Premium skill
Write prompt contracts the model can follow
Writes the strings the model uses to choose and act: structured tool descriptions, schema text, and sectioned instructions built from runtime context.
Install
Install with skills CLIPremium skills install through a short-lived private link.
$ npx skills add … --skill write-prompt-contractsOpen 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 write-prompt-contracts stays visible so you can see the pack before unlocking.
Use this when
- 01A support agent that used search_help for every 'where's my order' question.
- 02A RAG agent that narrated a retrieval plan and waited for approval it did not need.
- 03A commerce subagent that only has catalog tools but inherited the checkout prompt.
- 04Overlapping lookup and search tools with one-way redirects that still leaked.
What you get
- Descriptions that route
- What it does, when to use it, when not to, boundaries, caps, and examples.
- Instructions that act
- Tell the agent to use tools and answer, not to narrate a plan.
- Name the gravity tool
- Find the general tool the model defaults to, then make siblings refuse that job.
- Prompts from wired tools
- Build instructions from tools that are actually attached.
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
- 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