CtrlK
BlogDocsLog inGet started
Tessl Logo

migrate-ai-sdk-v6-to-v7

Migrate applications from AI SDK 6.x to AI SDK 7.0. Use when upgrading Vercel AI SDK packages, fixing v7 migration errors, or when the user mentions AI SDK v6, v7, upgrade, migration, breaking changes, system to instructions, fullStream, telemetry, tool context, or finalStep.

74

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An excellent, dense migration checklist: lean, well-structured, with a clear workflow that includes a baseline-safety step and explicit validation with a feedback loop. The only minor gap is that a few higher-level audit directives lack inlined before/after code context.

DimensionReasoningScore

Conciseness

Dense, lean checklist of exact rename mappings and rule statements with no padding or explanation of concepts Claude already knows; every line earns its place.

5 / 5

Actionability

Highly concrete symbol-by-symbol mappings (e.g. 'experimental_customProvider -> customProvider', 'result.toUIMessageStreamResponse(...) -> toUIMessageStream(...) plus createUIMessageStreamResponse({ stream })'), but a few entries are higher-level audit directives ('Audit prepareStep behavior', 'Add support for the new reasoning-file content type') and no full before/after code context is inlined, leaving minor gaps.

4 / 5

Workflow Clarity

A numbered Migration Workflow begins with a backup/committed-baseline safety step, directs migration followed by typecheck and targeted tests, and the Validation section provides an explicit feedback loop ('If type errors remain, search the migration guide... before inventing a workaround') plus smoke-test guidance for touched areas.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections with a single well-signaled one-level-deep reference to the AI SDK repo migration guide as source of truth; the checklist content is appropriately kept inline and navigation is easy via headers.

5 / 5

Total

19

/

20

Passed

Description

90%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 description with explicit what/when structure and rich natural trigger terms. The only soft spot is specificity, since the stated capability is essentially a single migrate action rather than a comprehensive action list.

DimensionReasoningScore

Specificity

Names the domain (AI SDK 6.x to 7.0 migration) and the concrete actions 'Migrate applications' and 'fixing v7 migration errors', but the action set is narrow rather than a comprehensive list of capabilities, matching the 1-2 concrete actions anchor.

3 / 5

Completeness

Explicitly answers both 'what' ('Migrate applications from AI SDK 6.x to AI SDK 7.0') and 'when' ('Use when upgrading Vercel AI SDK packages, fixing v7 migration errors, or when the user mentions...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural terms users would say — 'upgrade', 'migration', 'v6', 'v7', 'breaking changes' — plus specific v7 symbols like 'system to instructions', 'fullStream', 'telemetry', 'tool context', and 'finalStep', including synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (AI SDK v6-to-v7 migration) with version-specific trigger terms, making conflict with other skills minimal.

5 / 5

Total

18

/

20

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
saif-shines/channel-watcher-agent
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.