typeui-cli
Guide for agentic tools to use the typeui.sh CLI for generating, updating, listing, and pulling design system skill files.
50
55%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/typeui-cli/SKILL.mdQuality
Discovery
32%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 specific CLI tool (typeui.sh) and lists basic CRUD operations, which provides some distinctiveness. However, it lacks a 'Use when...' clause, doesn't explain what design system skill files are or why they matter, and misses natural trigger terms users would employ. The description reads more like an internal note than a selection-guiding description.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create or manage design system components via typeui.sh, or mentions generating UI skill files.'
Include natural trigger terms users might say, such as 'UI components', 'design tokens', 'component library', 'typeui', or 'design system files'.
Clarify what 'design system skill files' are and what concrete outcomes the CLI produces (e.g., 'Generates component documentation, theme configurations, and token definitions').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (typeui.sh CLI, design system skill files) and lists some actions (generating, updating, listing, pulling), but these actions are somewhat generic and don't explain what the skill files contain or what the CLI actually produces. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'typeui.sh' and 'design system' as relevant keywords, but misses natural user terms like 'UI components', 'design tokens', 'component library', or other terms a user might actually say when needing this skill. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'typeui.sh CLI' is fairly distinctive and unlikely to conflict with other skills, but 'design system skill files' is vague enough that it could overlap with other design-system-related skills. | 2 / 3 |
Total | 7 / 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 well-structured CLI operator skill that is concise and respects Claude's intelligence. The recommended workflow with dry-run validation is a strong point. The main weakness is the lack of concrete examples showing expected CLI output, interactive prompt flows, or sample generated file content, which would significantly improve actionability.
Suggestions
Add example CLI output for at least one command (e.g., what `list` returns or what `pull --dry-run` previews) to improve actionability.
Include a brief example of what a generated/pulled skill file looks like so the agent can verify correctness of output.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. It avoids explaining what CLIs, Node.js, or design systems are, and every section provides specific, non-redundant information that Claude wouldn't already know. | 3 / 3 |
Actionability | Commands are concrete and copy-paste ready, but the skill relies heavily on interactive prompts (generate, list) without showing example outputs or expected responses. There are no concrete examples of what the generated files look like or what CLI output to expect. | 2 / 3 |
Workflow Clarity | The 'Recommended Agent Workflow' section provides a clear sequence with a validation checkpoint (dry-run first, then re-run). The troubleshooting section covers error recovery paths. The workflow is simple enough that the 4-step sequence with the dry-run preview step constitutes adequate validation. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but everything is in a single file. The registry behavior section and command reference could potentially be split out, and there are no references to external documentation files for advanced usage or provider configuration details. | 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
- bergside/typeui
- Commit
9bd113a
- 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.