art-bible

Author the Art Bible — visual identity gating asset production. Run before /map-systems.

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/art-bible/SKILL.md

Quality

Content

81%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.

The skill body is a highly actionable, clearly sequenced orchestration workflow with strong validation checkpoints and feedback loops. Its weaknesses are verbosity in design-rationale prose and repeated boilerplate, plus a monolithic structure that could offload per-section detail to reference files.

Suggestions

Trim the spawn-policy rationale blockquotes and editorial asides ('single biggest cost lever', 'where production costs are born') to pure instruction — the batching rules stand without the justification.

State the per-section approval/write-once rule a single time in the Collaborative Protocol instead of repeating 'Write the approved section to file immediately' in all nine sections.

Move the per-section coverage lists and verbatim agent prompts to a reference file (e.g. references/section-briefs.md), keeping SKILL.md as the phase-level overview.

Dimension	Reasoning	Score
Conciseness	The body is dense with operational instruction rather than concept explanation, but contains trimmable design-rationale prose (the spawn-policy blockquotes, 'This is the single biggest cost lever in this skill', 'Ambiguity in asset standards is where production costs are born') and repeated per-section boilerplate ('Write the approved section to file immediately' appears in nearly every section). This matches anchor 3 — mostly efficient with some unnecessary explanation — rather than 4, where only minor instances would remain.	3 / 5
Actionability	Guidance is fully executable: exact Grep commands with patterns and flags for retrofit detection, verbatim agent-delegation prompts per section, exact AskUserQuestion option lists, concrete file paths, and explicit fallback rules. This matches anchor 5 — copy-paste-ready commands covering the common cases.	5 / 5
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit validation checkpoints: fail-fast on missing game concept, per-section user approval before every write, retrofit section-status detection, conflict-surfacing rules for agent disagreements, and a sign-off gate with a REJECT→re-draft→REVISED feedback loop. This matches anchor 5.	5 / 5
Progressive Disclosure	External material is well-signaled and one level deep (director-gates.md, automation-modes.md, workflow-modes.md, technical-preferences.md, templates/art-bible.md), but the ~390-line body is somewhat monolithic — per-section coverage lists and delegation prompts could live in a reference file. This matches anchor 4 (good structure, minor organization gaps) rather than 5 (content appropriately split).	4 / 5
	Total	17 / 20 Passed

Description

66%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 distinct and reasonably specific, naming a concrete artifact and its pipeline role, with explicit sequencing guidance. Its main gaps are the absence of user-need trigger phrasing ('Use when...') and natural keyword variations like 'art style' or 'art direction'.

Suggestions

Add an explicit 'Use when...' clause with user-need triggers, e.g. 'Use when defining the game's art style, visual direction, or art standards before asset production.'

Include natural synonym keywords users would say — 'art style', 'art direction', 'visual direction', 'color palette' — alongside 'Art Bible'.

Briefly enumerate what authoring the Art Bible produces (visual identity statement, color system, asset standards) to lift specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	"Author the Art Bible" names the domain ("visual identity gating asset production") and one concrete action, matching the 'names domain and 1-2 concrete actions' anchor. It does not list multiple specific actions, so it falls short of anchor 4.	3 / 5
Completeness	The 'what' is clear ("Author the Art Bible — visual identity gating asset production") and the 'when' is explicit ("Run before /map-systems"), but the 'when' is pipeline ordering rather than user-need triggers, so it fits anchor 4 ('when' could be more explicit) rather than 5.	4 / 5
Trigger Term Quality	"Art Bible", "visual identity", and "asset production" are relevant natural terms, but common variations users would actually say ("art style", "art direction", "visual direction", "color palette") are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Art Bible" is a distinctive named deliverable with a clear niche (visual identity gating asset production) and an explicit pipeline position, giving minimal overlap risk with sibling skills — a clear match for anchor 5.	5 / 5
	Total	15 / 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/art-bible/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.