stitch-design-taste

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

Quality

69%

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/stitch-skill/SKILL.md

Quality

Content

68%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.

A highly actionable, opinionated skill body with concrete values and a complete output template that Claude can execute directly. Its weaknesses are redundancy in the closing best-practices/tips/pitfalls sections and the absence of a final validation pass to check the generated DESIGN.md against the enforced rules.

Suggestions

Merge "Best Practices", "Tips for Success", and "Common Pitfalls to Avoid" into the relevant analysis sections or a single short checklist — they restate the nine rules at ~25 lines of extra tokens.

Add an explicit final validation step, e.g. "Before delivering, re-check the DESIGN.md against the anti-pattern list and the mandatory color/typography constraints."

Consider moving the full DESIGN.md output template into a references/ file (e.g. references/template.md) and keeping only a short structural summary in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, opinionated, non-generic rule content (hex constraints, font bans, exact spring values), but "Best Practices", "Tips for Success", and "Common Pitfalls to Avoid" largely restate the nine analysis sections — roughly 25 lines of repetition that could be merged. It is not a 4 because that duplicated tail is more than a minor trim.	3 / 5
Actionability	As an instruction-only skill it provides fully executable, copy-paste-ready guidance: exact values (stiffness: 100, damping: 20; 44px touch targets; min-h-[100dvh]; clamp(3rem, 8vw, 6rem)), named fonts, and a complete DESIGN.md output template covering the common case.	5 / 5
Workflow Clarity	The sequence is clearly listed (numbered analysis steps 1–9 followed by the output format), but there is no validation or review checkpoint confirming the generated DESIGN.md against the stated rules — checkpoints are entirely implicit. Not a 4 because the missing self-check is the main point of the workflow's end, not a minor gap.	3 / 5
Progressive Disclosure	No bundle files exist and none are referenced, so there are no dangling or nested references; the single file is well-organized with clear numbered sections. It falls short of 5 only because ~180 lines of inlined material (the full output template and the anti-pattern catalogue) could be split into reference files.	4 / 5
	Total	15 / 20 Passed

Description

70%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 specific, distinctive, third-person description that clearly states what the skill produces and the design domains it enforces. Its main weakness is the absence of any "when to use" guidance, which caps completeness and limits discoverability for users who describe their need in different words.

Suggestions

Append an explicit trigger clause, e.g. "Use when generating DESIGN.md files for Google Stitch, or when the user asks for a premium or anti-generic design system, semantic design language, or Stitch screen generation."

Add a few natural user phrasings ("UI design standards", "design guidelines", "design language") to broaden keyword coverage beyond the current terminology.

Trim stacked qualifiers ("agent-friendly... premium, anti-generic") slightly; they add length without adding trigger value.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("Generates agent-friendly DESIGN.md files") and enumerates specific sub-domains ("strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance") in third person, matching the 'several specific actions with minor gaps' anchor rather than the comprehensive 5-anchor.	4 / 5
Completeness	The "what" is clear and concrete, but the description field contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3. It is not a 4 because the "when" is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Natural keywords are present ("Google Stitch", "DESIGN.md", "design system", "premium", "UI standards", "typography", "color") but common variations users might say, such as "UI design" or "design guidelines", are missing — good coverage, not comprehensive.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — generating DESIGN.md files specifically for Google Stitch screen generation — with distinct triggers and minimal overlap with generic design or document skills.	5 / 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/stitch-skill/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.