art bible', 'asset manifest') but frames triggers as pipeline ordering rather than natural user-said phrases, missing common variations.	2 / 3
Distinctiveness Conflict Risk	A clearly scoped game-dev art-spec niche anchored to the art bible/GDD pipeline, with distinct triggers unlikely to overlap with generic skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/asset-spec/SKILL.md
Commit: 984023d

Reviewed: 3 days 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.