stitch
Generate UI designs and frontend code with Google Stitch via MCP. Use when asked to create screens, mockups, UI designs, or generate frontend code from text descriptions. Supports desktop, mobile, and tablet layouts.
92
88%
Does it follow best practices?
Impact
100%
2.12xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does, when to use it, and through which tool. It uses natural trigger terms, provides explicit 'Use when' guidance, and is distinctive enough to avoid conflicts with other skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Generate UI designs', 'frontend code', supports 'desktop, mobile, and tablet layouts'. Specifies the tool (Google Stitch via MCP) and the types of outputs clearly. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate UI designs and frontend code with Google Stitch via MCP) and 'when' (explicit 'Use when asked to create screens, mockups, UI designs, or generate frontend code from text descriptions'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'screens', 'mockups', 'UI designs', 'frontend code', 'text descriptions', 'desktop', 'mobile', 'tablet'. These cover common variations of how users would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific tool mention (Google Stitch via MCP) and the clear niche of UI design generation from text descriptions. Unlikely to conflict with generic coding or design skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent concrete examples and clear workflows. Its main weakness is length — it packs a lot of reference material (device types, model selection, prompt engineering, error tables) inline that could be split into separate files for better progressive disclosure. The content is well-organized and provides genuinely useful guidance for working with the Stitch MCP tool.
Suggestions
Consider moving the device types table, model selection details, and prompt engineering section into a separate REFERENCE.md file, keeping only the most essential quick-start info in the main skill.
The 'Weak Prompts' examples could be removed — Claude can infer what makes a weak prompt from the strong examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some content that could be tightened. The device types table, model selection section, and prompt engineering examples add useful value but the overall document is quite long. The tools table is a reference Claude could use but some entries are self-explanatory. The weak prompts section and some explanatory text could be trimmed. | 2 / 3 |
Actionability | Excellent actionability throughout. Every workflow has concrete, copy-paste-ready bash commands with realistic parameters. The prerequisites section has exact setup commands, the examples section shows complete end-to-end flows, and parameters are clearly documented with specific values and defaults. | 3 / 3 |
Workflow Clarity | Workflows are clearly sequenced with explicit steps. The iteration workflow provides a clear 5-step process. The complete design flow example shows the full sequence from project creation to code download. The note 'Generation takes 1–3 minutes. Do not retry' is an important validation checkpoint. The response handling section includes feedback loops for suggestions. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a fairly long monolithic document (~180 lines of content). The device types table, model selection, prompt engineering tips, and error handling could potentially be split into referenced files. However, the sections are well-organized and navigable with clear headers. | 2 / 3 |
Total | 10 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.