Premium skill
Expose your product to agents with MCP
Task-shaped tools, pagination and truncation discipline, real auth, destructive-operation safety, and an eval harness that measures whether models actually complete the job.
Install
Install with skills CLIPremium skills install through a short-lived private link.
$ npx skills add … --skill build-mcp-serverOpen 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-mcp-server stays visible so you can see the pack before unlocking.
Use this when
- 01A billing API exposed as a handful of task-shaped tools instead of forty endpoint mirrors.
- 02A remote Streamable HTTP server with OAuth and audit logs other companies can call safely.
- 03A delete_project tool that refuses unconfirmed destructive calls in the harness.
- 04An existing MCP server models misuse: diagnose with wrong-tool metrics, then edit descriptions.
What you get
- Tools from jobs
- A small task-shaped set. Never a 1:1 REST mirror.
- Caps response size
- Pagination, truncation markers, and per-tool budgets.
- Auth in code
- Authenticate callers and pass end-user identity to your API, not through the prompt.
- Measures tool quality
- Contract tests plus opt-in task evals on success and wrong-tool rate.
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
- EvaluateBuild AI SDK Agent EvalsProtecting critical agent journeys before you optimize
- 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
- 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