CtrlK
BlogDocsLog inGet started
Tessl Logo

stitch-ui-design

Expert guidance for crafting effective prompts in Google Stitch, the AI-powered UI design tool by Google Labs. This skill helps create precise, actionable prompts that generate high-quality UI designs for web and mobile applications.

42

Quality

43%

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-ui-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%Scale 1-5

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

This skill provides a comprehensive collection of prompt examples and templates for Google Stitch, which is its primary strength—the examples are concrete and well-structured. However, it is significantly over-long for a skill file, explaining concepts Claude already knows, including motivational conclusions, and inlining content that should be in separate reference files. The workflows lack validation checkpoints and the monolithic structure hurts discoverability.

Suggestions

Cut the 'What is Google Stitch?' section, the 'Conclusion' section, and the 'When to Use' section—these add no actionable value and waste tokens.

Extract the 'Common Use Cases' section into a separate EXAMPLES.md file and reference it from the main skill, reducing the main file to core principles and the template.

Trim anti-patterns to a compact table format (❌ vs ✅ in two columns) rather than full code blocks with headers and separators for each pair.

Add explicit validation steps to the iteration and export workflows, e.g., 'Verify the generated design matches requirements before proceeding to export.'

DimensionReasoningScore

Conciseness

The skill is significantly verbose at ~300+ lines. It explains what Google Stitch is (Claude can look this up), includes a conclusion section with motivational advice, repeats the description from the frontmatter, explains basic concepts like 'why it works,' and has extensive anti-pattern sections that largely duplicate the earlier examples. Many sections could be cut in half without losing actionable content.

2 / 5

Actionability

The skill provides numerous concrete, copy-paste-ready prompt examples across multiple use cases (landing pages, mobile apps, dashboards, forms). It includes a structured template and specific iteration strategies. However, since this is a prompting guide rather than a code skill, the 'actionability' is in prompt templates rather than executable code—and some guidance remains somewhat generic (e.g., 'refactor generated code for production standards').

4 / 5

Workflow Clarity

Several workflows are outlined (iteration strategies, design-to-code, rapid prototyping) with numbered steps, but they lack validation checkpoints. The annotation workflow is the most complete but still doesn't include verification steps. The export workflow lists 'before exporting' checks but doesn't frame them as explicit validation gates. For a non-destructive creative tool this is less critical, but the workflows remain surface-level.

3 / 5

Progressive Disclosure

The entire skill is a monolithic document with no bundle files or references to external files. At 300+ lines, the common use cases, anti-patterns, integration workflows, and tips sections could easily be split into separate reference files. Everything is inlined with no navigation structure beyond section headers, making it hard to scan efficiently.

2 / 5

Total

11

/

20

Passed

Description

39%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 identifies a clear niche (Google Stitch prompt crafting) but is too vague about what concrete actions the skill performs and entirely lacks a 'Use when...' clause. It uses second-person voice ('This skill helps') which slightly undermines professionalism, and the actual capabilities described amount to little more than 'helps write prompts' without specifying techniques, outputs, or concrete guidance offered.

Suggestions

Add a 'Use when...' clause with trigger terms like 'Google Stitch', 'Stitch prompt', 'AI UI design', 'generate UI mockup', or 'design tool prompt'.

Replace vague language like 'expert guidance' and 'helps create precise, actionable prompts' with concrete actions such as 'generates structured Stitch prompts specifying layout, components, color schemes, and responsive breakpoints'.

Rewrite in third person active voice (e.g., 'Generates optimized prompts for Google Stitch...') instead of 'This skill helps create...'.

DimensionReasoningScore

Specificity

Names the domain (Google Stitch, AI-powered UI design) but the actions are vague — 'crafting effective prompts' and 'create precise, actionable prompts' are generic and don't describe concrete actions like 'generates prompt templates', 'structures design specifications', or 'defines layout constraints'.

2 / 5

Completeness

Has a vague 'what' (helps create prompts for Google Stitch) but completely lacks a 'when' clause. There is no explicit trigger guidance such as 'Use when...' which per the rubric should cap completeness at 3, and the 'what' itself is too vague to merit a 3.

2 / 5

Trigger Term Quality

Includes relevant keywords like 'Google Stitch', 'prompts', 'UI design', 'web and mobile applications', and 'Google Labs'. However, it misses natural user phrases like 'Stitch prompt', 'AI UI generator', 'design tool prompt', or 'generate UI'.

3 / 5

Distinctiveness Conflict Risk

Google Stitch is a specific enough tool that this skill is mostly distinct from general prompt engineering or UI design skills. However, it could overlap with general prompt crafting skills or other UI design tool skills without clearer boundaries.

4 / 5

Total

11

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.