跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
部署与云服务

chainlink-cre-skill

Handle CRE (Chainlink Runtime Environment) work: Go/TypeScript workflows, CRE CLI/SDK, triggers (CRON, HTTP, EVM log), HTTP, Confidential HTTP and EVM Read/Write capabilities, Confidential Workflows that run handlers inside a TEE/enclave, secrets, simulation, deployment, and monitoring. Use this skill whenever the user mentions CRE, Chainlink workflows, workflow simulate or deploy, automation with Chainlink, or wants workflow logic to run confidentially in an enclave so node operators cannot see the data it computes over, even if they never say 'CRE'

smartcontractkit · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add smartcontractkit/chainlink-agent-skills --skill chainlink-cre-skill

技能说明


name: chainlink-cre-skill description: "Handle CRE (Chainlink Runtime Environment) work: Go/TypeScript workflows, CRE CLI/SDK, triggers (CRON, HTTP, EVM log), HTTP, Confidential HTTP and EVM Read/Write capabilities, Confidential Workflows that run handlers inside a TEE/enclave, secrets, simulation, deployment, and monitoring. Use this skill whenever the user mentions CRE, Chainlink workflows, workflow simulate or deploy, automation with Chainlink, or wants workflow logic to run confidentially in an enclave so node operators cannot see the data it computes over, even if they never say 'CRE'" license: MIT compatibility: Designed for AI agents that implement https://agentskills.io/specification, including Claude Code, Cursor Composer, and Codex-style workflows. allowed-tools: Read WebFetch Write Edit Bash metadata: purpose: CRE developer onboarding, assistance and reference version: "0.0.22"

Chainlink CRE Skill

Overview

Route CRE requests to the simplest valid path. Keep this file as the decision layer; load reference files only for the mechanics needed by the user's request. Generate working workflow code on first attempt when the user asks for implementation.

Progressive Disclosure

  1. Keep this file as the default guide.
  2. Read references/getting-started.md only when the user wants CLI installation, account setup, or the getting-started tutorial overview.
  3. Read references/project-scaffolding.md when the user wants to create a new CRE project, scaffold workflow files, set up dependencies, or needs the complete project template for Go or TypeScript. Always read this file before generating a new project from scratch.
  4. Read references/simulation.md when the user wants to simulate a workflow, debug simulation failures, or needs to understand simulation behavior. Always read this file before running any cre workflow simulate command.
  5. Read references/workflow-patterns.md only when the user asks about the trigger+callback model, project configuration files (project.yaml, workflow.yaml, config.json, secrets.yaml), secrets management, DON Time, or randomness.
  6. Read references/triggers.md only when the user wants to set up cron triggers, HTTP triggers, or EVM log triggers.
  7. Read references/evm-client.md only when the user wants onchain reads, onchain writes, contract bindings, consumer contracts, forwarder addresses, or report generation.
  8. Read references/http-client.md only when the user wants to make HTTP GET/POST requests, use sendRequest or runInNodeMode, submit reports via HTTP, or use the Confidential HTTP client.
  9. Read references/confidential-workflows.md when the user wants a handler to execute inside a TEE/enclave, mentions Confidential Workflows, handlerInTee/cre.HandlerInTee, TeeRuntime, enclave attestation, or asks how to hide workflow data from node operators. Read it before writing any confidential workflow code, and read it to tell Confidential Workflows apart from the Confidential HTTP client in http-client.md — the two are different capabilities whose APIs do not mix.
  10. Read references/sdk-reference.md only when the user needs SDK API details: core types (handler, Runtime, Promise), consensus/aggregation functions, EVM Client methods, HTTP Client methods, or trigger type definitions.
  11. Read references/cli-reference.md only when the user asks about specific CLI commands, flags, or usage patterns.
  12. Read references/operations.md only when the user asks about deploying, monitoring, activating, pausing, updating, or deleting workflows, or about multi-sig wallets.
  13. Read references/concepts.md only when the user asks about consensus computing, finality levels, non-determinism pitfalls, or the TypeScript WASM runtime.
  14. Read references/domain-patterns.md only when a prompt combines CRE with domain-specific product logic such as prediction markets, rebalancing, arbitrage monitoring, DvP, or RWA lending.
  15. Read references/official-sources.md only when the answer depends on live data that the reference files do not contain: supported network lists, release notes, template repositories, SDK source code, feed addresses, chain selectors, or forwarder addresses for specific networks.
  16. Read references/chain-selectors.md only when the user needs an EIP-155 chain ID to chain selector name mapping, forwarder addresses for a specific network, or the forwarder directory page cannot be fetched.
  17. Read references/feedback.md only when a feedback-loop trigger has fired in the current session (see "Feedback Loop" below): a content gap in the references, or user-voiced pain about this skill. Do not load it speculatively.
  18. Do not load reference files speculatively.

Routing and Artifact Fit

  1. Preserve the user's requested deliverable. Implementation prompts should get code, config, tests or simulation fixtures, and run/simulate commands; design prompts can stay architectural.
  2. Generate a CRE workflow project as the primary artifact only when the prompt explicitly asks for CRE, a Chainlink workflow, deployability in CRE, DON/decentralized execution, or Chainlink-based automation.
  3. For broad app/platform/product prompts that do not explicitly ask for CRE, lead with domain architecture. Add CRE only in a short "Where CRE fits" section for monitoring, verification, automation, or reporting.
  4. For explicit CRE monitoring or comparison workflows, cover the full loop: trigger -> onchain/offchain reads -> consensus aggregation for external data ->
阅读完整来源 ↗