CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-sdk

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

96

4.78x
Quality

Does it follow best practices?

Impact

91%

4.78x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The body is a concise, highly actionable overview that delegates detail to four real, well-signaled reference files and provides clear sequenced workflows with a typecheck validation checkpoint. It assumes Claude's intelligence and avoids explaining known concepts.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no padding explaining concepts Claude already knows; the version-sensitivity framing and curl/grep commands each earn their tokens. It assumes competence and instructs Claude to be minimal rather than verbose.

3 / 3

Actionability

It provides concrete, copy-paste-ready commands (pnpm add ai, grep queries against node_modules, a curl pipeline for fetching current model IDs, run typecheck), with the doc-search approach explicitly justified by the dynamic-version context.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced (Prerequisites, Finding Documentation, When Typecheck Fails, Consuming Agents) with an explicit typecheck validation checkpoint and a grep-common-errors feedback loop for error recovery.

3 / 3

Progressive Disclosure

SKILL.md acts as an overview with four well-labeled, one-level-deep references (common-errors, ai-gateway, type-safe-agents, devtools), all verified to exist in ./references/, with content appropriately split across files.

3 / 3

Total

12

/

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 concisely states the skill's purpose and provides an explicit trigger clause with broad, natural keyword coverage and a clear niche. It satisfies every dimension at the top anchor without verbosity or over-claims.

DimensionReasoningScore

Specificity

The description lists many concrete actions ("chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation"), matching the anchor for multiple specific concrete actions rather than the partial list at level 2.

3 / 3

Completeness

It explicitly states what the skill does ("Vercel AI SDK expert guidance") and when to use it ("Use when building AI-powered features..."), satisfying both the what and when with an explicit trigger clause.

3 / 3

Trigger Term Quality

It uses a natural "Use when building AI-powered features" trigger with broad coverage of terms users would actually say (chat, tool calling, agents, streaming, embeddings, image generation, LLM provider), matching the high-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

It targets a clear niche ("Vercel AI SDK") with AI-SDK-specific triggers, making it unlikely to fire for unrelated skills and distinct from generic AI/library skills.

3 / 3

Total

12

/

12

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.

Validation13 / 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

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
vercel/vercel-plugin
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.