CtrlK
BlogDocsLog inGet started
Tessl Logo

vercel-ai-sdk-expert

Expert in the Vercel AI SDK. Covers Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components with React and Next.js.

56

Quality

65%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/vercel-ai-sdk-expert/SKILL.md

The canonical home for this skill is vercel-ai-sdk-expert in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 body delivers strong, executable code examples across the SDK's main use cases and is well-sectioned, but it is a single inline monolith with no progressive disclosure to separate reference files and no explicit validation-gated workflow.

Suggestions

Split the larger code blocks (full useChat component, multi-step tool UI, troubleshooting) into reference files under references/ and link to them from a concise overview, improving progressive disclosure.

Trim the intro paragraph and "Why Vercel AI SDK?" section to the essentials to lift conciseness.

Add an explicit decision/workflow sequence (e.g. choose generateText vs streamText vs generateObject, then verify output) with checkpoints to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient, code-driven examples with helpful inline comments; the intro paragraph ("You are a production-grade Vercel AI SDK expert...") and the "Why Vercel AI SDK?" framing add minor over-explanation that could be trimmed, so it sits at the 'efficient; minor instances' anchor rather than 5.

4 / 5

Actionability

Fully executable, copy-paste-ready TypeScript/TSX examples cover the common cases — generateText, streamText, generateObject with Zod, useChat, and tool() with maxSteps — matching the 'fully executable; copy-paste ready' anchor.

5 / 5

Workflow Clarity

Content is organized topically with a useful Troubleshooting problem→solution section, but there is no explicit sequenced workflow with validation checkpoints; the destruct/batch cap-3 rule's premise does not apply, yet sequencing remains implicit.

3 / 5

Progressive Disclosure

No bundle files exist and all ~215 lines sit inline in one document with good section headers but no references to separate files; over the 50-line simple-skill threshold, so the inline-only structure lands at 'some structure; content that should be separate is inline' rather than higher.

3 / 5

Total

15

/

20

Passed

Description

58%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 clearly identifies its niche and names concrete SDK capabilities, but it lacks a "Use when..." trigger clause and relies on technical API jargon rather than natural user phrases, capping completeness and trigger-term quality at 3.

Suggestions

Add a "Use when..." clause with concrete user-facing triggers, e.g. "Use when adding AI chat or streaming text to a React/Next.js app, implementing tool/function calling, or generating structured JSON from an LLM."

Include natural-language synonyms users actually say ("AI chat", "stream LLM responses", "function calling", "generative UI") alongside the API names.

Lead with action verbs (e.g. "Generates, streams, and structures LLM output...") rather than the passive "Covers" to lift specificity.

DimensionReasoningScore

Specificity

Lists several concrete capabilities/APIs — "Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components" — matching the 'several specific actions; minor gaps' anchor; not 5 because "Covers" is passive API-name listing rather than comprehensive concrete action verbs.

4 / 5

Completeness

The "what" is clear (Core API, UI hooks, tool calling, streaming UI), but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Keywords are mostly technical API jargon (generateText, streamText, useChat, useCompletion) and miss natural user phrases like "add AI chat" or "stream LLM responses"; not 2 because more than one or two relevant keywords are present.

3 / 5

Distinctiveness Conflict Risk

"Expert in the Vercel AI SDK" names a clear product niche with minimal conflict risk; not 5 because of minor overlap with general React/Next.js or LLM-integration skills.

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.