ai-sdk-core
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, Output API errors, Gemini caching issues, Anthropic tool errors, MCP tools, or stream resumption failures.
81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific capabilities (Output API, speech synthesis, transcription, embeddings, MCP tools), includes explicit migration and troubleshooting guidance, and has a comprehensive 'Use when:' clause with highly specific trigger terms including actual error names. The description is distinctive enough to avoid conflicts with other AI-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: Output API, speech synthesis, transcription, embeddings, MCP tools, migration guidance, and 15 error solutions. Uses third person voice appropriately. | 3 / 3 |
Completeness | Clearly answers both what (Output API, speech synthesis, transcription, embeddings, MCP tools, migration, error solutions) AND when with explicit 'Use when:' clause listing specific scenarios and error types. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'AI SDK v5/v6', 'AI_APICallError', 'Workers startup issues', 'Output API errors', 'Gemini caching issues', 'Anthropic tool errors', 'MCP tools', 'stream resumption failures'. These are specific error names and features users would search for. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets Vercel AI SDK v6 stable, mentions specific version numbers (v4→v5, v5/v6), and lists unique error types that wouldn't overlap with generic AI or backend skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent executable code examples covering AI SDK v5/v6 comprehensively. However, it suffers from being overly long with time-sensitive content (model versions, dates) inline rather than in separate files. The error solutions section is valuable but could benefit from clearer recovery workflows.
Suggestions
Extract the 'Latest AI Models' section to a separate MODELS.md file that can be updated independently, keeping only a brief reference in the main skill
Move the 'Top 15 Errors & Solutions' to an ERRORS.md reference file, keeping only the 3-4 most critical errors inline with links to the full list
Add explicit validation checkpoints to the v4→v5 migration workflow (e.g., 'After each change, run `npm run typecheck` to verify no type errors')
Remove explanatory text about what models are best for (e.g., 'Enhanced reasoning capabilities') - Claude knows model capabilities
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., model descriptions, provider comparisons) and could be tightened. The model version sections with dates and pricing add bulk that may become stale quickly. | 2 / 3 |
Actionability | Excellent executable code examples throughout - from basic text generation to complex tool definitions, error handling patterns, and migration examples. All code is copy-paste ready with proper imports. | 3 / 3 |
Workflow Clarity | Multi-step processes like migration have checklists, but validation checkpoints are inconsistent. The migration section lists steps without explicit verification points, and error handling sections describe what to do but lack feedback loops for recovery. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a 'When to Use This Skill' guide, but the document is monolithic (~800 lines). The model versions, error solutions, and migration guide could be split into separate reference files with links from the main skill. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1357 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- 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.