asset-spec

Per-asset visual specs plus AI generation prompts from GDDs and character profiles. After the art bible.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/asset-spec/SKILL.md

Quality

Content

85%Weight 40%Scale 1-5

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

An exceptionally actionable, well-sequenced workflow skill: every phase has concrete commands, verbatim prompts, templates, and error-recovery paths. Its main weaknesses are token weight in a monolithic single file with zero progressive disclosure, and minor wordy passages that could be trimmed.

Suggestions

Move the Phase 0b entity-inventory flow into a reference file (e.g. references/entity-inventory.md) and keep a short trigger summary in SKILL.md, cutting the main file substantially.

Offload the entity-inventory and asset-manifest markdown templates into a templates/ or references/ file so the main body carries only the workflow.

Tighten the automation-guard note and the minimal-path exception paragraph — both restate conditions that could be expressed in one or two lines.

Dimension	Reasoning	Score
Conciseness	The body is dense, procedural, and assumes Claude's competence — no concept explanations, just exact commands, verbatim prompts, and templates. Minor wordiness remains (the image-generator guard note and the minimal-path exception paragraph could each be tightened).	4 / 5
Actionability	Guidance is copy-paste ready throughout: exact Grep patterns, verbatim Agent briefs, scripted AskUserQuestion prompts and options, complete file templates, and a deterministic ASSET-NNN assignment rule. Nothing is left as vague direction.	5 / 5
Workflow Clarity	Phases 0b–6 are clearly sequenced with explicit approval checkpoints at every phase, conflict surfacing between agents ("do NOT silently resolve"), an Error Recovery Protocol for blocked agents, and revise/re-spawn feedback loops after review.	5 / 5
Progressive Disclosure	The skill is a single 410-line file with no bundle references at all. Sections are well-labeled and navigable, but content that belongs in separate files is inlined — the ~90-line Phase 0b alternate flow, the entity-inventory and manifest file templates, and the mode-behavior notes could each be one-level-deep reference files.	3 / 5
	Total	17 / 20 Passed

Description

61%Weight 40%Scale 1-5

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 and domain-appropriate with good natural trigger terms, but it answers only "what" — the "when to use" half is absent, "After the art bible" being sequencing rather than trigger guidance. It also under-represents the skill's actual scope (levels, inventory, manifest).

Suggestions

Add an explicit trigger clause, e.g. "Use when speccing art assets for a system, level, or character, or when the user mentions asset specs, generation prompts, or the entity inventory."

Mention the level target type and the inventory/manifest outputs so the description covers the skill's full scope.

Include a common variation or two ("sprites", "art assets") to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	"Per-asset visual specs plus AI generation prompts from GDDs and character profiles" names the domain and two concrete actions with their source docs, but omits levels, the entity-inventory flow, and manifest maintenance — gaps broader than the 'minor' ones anchor 4 allows.	3 / 5
Completeness	The "what" is clear, but the "when" is only weakly implied by "After the art bible", with no explicit "Use when..." clause or equivalent trigger guidance, so completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural domain keywords are present — "visual specs", "AI generation prompts", "GDDs", "character profiles", "art bible" — which a game-dev user would plausibly say; a few natural terms are still missing ("levels", "sprites", "asset manifest", no synonyms or extensions).	4 / 5
Distinctiveness Conflict Risk	The game-art pipeline niche (GDDs, character profiles, art bible) is distinct, and "After the art bible" separates it from /art-bible itself, but it could still overlap with closely related sibling skills (ux-design, asset-audit) since no explicit trigger phrase disambiguates.	4 / 5
	Total	14 / 20 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: b21fa0f

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.