art-bible

Guided, section-by-section Art Bible authoring. Creates the visual identity specification that gates all asset production. Run after /brainstorm is approved and before /map-systems or any GDD authoring begins.

Quality

76%

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/art-bible/SKILL.md

Quality

Content

77%

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

A well-engineered, highly actionable orchestration workflow with clear sequencing, validation gates, and conflict-surfacing feedback loops. Its main weaknesses are mild verbosity from repetition and a monolithic single-file structure that does not offload detail into bundle references.

Suggestions

Factor the repeated per-section authoring pattern into a single named loop or a reference file (e.g., references/section-template.md) to remove the repeated 'Write the approved section to file' instructions and tighten conciseness.

Move the Phase 6 next-steps option pool into a reference (e.g., references/next-steps.md) so the core SKILL.md reads as an overview, improving progressive disclosure for a skill of this length.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly free of concepts Claude already knows, but it could be tightened: 'Write the approved section to file immediately' repeats across eight sections and the Phase 6 option pool is elaborate, so not every token earns its place.	2 / 3
Actionability	Highly actionable for an instruction skill: copy-paste-ready agent-delegation prompts ('Ask: ...'), exact file paths, concrete AskUserQuestion option lists, and per-section coverage checklists give specific executable guidance.	3 / 3
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit validation checkpoints (missing game-concept.md fail message, retrofit section-status table, Phase 5 director-gate verdict handling) and feedback loops that surface agent conflicts via AskUserQuestion rather than silently resolving them.	3 / 3
Progressive Disclosure	The file is well-organized into phases and signals one-level-deep external docs (director-gates.md, technical-preferences.md), but no bundle reference files exist and large inline detail (per-section delegation prompts, the Phase 6 option pool) could be split out for a skill this size.	2 / 3
	Total	10 / 12 Passed

Description

75%

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

A strong, niche-specific description that clearly states what it does and when to run it within the pipeline. It is capped mainly by a thin action list and the absence of an explicit user-utterance 'Use when...' trigger clause.

Suggestions

Add an explicit 'Use when the user mentions an art bible, visual identity, art direction, or needs to define the look of the game' trigger clause to lift trigger_term_quality and completeness margins.

Enumerate one or two more concrete actions (e.g., 'defines color system, shape language, and asset standards') so specificity reaches the multiple-concrete-actions bar.

Dimension	Reasoning	Score
Specificity	Names the domain ('section-by-section Art Bible authoring') and one concrete action ('Creates the visual identity specification that gates all asset production'), but lists only ~two actions rather than the multiple specific concrete actions the score-3 anchor expects.	2 / 3
Completeness	It answers both what ('Guided, section-by-section Art Bible authoring...') and when with equivalent explicit trigger guidance ('Run after /brainstorm is approved and before /map-systems or any GDD authoring begins'), satisfying the what-and-when bar.	3 / 3
Trigger Term Quality	Relevant niche terms are present ('Art Bible', 'visual identity', 'GDD', 'asset production') that a game-dev user would say, but there is no explicit 'Use when...' clause enumerating common trigger variations, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The art-bible/visual-identity niche is highly specific with a distinct pipeline position (after /brainstorm, before /map-systems/GDD authoring), making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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/art-bible/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.