CtrlK
BlogDocsLog inGet started
Tessl Logo

plate-ui

Build new shadcn-style components for Plate's registry and editor surfaces. Use when authoring or refactoring registry UI/components, deciding what belongs in packages vs app-local component files, creating base/live kits and registry wiring, or applying React Compiler, Effects, accessibility, polymorphism, data-slot, data-state, and composable-component rules to Plate UI work.

68

Quality

83%

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

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 well-structured, opinionated rules skill with concrete paths, commands, code patterns, and a thorough workflow. Its weaknesses are moderate: dead reference links within the bundle, some repetition of the extraction doctrine across sections, and no explicit failure-recovery loop in the workflow.

Suggestions

Ship the six ./rules/*.md files referenced throughout the body (ownership, component-shape, cross-platform, react-performance, registry, shadcn-proofing) or inline/remove the dead links so every reference resolves within the bundle.

Consolidate the extraction doctrine — currently repeated in Principles, Ownership & Extraction, Major-Release Law, and the Extraction Test — into a single authoritative section to cut token cost.

Add an explicit error-recovery branch to the workflow (e.g., what to do when the registry changelog check, pnpm brl, or package typecheck fails) to close the validation loop.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with no explanations of concepts Claude already knows, but extraction guidance is repeated across four sections (Principles, Ownership & Extraction, Major-Release Law, Extraction Test), which is trimmable redundancy. Not 5 because that repetition costs tokens without adding guidance.

4 / 5

Actionability

Concrete repo paths, real commands ("pnpm brl", "registry-kits.ts", "registry-ui.ts"), and good/bad tsx snippets make the guidance mostly executable. Not 5 because the code examples are illustrative fragments of repo patterns rather than copy-paste runnable code.

4 / 5

Workflow Clarity

The 11-step workflow is clearly sequenced with decision points and explicit verification (registry changelog check, pnpm brl, "Verify the smallest honest surface" with tiered checks). Not 5 because there is no explicit error-recovery loop for what to do when a check or verification fails.

4 / 5

Progressive Disclosure

Structure and signaling are good (section-per-rule with links, "Load these only when the task needs the detail"), but 6 of 7 referenced paths — ./rules/ownership.md, component-shape.md, cross-platform.md, react-performance.md, registry.md, shadcn-proofing.md, and the .agents/rules/plate-ui/references/ files — do not exist in the bundle (only references/component-audit.md is present), so most navigation links fail. Not 4 because broken reference paths undermine navigation; not 2 because the in-file structure itself is well organized.

3 / 5

Total

15

/

20

Passed

Description

96%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, tightly scoped description: it states concrete capabilities in third person, gives an explicit multi-clause "Use when" trigger list, and anchors on domain-specific terms. The only weakness is slight trigger overlap with the generic shadcn skill.

DimensionReasoningScore

Specificity

Multiple concrete actions are explicitly listed — "Build new shadcn-style components for Plate's registry and editor surfaces", "creating base/live kits and registry wiring", "deciding what belongs in packages vs app-local component files", and applying named rules — covering the build/refactor/ownership/wiring space comprehensively with no vague filler.

5 / 5

Completeness

It explicitly answers both: what ("Build new shadcn-style components for Plate's registry and editor surfaces") and when ("Use when authoring or refactoring registry UI/components... creating base/live kits and registry wiring, or applying... rules to Plate UI work") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural terms a Plate contributor would actually say are comprehensively present: "shadcn-style components", "Plate", "registry", "editor surfaces", "base/live kits", "React Compiler", "Effects", "data-slot", "data-state", "polymorphism" — mixing colloquial and technical variations.

5 / 5

Distinctiveness Conflict Risk

The "Plate's registry" framing carves a clear niche, but "shadcn-style components" retains minor overlap risk with the closely related generic shadcn skill; a user asking for plain shadcn/ui work could trigger this skill too.

4 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 12 missing

Warning

Total

13

/

16

Passed

Repository
udecode/plate
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.