CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

a2ui-playground

Compose UI from the A2UI Playground catalog (CopilotKit Gen UI 2.0 standard components, charts, maps, data views, inputs, domain cards and macros) in A2UI Express. Use when an answer is better shown than told: dashboards, comparisons, forms, plans, maps.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/showcases/a2ui-playground/skills/generated/express/a2ui-playground/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A highly actionable catalog skill whose terse, complete signatures and worked examples leave no ambiguity about how to instantiate components. Its weaknesses are token-scale: heavy verbatim repetition of shared container and chart properties, and a monolithic single-file structure with no progressive disclosure.

Suggestions

Factor the shared container props (onVisible, align, justify, wrap, gap) and the chart 'format' enum into one 'Common props' section and reference it from each component, instead of repeating the same 6-8 lines under ~15 components and every chart type.

Move the full component and function signature catalog into a references/ file (e.g., references/catalog.md), keeping the design rules and the three worked examples in SKILL.md as the always-loaded overview.

Within the catalog, group components by purpose (charts, inputs, layout, domain cards, macros) with a one-line index per group so the reference is navigable without scanning every signature.

DimensionReasoningScore

Conciseness

Entries are telegraphic and contain only non-obvious catalog data (e.g., 'Collapsible items (FAQs, details, per-file notes)'), but the onVisible/align/justify/wrap/gap property docs are repeated verbatim under ~15 container components and 'Must be one of: number/currency/percent/compact' under every chart. Mostly efficient, but the duplicated blocks are a clear tightening opportunity.

3 / 5

Actionability

Exact positional signatures with constraints, defaults, and data shapes ('data [{x,y,series?}]') plus three complete executable examples inside <a2ui> fences (e.g., the sales-dashboard example binding $/form/email and using Event(...)) provide copy-paste-ready guidance covering common cases.

5 / 5

Workflow Clarity

The design rules give a clear decision mapping ('comparisons -> ComparisonTable, plans/options -> RadioGroup...') and sequencing ('Lead with a Heading'), and composition is non-destructive so no validation loop is required. Minor gaps remain: no explicit compose-and-check procedure is laid out.

4 / 5

Progressive Disclosure

The body has clear sections ('Positional Component Signatures', 'Positional Function Signatures', 'Design rules', 'Examples') but is a ~680-line monolith with zero bundle files. The full ~100-component catalog is inlined in SKILL.md when much of it could live in one-level-deep reference files.

3 / 5

Total

15

/

20

Passed

Description

78%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.

A strong description with an explicit what-and-when structure, natural trigger terms, and a clearly distinctive platform niche. Its only weaknesses are the single action verb ('Compose') and a couple of generic trigger words with mild overlap risk.

DimensionReasoningScore

Specificity

The single concrete action is 'Compose UI from the A2UI Playground catalog'; the parenthetical ('charts, maps, data views, inputs, domain cards and macros') enumerates object categories rather than distinct actions, matching the 'names domain and 1-2 concrete actions' anchor. It is not a 4 because no additional distinct operations (e.g., editing, validating, exporting) are listed.

3 / 5

Completeness

The 'what' is explicit ('Compose UI from the A2UI Playground catalog...') and the 'when' is an explicit 'Use when...' clause with concrete trigger phrases ('dashboards, comparisons, forms, plans, maps'), clearly matching the top anchor.

5 / 5

Trigger Term Quality

'Use when an answer is better shown than told: dashboards, comparisons, forms, plans, maps' supplies natural words users would actually say, alongside distinctive platform terms ('CopilotKit Gen UI 2.0', 'A2UI Express'). A few common variations ('visualize', 'report', 'table') are missing, so coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

Platform-specific names ('A2UI Playground', 'CopilotKit Gen UI 2.0', 'A2UI Express') carve a clear niche with distinct triggers. Generic trigger words like 'forms' and 'maps' carry minor overlap risk with document-form or mapping skills, keeping it just below the top anchor.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (684 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

CopilotKit/CopilotKit

Path

examples/showcases/a2ui-playground/skills/generated/express/a2ui-playground/SKILL.md

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.