CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/stitch-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is highly actionable with precise values and a complete output template, and the synthesis workflow is clearly sequenced. The main weakness is redundancy: the anti-patterns section and the three closing advisory sections restate rules already covered earlier.

Suggestions

De-duplicate the anti-patterns: make section 9 reference the earlier sections for already-stated bans (e.g. color, typography, hero, layout) and keep only net-new anti-patterns there, or merge section 9 into a single consolidated banned list and remove the scattered repeats.

Consolidate 'Best Practices', 'Tips for Success', and 'Common Pitfalls' into one concise section to reduce overlap and trim tokens.

Add an explicit final validation step, e.g. 'Review the generated DESIGN.md against the anti-pattern list before delivering', to close the workflow with a checkpoint.

DimensionReasoningScore

Conciseness

The body is dense and opinionated with content Claude would not already know, but section 9 ('List Anti-Patterns') restates bans already covered in sections 2–8 (e.g. no pure black, no neon glows, no 3-column grids, no centered Heroes), and the closing 'Best Practices', 'Tips for Success', and 'Common Pitfalls' sections overlap, so it could be tightened.

3 / 5

Actionability

Highly actionable for an instruction-only skill: exact hex codes (#F9FAFB, #18181B), precise values (stiffness:100, damping:20, 65ch, 44px, min-h-[100dvh], clamp(3rem,8vw,6rem)), named fonts, and a complete copy-paste-ready DESIGN.md output template covering the common cases.

5 / 5

Workflow Clarity

A clear numbered 1–9 synthesis sequence (Atmosphere → Color → Typography → Hero → Components → Layout → Responsive → Motion → Anti-patterns) flows into a defined output format; the only gap is the absence of an explicit validation/review checkpoint, which is a minor gap for a generative (non-destructive) task.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, a fenced output template, and distinct advisory sections; no bundle files exist and none are needed. Minor organization redundancy across the three closing advisory sections keeps it just below a 5.

4 / 5

Total

16

/

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.

The description is specific, well-keyworded, and clearly distinct, but it omits any explicit 'Use when...' trigger guidance, which caps completeness. Adding a concrete usage trigger clause would raise the score.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when generating or refining a DESIGN.md for Google Stitch, or when the user wants a premium, anti-generic design system for Stitch screen generation.'

Include a few more natural trigger synonyms/extensions users might say, such as 'design system', 'Stitch design language', or 'DESIGN.md' alongside 'DESIGN.md files', to broaden trigger coverage.

Tighten the buzzwordy phrase 'premium, anti-generic UI standards' by pairing it with a more concrete capability verb to keep specificity high.

DimensionReasoningScore

Specificity

Names the domain ('Generates agent-friendly DESIGN.md files') and lists several concrete enforced dimensions ('strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance'), with only minor coverage gaps relative to the comprehensive 5 anchor.

4 / 5

Completeness

The 'what' is explicit (generates DESIGN.md files enforcing specific UI standards), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good natural keyword coverage including 'DESIGN.md', 'Google Stitch', 'typography', 'color', and 'micro-motion' that a user would plausibly say, though a few common synonyms and variants are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche ('Semantic Design System Skill for Google Stitch' producing DESIGN.md files) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Leonxlnx/taste-skill
Reviewed

Table of Contents

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.