design-review

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

Quality

66%

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

57%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 body is a well-organized, token-efficient catalogue stub, but it delegates the entire actual workflow to an external repository without any executable install steps or actionable audit/fix guidance of its own. It reads as an advertisement rather than an instruction file.

Suggestions

Replace the `open https://github.com/garrytan/gstack` placeholder with an actual clone/install command for the upstream bundle (or inline the concrete installation steps), since "install the upstream bundle" currently has no executable path.

Add at least a minimal inline outline of the visual-audit workflow (what to inspect, how commits are structured, how before/after screenshots are captured) so the skill is useful without round-tripping to the external README.

Trim the duplicated content: the body restates the frontmatter description verbatim and repeats the upstream URL in both the Source section and the code block.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~25-line catalogue entry with no concept explanations Claude already knows. It only misses a 5 because it repeats the frontmatter description verbatim and duplicates the upstream URL in both the Source section and the code block.	4 / 5
Actionability	The core instruction "install the upstream bundle into your active agent's skills directory" has no accompanying command, and the only code block is `open https://github.com/garrytan/gstack` plus "Inspect the upstream README for exact paths" — high-level hints with the specific steps to execute missing. There is no pseudocode or partial executable path that would justify a 3.	2 / 5
Workflow Clarity	A rough three-step sequence is present (inspect upstream README, install bundle, invoke by name or trigger phrases), but the install step is undefined and there are no validation checkpoints. This is not a destructive or batch operation, so the cap at 3 is not the binding reason — the gaps versus the 4 anchor are.	3 / 5
Progressive Disclosure	The skill is under 50 lines, ships no bundle files, and needs no external references beyond the clearly signaled one-level-deep upstream link, with well-organized sections (What it does, Source, How to use) making navigation trivial — the short-skill guideline for a 5 applies.	5 / 5
	Total	14 / 20 Passed

Description

75%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.

A solid description that states concrete actions and an explicit use scenario in third person. Its main gaps are the missing natural synonyms for the skill's own name and slightly vague coverage of what the visual audit actually inspects.

Dimension	Reasoning	Score
Specificity	"visual audit then fixes with atomic commits and before/after screenshots" lists several concrete actions, matching the several-specific-actions-with-minor-gaps anchor. It falls short of 5 because it never says what the audit examines or what the fixes entail.	4 / 5
Completeness	Both what ("visual audit then fixes with atomic commits and before/after screenshots") and when ("Useful for tightening shipped UI before launch") are answered, so the missing-when cap at 3 does not apply. The when-clause is explicit but less trigger-phrase-specific than the 5 anchor's "when the user mentions PDFs, forms, or document extraction".	4 / 5
Trigger Term Quality	Natural phrases like "visual audit", "before/after screenshots", and "before launch" give good keyword coverage a user would actually say. Not 5: common synonyms such as "design review" (the skill's own name), "UI polish", or "design QA" are absent from the description.	4 / 5
Distinctiveness Conflict Risk	"tightening shipped UI before launch" combined with "atomic commits" carves a pre-launch visual-QA niche that is mostly distinct from generic skills. Minor overlap risk remains with general design or code-review skills, keeping it below the clear-niche 5 anchor.	4 / 5
	Total	16 / 20 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: 1b47e60

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.