Premium skill
Build evals around your real AI SDK agent
Adds datasets, deterministic tests, model-graded scorers, and local or CI commands around an existing TypeScript or JavaScript AI SDK agent. Live model runs are opt-in.
Install
Install with skills CLIPremium skills install through a short-lived private link.
$ npx skills add … --skill build-ai-sdk-agent-evalsOpen Premium install
Sign in with Premium to generate a fresh install link.
Filesystem
Browse the authored file tree — tools, references, and evals included. Source unlocks with Premium.
SKILL.mdmarkdownUnlock skill source
Browse every authored SKILL.md with premium.
File tree for build-ai-sdk-agent-evals stays visible so you can see the pack before unlocking.
Use this when
- 01An agent that seems to work, with no dataset or scorers.
- 02Prompt or model swaps you cannot compare on the same cases.
- 03Destructive tools that need fake-safe trajectories in tests.
- 04CI that should fail when quality, cost, or latency regresses.
What you get
- Tests the real agent
- Datasets and deterministic tests that hit the actual agent boundary.
- Fakes dangerous tools
- Approval, tenancy, and destructive calls stay behind gates.
- Compares fairly
- Shared cases and calibrated scorers so prompt or model swaps survive reruns.
- Fails CI on regression
- Separate offline, live smoke, and full tiers for quality, cost, and latency.
Unlock the files
Available with Premium. The private install link expires; the downloaded skill does not. Generate a fresh link when you want to update it.
Other Premium skills
Lifecycle skills and UI craft skills
- PlanPlan AI SDK AgentBefore you write agent code
- BuildAISDK AgentsImplementing agents, chat apps, and streaming UIs
- ObserveObserve AI SDK AgentDebugging and attributing agent behavior in production
- OptimizeOptimize AI SDK AgentImproving quality, speed, cost, or reliability with proof
- InstructWrite Agent PromptsAgents that ignore instructions or run on folklore prompts
- InstructWrite Prompt ContractsAgents that pick the wrong tool or narrate a plan instead of acting
- Chat UIBetter Chat UIBuilding or reviewing the conversation surface
- Generative UIBetter Generative UITurning model output into interactive product UI
- PrototypeTest UI VariantsSurfaces where one polished mock would hide the real choice
- IngestIngest Messy DocumentsPDF, scan, and table-heavy corpora feeding RAG or extraction
- GroundGround AI SDK AgentMaking an agent answer from your data with proof
- MemoryAgent MemoryAgents that should remember users across sessions
- ExposeBuild MCP ServerMaking your product agent-accessible
- ExtractExtract Structured DataInvoices, resumes, contracts, forms, and free text to typed data
- ShipShip AI SDK on CloudflareGetting an AI SDK agent into production on Cloudflare
- ShipShip AI SDK on AWSGetting an AI SDK agent into production on AWS
- MobileAI SDK on MobileShipping AI SDK chat in an Expo or React Native app
- MigrateMigrate to AI SDKLeaving LangChain, the Assistants API, or hand-rolled LLM code