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.

54

Quality

61%

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

65%

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, but it is somewhat repetitive across the anti-pattern and tips sections, lacks a validation checkpoint, and keeps everything inline with no file separation.

Suggestions

Add a final validation step/checklist (e.g., "Review the generated DESIGN.md against the anti-pattern list before returning it") to close the workflow with an explicit checkpoint.

Consolidate the duplicated rules between sections 2–6 and the "List Anti-Patterns" section, and trim the overlapping Best Practices/Tips/Pitfalls sections to reduce repetition.

Move the full DESIGN.md output template into a references/ file (e.g., DESIGN_TEMPLATE.md) and signal it one level deep, keeping SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is actionable rule-list rather than padded concept explanation, but the anti-pattern list duplicates rules already in sections 2–6 and the Tips/Pitfalls sections restate earlier content, so it could be tightened.

2 / 3

Actionability

Guidance is concrete and copy-paste-ready: exact values ("stiffness: 100, damping: 20", "max 1 accent, saturation < 80%"), banned-font lists, named hex codes, and a full DESIGN.md output template.

3 / 3

Workflow Clarity

A clear numbered sequence (sections 1–9 then output format) is present, but there is no validation or completion checkpoint before emitting the generated DESIGN.md.

2 / 3

Progressive Disclosure

No bundle files exist and the body references no external files; the ~180-line skill is monolithic with the full output template and accumulated guidance inline rather than split into one-level-deep references.

2 / 3

Total

9

/

12

Passed

Description

57%

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 clearly communicates a niche, branded capability with strong "what" clarity, but omits an explicit "Use when..." trigger clause and uses branded/technical phrasing over natural user language.

Suggestions

Add an explicit "Use when..." clause naming the situations that should invoke this skill (e.g., generating or regenerating a Stitch design system).

Broaden trigger coverage with common user phrasings like "design system", "UI style guide", or "make my app look premium".

Lead with the single concrete action and trim jargon ("perpetual micro-motion", "hardware-accelerated") so the description reads as natural intent.

DimensionReasoningScore

Specificity

It names a concrete domain and one main action ("Generates agent-friendly DESIGN.md files") plus enforced quality axes, but does not list multiple distinct concrete actions like a top score requires.

2 / 3

Completeness

The "what" is clearly stated, but there is no explicit "Use when..." clause in the description text; trigger guidance lives only in the separate triggers field, capping completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

The separate triggers field offers several relevant phrases ("generate DESIGN.md", "stitch design taste"), but the description text leans on branded/technical terms ("perpetual micro-motion", "hardware-accelerated") and misses common user variations.

2 / 3

Distinctiveness Conflict Risk

The skill targets a specific branded niche (Google Stitch DESIGN.md generation) with distinct triggers, making conflict with other skills unlikely.

3 / 3

Total

9

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.