CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

asset-spec

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

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

77%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.

This is a strongly actionable, well-sequenced orchestration skill: every phase has concrete tools, verbatim prompts, templates, user-confirmation gates, and an explicit error-recovery feedback loop. Its weaknesses are structural and editorial — a 400-line monolithic body where the Phase 0b inventory flow and file templates could be split into reference files, and a few wordy passages that could be trimmed without losing clarity.

DimensionReasoningScore

Conciseness

The body is mostly dense project-specific instruction with almost no explanation of concepts Claude already knows, but several sections could be tightened: the long parenthetical note guarding external image-generator calls, the verbose minimal-path exception paragraph in Phase 1, and repeated "technical constraints not validated" phrasing across Phase 3 and the Error Recovery Protocol.

3 / 5

Actionability

Fully executable throughout: verbatim Grep patterns with glob and output modes, exact file paths, copy-paste agent briefs ("Ask: 'For each asset in this list, produce...'"), complete markdown templates for the inventory, spec, and manifest files, and an exact ID-assignment command — all covering the common system/level/character cases.

5 / 5

Workflow Clarity

Phases 0b through 6 are clearly sequenced with explicit validation checkpoints at every transition ("Do not proceed to Phase 3 without user confirmation", approval gates before every write), conflict surfacing between agents, and an Error Recovery Protocol providing feedback loops for blocked agents; file writes are gated and re-runs are protected by in-place update rules, so no destructive-operation cap applies.

5 / 5

Progressive Disclosure

No bundle files exist, so the entire ~400-line skill is inline, including the self-contained ~95-line Phase 0b inventory sub-flow and three full file templates that would fit naturally in references/; external doc pointers (.claude/docs/automation-modes.md, technical-preferences.md) are one level deep and clearly signaled, but the monolithic structure with inlined content that should be separate matches the anchor for "could be better organized".

3 / 5

Total

16

/

20

Passed

Description

53%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 states a clear, distinctive capability in a game-development niche with third-person voice and no fluff, but it reads as a pipeline position marker rather than trigger guidance. It lacks a "use when" clause covering the situations that call for it, and omits the level target type and technical-spec half of the skill's output.

Suggestions

Add an explicit trigger clause, e.g. "Use when speccing visual assets for a system, level, or character — writing per-asset descriptions, dimensions, formats, and AI image generation prompts."

Mention all three target types (system, level, character) and the technical constraint pass (dimensions, formats, naming) so the "what" covers the skill's actual output.

Include a few more natural trigger terms users would say — "asset specs", "level art", "sprites", "VFX" — to improve keyword coverage.

DimensionReasoningScore

Specificity

"Per-asset visual specs plus AI generation prompts" names the domain and two concrete deliverables, sourced "from GDDs and character profiles", but coverage is not comprehensive — level specs, technical constraints, and the inventory/manifest workflow are all unmentioned, matching the anchor for 1-2 concrete actions rather than several.

3 / 5

Completeness

The "what" is clear and concrete, but the only "when" is "After the art bible", which conveys pipeline ordering rather than when a user needs the skill; per the guideline, absent explicit user-trigger guidance completeness is capped at 3.

3 / 5

Trigger Term Quality

"visual specs", "AI generation prompts", "GDDs", and "character profiles" are natural terms in this domain, but common variations are missing — most notably "level", plus "art", "sprites", and "VFX" — fitting the anchor for relevant keywords with missing variations.

3 / 5

Distinctiveness Conflict Risk

A clear niche (per-asset visual spec generation for game GDDs) with "After the art bible" explicitly disambiguating it from the art-bible skill itself; minor overlap risk remains with adjacent art-pipeline skills because trigger terms are sparse.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.