ai-sdk

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, or tools, (2) Want to build AI agents, chatbots, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, etc.), streaming, tool calling, or structured output.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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.

A well-organized retrieval skill with concrete executable commands, clear version branching, and clean progressive disclosure to two real reference files. The main weakness is mild redundancy in the provider-specific section and placeholder-only examples.

Suggestions

Collapse the 'Provider-Specific Information' section's grep/glob instructions into a brief pointer to the same pattern applied to node_modules/@ai-sdk/<provider>/, reducing repetition.

Add one short worked example (e.g., a real grep query and the kind of file it returns) so the commands are fully copy-paste-ready rather than placeholder-only.

Trim the trailing sentence 'Use these resources for current API details, examples, and usage patterns.' since it restates the section's purpose.

Dimension	Reasoning	Score
Conciseness	Largely lean with no over-explanation of what the AI SDK is, but the 'Provider-Specific Information' section repeats the same grep/glob pattern already shown, and 'Use these resources for current API details, examples, and usage patterns' is mildly redundant — minor trimming possible.	4 / 5
Actionability	Provides concrete, executable commands (grep, glob patterns, fetchable .md URLs) with clear branching, but uses 'your query' placeholders throughout and shows no worked example or sample output, leaving minor gaps versus copy-paste-ready completeness.	4 / 5
Workflow Clarity	Clear version-conditional branching (ai@6+ bundled docs vs. online search) with numbered steps and a fallback ('When in doubt, update'), but there are no validation checkpoints — acceptable since this is a retrieval, not destructive, operation.	4 / 5
Progressive Disclosure	SKILL.md acts as a concise overview with two well-signaled, one-level-deep references to real files (references/common-errors.md and references/ai-gateway.md) that hold the detailed error and gateway content, with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

95%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.

A strong, well-structured description that explicitly covers both what the skill does and when to use it, with comprehensive natural trigger terms and clear distinctiveness. The only minor weakness is that the headline action verbs are slightly generic despite the strong enumerated specifics.

Dimension	Reasoning	Score
Specificity	Names concrete functions (generateText, streamText, ToolLoopAgent, tools) and feature types (agents, chatbots, streaming, structured output), but the two primary verbs 'Answer questions' and 'help build' are slightly generic compared to the highly concrete action verbs in the score-5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Answer questions about the AI SDK and help build AI-powered features') and 'when' with a numbered 'Use when developers:' clause listing concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage a developer would actually say — 'AI agents', 'chatbots', 'streaming', 'tool calling', 'structured output', plus provider names (OpenAI, Anthropic) and named functions.	5 / 5
Distinctiveness Conflict Risk	Scoped specifically to the AI SDK with named functions and providers, giving it a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: compozy/compozy
Path: .agents/skills/ai-sdk/SKILL.md
Commit: bfd5622

Reviewed: 3 days 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.