react-ui
Opinionated constraints for building better interfaces with agents.
67
50%
Does it follow best practices?
Impact
99%
1.41xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-mikeastock/skills/react-ui/SKILL.mdQuality
Discovery
0%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 description is extremely vague and abstract, providing no concrete actions, no trigger terms, and no guidance on when to use the skill. It reads more like a tagline than a functional description, making it nearly impossible for Claude to correctly select this skill from a pool of options.
Suggestions
Replace abstract language with specific concrete actions, e.g., 'Defines layout patterns, component hierarchies, and interaction flows for agent-driven UIs' instead of 'opinionated constraints for building better interfaces'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when designing or building user interfaces for AI agents, chatbots, or conversational UIs'.
Clarify the domain by specifying what kind of interfaces and agents are covered (e.g., chat UIs, tool-use agents, multi-agent dashboards) to reduce conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('opinionated constraints', 'better interfaces') without listing any concrete actions. It does not describe what the skill actually does in actionable terms. | 1 / 3 |
Completeness | The description fails to clearly answer either 'what does this do' or 'when should Claude use it'. There is no 'Use when...' clause or equivalent explicit trigger guidance, and the 'what' is extremely vague. | 1 / 3 |
Trigger Term Quality | The terms 'opinionated constraints', 'interfaces', and 'agents' are abstract and not natural keywords a user would say when seeking help. There are no concrete trigger terms like 'UI', 'design patterns', 'agent framework', or specific technologies. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it could overlap with any skill related to UI design, agent development, coding best practices, or design guidelines. 'Building better interfaces with agents' is not a clear niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent constraint-based skill that is lean, specific, and immediately actionable. It uses RFC-style keywords (MUST/SHOULD/NEVER) consistently to communicate priority, covers a comprehensive set of UI concerns without any filler, and organizes rules into intuitive categories. The skill exemplifies what a good opinionated guideline document should look like.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line is a concrete constraint or rule. No explanations of what Tailwind CSS is, no tutorials on how animations work, no padding. Each bullet earns its place as a specific, opinionated directive that Claude wouldn't know from general training. | 3 / 3 |
Actionability | The rules are highly specific and directly actionable: exact utility classes (`text-balance`, `tabular-nums`, `h-dvh`), specific libraries (`motion/react`, `tw-animate-css`), exact CLI commands (`npx shadcn@latest add <component>`), and concrete CSS properties to animate or avoid. Claude can apply these constraints immediately without ambiguity. | 3 / 3 |
Workflow Clarity | This is a constraint/rule-based skill rather than a multi-step workflow skill. The rules are clearly categorized into logical sections (Stack, Components, Interaction, Animation, Typography, Layout, Performance, Design) with unambiguous MUST/SHOULD/NEVER directives. For this type of skill, the organization provides all the clarity needed. | 3 / 3 |
Progressive Disclosure | For a skill under 80 lines with no need for external references, the content is well-organized into clearly labeled sections that serve as a scannable reference. The single external link to shadcn/ui docs is appropriate. No content needs to be split out into separate files. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
bbc5ade
- 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.