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.

56

Quality

64%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/stitch-ui-design/SKILL.md

The canonical home for this skill is stitch-ui-design in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured and actionable with concrete prompt templates and clear iterative workflows, but it is verbose and fails to route to the existing reference bundle files, inlining example content that duplicates them.

Suggestions

Link the bundle files from the body — e.g., under a 'Examples' section add 'See [prompt-examples.md](references/prompt-examples.md)' and under advanced topics 'See [advanced-techniques.md](references/advanced-techniques.md)' — so the orphaned references become navigable.

Move the inlined Common Use Cases examples into prompt-examples.md and keep only a brief pointer in SKILL.md, reducing token cost and duplication.

Trim the repeated poor/effective prompt pairs and the prose explanation of what Stitch is, keeping only the distinctive guidance Claude would not already infer.

DimensionReasoningScore

Conciseness

The body is mostly useful actionable prompting guidance, but at ~370 lines it is padded with repeated poor/effective prompt pairs and a Common Use Cases section whose examples overlap with the bundled prompt-examples.md, so it could be tightened considerably.

3 / 5

Actionability

Provides copy-paste-ready prompts and a concrete prompt structure template covering common cases (dashboards, landing pages, mobile apps, forms), with only minor gaps in edge-case handling.

4 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced (the 4-step annotation workflow, progressive refinement, and Stitch→Figma→Code handoff); this is a low-risk iterative design skill so the absence of hard validation checkpoints is acceptable, leaving only minor gaps.

4 / 5

Progressive Disclosure

The body is well-organized with clear section headers, but the two bundle files (references/advanced-techniques.md and references/prompt-examples.md) are never referenced or linked from the body, and use-case/example content that belongs in those files is inlined instead.

3 / 5

Total

14

/

20

Passed

Description

65%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 clearly identifies a distinct, named-tool niche and states what the skill does, but it lacks an explicit 'Use when...' trigger clause and describes a single repeated capability rather than several distinct actions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating UI designs in Google Stitch, converting prompts or sketches to web/mobile interfaces, or exporting Stitch designs to code or Figma.'

Broaden specificity beyond a single prompting action by listing distinct capabilities (e.g., text-to-UI generation, image-to-UI conversion, multi-screen flows, variant/annotation refinement, export to HTML/Figma/code).

DimensionReasoningScore

Specificity

Names the domain ("crafting effective prompts in Google Stitch") and a concrete action ("create precise, actionable prompts that generate high-quality UI designs for web and mobile applications"), but the actions are essentially one repeated capability rather than several distinct ones, so it does not reach comprehensive coverage.

3 / 5

Completeness

The 'what' is clearly stated (prompting guidance for Stitch to generate UI designs), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes the named tool trigger ("Google Stitch") plus natural task terms ("UI design", "prompts", "web and mobile applications") a user would say, with only minor synonyms missing.

4 / 5

Distinctiveness Conflict Risk

Tied to a specific named tool ("Google Stitch, the AI-powered UI design tool by Google Labs") with a clear niche (UI design prompting), giving it distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

15

/

20

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
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.