ai-elements

AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn/ui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/vercel/skills/ai-elements/SKILL.md

Quality

Content

70%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 content is highly actionable with executable code and a useful breakage checklist, but it carries meaningful redundancy across sections and inlines a large component catalog that would be better served by progressive disclosure into separate reference files.

Suggestions

De-duplicate the repeated directives (never render raw JSX, never install all.json, use toUIMessageStreamResponse) into a single canonical statement and reference it once to tighten the token budget.

Split the full component catalog and per-component examples into a separate COMPONENTS.md (or references/ files) and link to it from SKILL.md so the overview stays lean and one level deep.

Add an explicit validation checkpoint after installation (e.g. run `next build` or `tsc --noEmit` and only proceed when it passes) to convert the type-error recovery steps into a true validate-fix-retry loop.

Dimension	Reasoning	Score
Conciseness	The body is informative and mostly efficient, but it repeats several directives across sections (the 'never render raw JSX' rule, the install-only-what-you-need and never-install-all.json warnings, and the toUIMessageStreamResponse reminder appear 2-3 times), which is noticeable padding for a context-window-loaded skill.	3 / 5
Actionability	It provides copy-paste-ready, executable code for every key component plus concrete install commands and a server-side route example; the guidance is specific and covers the common cases fully.	5 / 5
Workflow Clarity	Installation and type-error fix steps are clearly sequenced with an ordered recovery path and a 'common breakages' checklist, but there is no explicit validate-then-proceed checkpoint (e.g. verifying a build passes) between install and use.	4 / 5
Progressive Disclosure	There are no references/ or scripts/ bundle files, and the body is a monolithic ~480-line reference that inlines the full component table and per-component examples rather than splitting them into separate files with one-level-deep links, so structure is present but content is not appropriately split.	3 / 5
	Total	15 / 20 Passed

Description

88%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 strong: it clearly states what AI Elements is and when to reach for it, with rich natural trigger terms and ecosystem anchoring. The main weakness is slight breadth in the catch-all 'any AI-native interface' clause, which marginally raises overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete capabilities ('chat UIs, message displays, tool call rendering, streaming responses, reasoning panels'), though it relies on enumerated product features rather than fully self-contained action verbs, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers both what it is ('pre-built React components for AI interfaces built on shadcn/ui') and when to use it ('Use when building chat UIs... or any AI-native interface with the AI SDK') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms users actually say ('chat UIs', 'message displays', 'streaming responses', 'reasoning panels') and the precise ecosystem term ('AI SDK'), matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	The ecosystem anchor ('built on shadcn/ui... AI SDK') gives it a clear niche with distinct triggers, but the broad phrase 'any AI-native interface' creates minor overlap risk with general UI skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/vercel/skills/ai-elements/SKILL.md
Commit: 1dc1958

Reviewed: 8 hours ago

Table of Contents

Discovery Implementation Validation

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.