design-review

Reviews a game design document for completeness, internal consistency, implementability, and adherence to project design standards. Run this before handing a design document to programmers.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body is a well-sequenced, highly actionable multi-phase workflow with strong validation and feedback loops. Its weaknesses are emphatic redundancy that hurts token efficiency and a total absence of progressive disclosure — everything lives inline in one large file.

Suggestions

Move the large domain-to-agent table, the Phase 4 output template, and the review-log format into separate reference files and link to them, reducing SKILL.md to an overview.

Tighten redundant emphasis (e.g. collapse "MANDATORY... Do not skip it" and the CRITICAL subagent block to a single firm statement).

Dimension	Reasoning	Score
Conciseness	Largely efficient and actionable, but contains emphatic redundancy — e.g. "This phase is MANDATORY in full mode. Do not skip it" and the multi-sentence CRITICAL block restating the subagent point several ways — that could be tightened; not a 1 because it does not pad with concepts Claude already knows, not a 3 because some tokens do not earn their place.	2 / 3
Actionability	Provides a concrete section checklist, a domain-to-agent mapping table, named specialists, exact file paths (e.g. "design/gdd/reviews/[doc-name]-review-log.md"), and a copy-paste output template; not a 2 because guidance is complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	Phases 0–5 are clearly sequenced with explicit validation checkpoints (dependency-graph Glob check, prior-review check) and a feedback loop (re-review after revision); not a 2 because validation is explicit, and a checklist is present in Phase 2.	3 / 3
Progressive Disclosure	Well-organized into phases but presented as a single 269-line monolithic file with no bundle/reference files (references/, scripts/, assets/ are empty) and inline content (the agent table, output template, review-log format) that could be split out; not a 1 because organization is good, not a 3 because no one-level-deep references are used.	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 clearly niched, with an explicit use-when trigger. Its main weakness is limited trigger-term variation — it omits common shorthand like "GDD" or "design doc" that users would naturally say.

Suggestions

Add common trigger variations such as "GDD" and "design doc" to broaden natural keyword coverage.

Consider phrasing the trigger as an explicit "Use when..." clause to mirror the good-example pattern more closely.

Dimension	Reasoning	Score
Specificity	Names four concrete review dimensions — "completeness, internal consistency, implementability, and adherence to project design standards" — matching the anchor for multiple specific concrete actions; not a 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly states what (the four review dimensions) and when ("Run this before handing a design document to programmers"), satisfying both halves with an explicit trigger; not a 2 because the when clause is explicit rather than implied.	3 / 3
Trigger Term Quality	Includes natural terms like "game design document" and "design document" but misses common variations users would say ("GDD", "design doc"); not a 3 due to limited coverage, not a 1 because the terms present are natural.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (game design document review) with distinct triggers unlikely to fire for unrelated skills; not a 2 because it is not merely domain-named but fully scoped.	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/design-review/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.