design-review

Designer Who Codes: visual audit then fixes with atomic commits and before/after screenshots. Useful for tightening shipped UI before launch.

Quality

65%

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 ./skills/design-review/SKILL.md

Quality

Content

45%

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

The body functions as a thin catalogue pointer to an external repo rather than a self-contained skill: it is organized and lean but provides almost no executable workflow or guidance for the actual task it advertises.

Suggestions

Add a concrete, sequenced workflow for the advertised task (visual audit -> fix -> atomic commit -> before/after screenshot) with validation checkpoints instead of only linking to the upstream repo.

Replace the generic 'install the upstream bundle' direction with an explicit, copy-pasteable install command and the key paths the agent should read.

Inline at least one executable example of the audit/fix step so the skill is actionable without first fetching the external repository.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, but the 'How to use' section is generic catalogue boilerplate ('this catalogue entry advertises the skill...') that earns few tokens with skill-specific value, placing it in the mostly-efficient-but-could-be-tightened band.	2 / 3
Actionability	It offers a concrete-ish `open https://github.com/garrytan/gstack` command but defers the real work ('Inspect the upstream README for exact paths', 'install the upstream bundle') without executable steps for the actual audit/fix/commit/screenshot task, so guidance is incomplete and missing key details.	2 / 3
Workflow Clarity	Although the skill implies a multi-step process (audit, fix, atomic commit, screenshot), the body provides no sequenced steps and no validation checkpoints for it — it only describes installing an upstream bundle, matching the missing-sequence anchor.	1 / 3
Progressive Disclosure	At under 50 lines with no bundle files, the content is organized into clean shallow sections (What it does / Source / How to use) with a single-level external pointer, which the rubric allows to score 3 for simple well-organized skills.	3 / 3
	Total	8 / 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, third-person, and covers both capability and trigger context with a clear niche. Its main weakness is that the most natural trigger phrasing sits in frontmatter rather than the description text itself.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'visual audit', 'fixes with atomic commits', and 'before/after screenshots' — matching the anchor for listing several specific concrete actions rather than a vague domain mention.	3 / 3
Completeness	It states both what it does (visual audit then fixes with atomic commits and screenshots) and when to use it via the explicit clause 'Useful for tightening shipped UI before launch', satisfying both halves rather than leaving 'when' only implied.	3 / 3
Trigger Term Quality	The description carries some relevant natural terms ('visual audit', 'shipped UI', 'before launch') but leans technical ('atomic commits', 'Designer Who Codes') and the strongest user-facing triggers live in the separate frontmatter, so coverage of natural phrasing is partial.	2 / 3
Distinctiveness Conflict Risk	The pre-launch visual-audit niche with distinct triggers is unlikely to overlap with general skills, matching the clear-niche anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/design-review/SKILL.md
Commit: f2760fd

Reviewed: about 15 hours 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.