CtrlK
BlogDocsLog inGet started
Tessl Logo

shadcn-parity

Clone shadcn implementation patterns with source-by-source parity. Use when the user says "shadcn parity", asks to mirror shadcn, copy shadcn UX/architecture/tests, or wants more than inspiration.

67

Quality

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable contract skill with concrete paths, namespaces, and decision rules, but it carries cross-section redundancy, lacks an explicit sequenced workflow with validation checkpoints, and is a monolithic single file above the simple-skill line.

Suggestions

Deduplicate the repeated "upstream first / do not fork shadcn CLI" guidance: state the core rule once in Core Contract and reference it from Registry Rules and Red Flags rather than restating it.

Turn the Red Flags list into an explicit pre-flight checklist with a validate step (e.g., "check ../shadcn first, then proceed") so the decision workflow has a clear sequence with checkpoints.

Move the detailed Registry dependency rules and Current Divergences into a reference file referenced one level deep from SKILL.md to reduce inline bulk and improve navigation.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and uses lean bullets, but the same injunctions ("upstream first", "do not fork shadcn CLI") are restated across Core Contract, Registry Rules, and Red Flags, so it could be tightened.

2 / 3

Actionability

Guidance is concrete and specific — exact paths (apps/www/src/registry/*, apps/www/public/rd), namespaces (@plate, @shadcn/*), URL patterns (https://platejs.org/r/*.json), the --local flag, and clear prefer-X-over-Y decision rules — actionable without code, as the rubric allows for instruction-only skills.

3 / 3

Workflow Clarity

Sections are well-organized and Red Flags act as a reassess-checklist, but this is declarative policy rather than a sequenced multi-step workflow with explicit validate-fix-retry checkpoints, so checkpoints remain implicit rather than embedded in a clear sequence.

2 / 3

Progressive Disclosure

The skill is a single self-contained ~130-line file with clear headers and no bundle/reference files, but it exceeds the simple-skill (<50 line) threshold and keeps all detail inline rather than splitting reference material out one level deep.

2 / 3

Total

9

/

12

Passed

Description

100%

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, third-person description that states concrete capabilities and gives an explicit, naturally worded trigger clause covering several user phrasings. It clearly communicates both what the skill does and when to invoke it, with low conflict risk.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Clone shadcn implementation patterns", "mirror shadcn", "copy shadcn UX/architecture/tests" — rather than vague language, matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ("Clone shadcn implementation patterns with source-by-source parity") and when (a "Use when..." clause with concrete triggers), satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Natural phrasings a user would actually say are covered: "shadcn parity", "mirror shadcn", "copy shadcn UX/architecture/tests", "more than inspiration" — good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The shadcn-parity niche is narrow and the triggers are specific to shadcn, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 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

Total

14

/

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.