Token导航 LogoToken导航

Agent Skill · 研究检索

chainlink-ccip-skill(chainlink ccip 技能)

chainlink-ccip-skill 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

chainlink-ccip-skill 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 43,703。

总安装 964周安装 41GitHub Stars 95下载 338核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:chainlink-ccip-skill(chainlink ccip 技能)
来源仓库:https://github.com/smartcontractkit/chainlink-agent-skills
仓库路径:skills/chainlink-ccip-skill
安装命令:
npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill chainlink-ccip-skill
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill chainlink-ccip-skill

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

专门处理 Chainlink CCIP(跨链互操作性协议)相关请求。优先选择最简单有效的路径执行操作。仅在必要时才获取文档或示例, 保持响应简洁高效。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

chainlink-ccip-skill 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/chainlink-ccip-skill

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skil…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

chainlink-ccip-skill 怎么安装?

在终端执行 npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill chainlin…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

chainlink-ccip-skill 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

chainlink-ccip-skill 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

chainlink-ccip-skill 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

chainlink-ccip-skill 用的人多吗?

公开数据是累计安装 964 次,近一周安装 41 次,下载 338 次,GitHub 95 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

chainlink-ccip-skill 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
chainlink-ccip-skill

chainlink ccip 技能 · 本页

96495操作浏览器未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Chainlink CCIP Skill

Overview

Route CCIP requests to the simplest valid path while keeping side effects tightly controlled.

Progressive Disclosure

  1. Keep this file as the default guide.
  2. Read references/examples.md only when you need a concrete reference for what a good response looks like (preflight summaries, monitoring explanations, contract-generation structure).
  3. Read references/official-sources.md only when the answer depends on live CCIP facts, current tool behavior, route or token availability, or message-status surfaces.
  4. Read references/ccip-mcp.md only when the ccip_sdk MCP tool is available and the request can be fulfilled by it for monitoring, discovery, or SDK method calls.
  5. Read references/ccip-tools.md only when the user wants a tool-first workflow through CCIP CLI, API, or SDK.
  6. Read references/ccip-contracts.md only when the user wants sender or receiver contracts, token-transfer contracts, programmable token-transfer contracts, or contract setup help.
  7. Read references/ccip-cct.md only when the user wants to create a token, register it as a CCT, configure pools, set rate limits, or add networks for CCT operation.
  8. Read references/chainlink-local.md only when the user wants local simulation, local tests, or forked-environment testing for CCIP contracts.
  9. Read references/ccip-monitoring.md only when the user wants message lookup, monitoring, status explanation, lane performance, or failed-message diagnosis.
  10. Read references/ccip-discovery.md only when the user wants route connectivity checks, network classification, or supported-token discovery.
  11. Read references/ccip-solidity-examples.md only when generating or reviewing CCIP Solidity contracts and you need concrete code patterns (sender, receiver, token transfer, defensive receiver).
  12. Read references/ccip-sdk-examples.md only when the user wants TypeScript SDK usage examples for fee estimation, token transfers, messaging, or status checks.
  13. Read references/ccip-non-evm.md only when the user wants to work with CCIP on Solana, Aptos, Sui, TON, or any non-EVM chain family.
  14. Do not load reference files speculatively.

Routing

  1. Use a tool-first path for sending without custom contracts, bridging funds, status lookup, connectivity checks, and route or token discovery.
  2. When the ccip_sdk MCP tool is available, prefer it over direct CLI or SDK invocation for monitoring, discovery, and programmatic SDK method calls. Fall back to CLI or SDK when the tool is not available.
  3. Use a contract-first path for sender and receiver contract work and CCT setup flows.
  4. For non-EVM chain requests (Solana, Aptos, Sui, TON), route to the non-EVM reference for workflow guidance. Do not apply EVM-specific patterns (Solidity, Foundry, Hardhat, Chainlink Local) to non-EVM chains.
  5. Ask one focused question if the route, network, token, amount, or target contracts are missing.
  6. Proceed without approval only for read-only work such as explanation, discovery, status checks, and code generation.
  7. Trigger the approval protocol before any action that could create, transfer, deploy, register, enable, or configure on-chain state.
  8. Do not assume this skill is the only capability available. Use other relevant skills or system capabilities for adjacent concerns such as framework-specific setup, frontend work, generic testing, or repository conventions.

Safety Guardrails

  1. Never execute any on-chain action without explicit user approval.
  2. Never assume the intended route, lane, network, token, amount, or destination.
  3. Refuse all mainnet write actions in this version.
  4. Allow read-only mainnet lookups in this version.
  5. Prefer the least risky valid path. If the user can accomplish the goal through CCIP tools, do not default to custom contracts.
  6. For contract work, prefer secure, conservative patterns with explicit access control, validation, least-privilege configuration, and minimal moving parts.
  7. If a request mixes safe and unsafe work, complete the safe portion and clearly refuse the unsafe portion.
  8. If the user asks to bypass these guardrails, refuse and explain the constraint directly.

Approval Protocol

Before any on-chain action, present a short preflight summary that includes:

  1. action type
  2. network type
  3. source chain
  4. destination chain
  5. route or lane details if known
  6. token and amount if applicable
  7. whether the action sends data, tokens, or both
  8. contract addresses involved if applicable
  9. tool or method to be used
  10. expected effect

End the preflight with a direct approval question.

Use this structure:

Proposed on-chain action:
- Action: ...
- Network: ...
- Source chain: ...
- Destination chain: ...
- Route/lane: ...
- Token/amount: ...
- Payload: ...
- Contracts: ...
- Method: ...
- Expected effect: ...

Do you want me to execute this?

Second Confirmation Rule

Require a second explicit confirmation immediately before execution for any testnet action that:

  1. sends a CCIP message
  2. transfers or bridges tokens
  3. deploys contracts
  4. creates a token
  5. enables or configures a CCT lane

Do not treat the user's original intent as the second confirmation. Ask again right before the side-effecting step.

Working Rules

  1. Keep questions narrow and unblock the next safe step.
  2. Explain the chosen path briefly.
  3. Generate code only when code is actually needed.
  4. Keep unsupported or out-of-scope features out of the answer rather than speculating about them.

Documentation Access

This skill references official CCIP documentation URLs throughout its reference files. Whether the model can fetch those URLs depends on the host agent's capabilities.

  1. If WebFetch, a browser tool, or an MCP server that can retrieve documentation is available, use it to fetch the referenced URL before answering.
  2. If no documentation-fetching tool is available, do not silently improvise CCIP patterns from training data alone. Instead:

- Use the embedded reference content in this skill's reference files as the floor for guidance. - Tell the user that live documentation could not be verified. - Provide the specific URL so the user can check it directly.

  1. For contract-first workflows where correctness matters most, prefer the concrete examples in references/ccip-solidity-examples.md over generating patterns from memory.

MCP Recommendations

This skill works best when the Chainlink MCP server (@chainlink/mcp-server) is connected. It provides live access to CCIP message status, lane data, and SDK methods through the ccip_sdk tool.

When the Chainlink MCP server is not available, the Context7 MCP server (@upstash/context7-mcp) is a useful fallback for fetching current Chainlink documentation. It can retrieve content from docs.chain.link and other public documentation sources, covering the gap for contract patterns, tutorials, and API references that this skill cannot embed in full.

平台分布

Codex

34.79%
按下载量换算118

Claude

30.63%
按下载量换算104

Cursor

17.32%
按下载量换算59

Gemini CLI

8.3%
按下载量换算28

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills