CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-elements

Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.

84

8.33x
Quality

75%

Does it follow best practices?

Impact

100%

8.33x

Average score across 3 eval scenarios

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/ai-elements/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-3

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

The body covers prerequisites, install, usage, extensibility, customization, and troubleshooting with concrete code, but is padded with prose and leaves the central install command out of the body. Progressive disclosure is present but only weakly signaled.

Suggestions

Show the actual install command in the body (e.g. `npx ai-elements@latest add conversation`) in the 'Installing Components' section instead of only describing the two methods in prose.

Trim narrative filler such as 'Installing AI Elements is straightforward', 'the usage feels very natural', and 'you should see a confirmation in your terminal' to tighten the body.

Replace the generic 'See the `references/` folder' line with named links to the most-used component docs (e.g. conversation.md, message.md, prompt-input.md) to make navigation one level deep and clearly signaled.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete code, but padded with narrative prose ('Installing AI Elements is straightforward...', 'the usage feels very natural', 'you should see a confirmation in your terminal') that could be trimmed. Not a 1 because it avoids explaining generic concepts Claude already knows.

2 / 3

Actionability

Provides executable code examples and CLI commands, but the core 'Installing Components' section only describes the two install methods in prose without showing the actual `npx ai-elements@latest add <component>` command (which lives only in the references), leaving the primary action incomplete in the body.

2 / 3

Workflow Clarity

The install→import→use flow is present but loosely described rather than sequenced, and the example switch statement only handles the 'text' case. Not a 1 because steps are discernible; not a 3 because there is no explicit numbered sequence or validation checkpoint for the install step.

2 / 3

Progressive Disclosure

A references/ folder with 48 component docs exists and is pointed to, but the body only signals it generically ('See the `references/` folder') at the very end rather than linking individual component docs, so navigation is weak relative to the well-signaled one-level-deep anchor.

2 / 3

Total

8

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 concise, uses third-person imperative voice, and cleanly covers what the skill does and when to invoke it with natural trigger terms. No first/second person or vague fluff is present.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete component actions — 'conversations, messages, tool displays, prompt inputs, and more' — matching the anchor that lists several specific concrete actions.

3 / 3

Completeness

Explicitly answers both 'what' (Build AI chat interfaces using ai-elements components) and 'when' via a clear 'Use when...' clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Natural user-facing triggers are present: 'build a chatbot', 'AI assistant UI', 'AI-powered chat interface' — terms a user would plausibly say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche (ai-elements chat UI components on shadcn/AI SDK) with distinct triggers, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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
vercel/ai-elements
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.