CtrlK
BlogDocsLog inGet started
Tessl Logo

react-ui

Opinionated constraints for building better interfaces with agents.

76

1.41x
Quality

64%

Does it follow best practices?

Impact

99%

1.41x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-mikeastock/skills/react-ui/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 body is an exemplary lean, directive constraint set — token-efficient, well-organized by concern, and concrete with named libraries, properties, and thresholds. The only gap is the absence of any assembled code example for the more involved rules.

DimensionReasoningScore

Conciseness

The body is a lean list of MUST/SHOULD/NEVER directives that assumes Claude's competence — it never explains what Tailwind, shadcn/ui, or compositor properties are. Every token earns its place with no padding. Below is not applicable; score 4 would require noticeable over-explanation, which is absent.

5 / 5

Actionability

Guidance is concrete and executable: named libraries (motion/react, clsx+tailwind-merge), named properties (transform, opacity), concrete thresholds (200ms, h-dvh), and one runnable command (npx shadcn@latest add <component>). Not score 5 because there are no assembled copy-paste code blocks (e.g. a cn() usage or AlertDialog snippet) — only inline code and directives.

4 / 5

Workflow Clarity

This is a single-purpose declarative constraint set, not a multi-step workflow; the simple-skill exception applies and the single action (apply these constraints when building UI) is unambiguous. Rules are grouped into clear, well-ordered sections by concern. No destructive/batch operation is present, so the validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed — the skill is a concise self-contained constraint list organized into clear sections (Stack, Components, Interaction, Animation, Typography, Layout, Performance, Design) with only an external shadcn/ui link. Per the simple-skills note, well-organized sections with no need for external references score 5.

5 / 5

Total

19

/

20

Passed

Description

36%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 is terse and names a clear niche, but it is abstract rather than action-oriented and omits any "Use when" trigger guidance. It reads as a tagline, not a triggerable skill description.

Suggestions

Add a concrete "Use when..." trigger clause naming natural user phrases, e.g. "Use when building UIs, components, or frontend interfaces with an agent."

List 1-2 concrete actions or scope cues (e.g. "Applies Tailwind, shadcn/ui, and accessibility constraints to React interfaces") so the what is specific, not just "opinionated constraints".

Include common synonyms/extensions users actually say (UI, frontend, React, components) to improve trigger term coverage and reduce overlap with generic style skills.

DimensionReasoningScore

Specificity

Names the domain ("building better interfaces with agents") but the only action framing is the abstract phrase "opinionated constraints" — no concrete actions are listed. It is above score 1 because a specific domain is named, but below score 3 because there are no concrete actions like specific build or apply steps.

2 / 5

Completeness

The "what" is vague ("opinionated constraints for building better interfaces") and there is no "when"/"Use when" trigger clause at all. The missing-trigger cap (3) applies, but since the what is itself vague the anchor-2 fit (vague what + no when) is better than anchor 3.

2 / 5

Trigger Term Quality

Includes relevant keywords ("interfaces", "agents", "building") but misses natural variations and synonyms a user would say (UI, frontend, React, components). Not score 4 because keyword coverage is thin with no synonyms; not score 2 because it does carry a couple of relevant domain terms.

3 / 5

Distinctiveness Conflict Risk

"building interfaces with agents" is a fairly specific niche, but the broad "opinionated constraints" framing and lack of explicit triggers create overlap risk with general frontend/style skills. Above score 2 (not very broad) but below score 4 (no explicit triggers to minimize conflict).

3 / 5

Total

10

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Dicklesworthstone/pi_agent_rust
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.