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 too vague and abstract to be useful for skill selection. It fails to specify concrete actions, lacks natural trigger terms, provides no guidance on when to use the skill, and is not distinguishable from other potentially overlapping skills. It reads more like a tagline than a functional description.
Suggestions
Replace abstract language with concrete actions the skill performs, e.g., 'Provides layout patterns, component guidelines, and interaction rules for designing agent-facing UIs.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when designing chat interfaces, agent dashboards, conversational UIs, or building front-ends for AI agents.'
Clarify the specific domain niche to reduce conflict risk — specify what kind of interfaces (web, chat, dashboard) and what kind of agents (AI assistants, chatbots, autonomous agents).
| 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 neither clearly explains what the skill does nor when Claude should use it. There is no 'Use when...' clause or equivalent explicit trigger guidance. | 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', 'agent UI', 'chatbot interface', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'building better interfaces with agents' could overlap with UI design skills, agent development skills, UX guidelines, or many other domains. There is nothing to distinguish it clearly. | 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 file. It is maximally concise, using a consistent MUST/SHOULD/NEVER pattern that makes every rule immediately actionable. The categorical organization is clean and logical, and the content avoids explaining anything Claude already knows while providing specific, opinionated guidance that Claude wouldn't have by default.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line is a constraint or rule that Claude wouldn't inherently know as project-specific opinion. No filler, no explanations of what Tailwind or shadcn are. Each bullet earns its place. | 3 / 3 |
Actionability | Rules are concrete and directly actionable: specific utility names (`cn`, `text-balance`, `tabular-nums`), specific tools (`npx shadcn@latest add`), specific thresholds (`200ms`), and specific CSS properties to avoid. Claude can apply these immediately without ambiguity. | 3 / 3 |
Workflow Clarity | This is a constraint-based skill rather than a multi-step workflow, so sequential steps aren't applicable. The rules are clearly categorized by domain (Stack, Components, Interaction, Animation, etc.) with unambiguous MUST/SHOULD/NEVER modifiers, making the priority and enforcement level of each rule crystal clear. | 3 / 3 |
Progressive Disclosure | Content is well-organized into logical sections with clear headings. At under 80 lines with no need for external deep-dives, the single-file format is appropriate. The one external link (shadcn/ui docs) is properly signaled. | 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
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.