Token导航 LogoToken导航

Agent Skill · 研究检索

chainlink-data-feeds-skill(chainlink 数据馈送技能)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

chainlink-data-feeds-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 66,424。

总安装 264周安装 11GitHub Stars 95下载 88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-data-feeds-skill(chainlink 数据馈送技能)
来源仓库:https://github.com/smartcontractkit/chainlink-agent-skills
仓库路径:skills/chainlink-data-feeds-skill
安装命令:
npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill chainlink-data-feeds-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-data-feeds-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。

用于读取价格馈送、编写消费者合约及调试集成问题。支持 EVM 链上读取和链下查询操作。提供 AggregatorV3Interface 标准接口说明和错误排查指南。chainlink-data-feeds-skill 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

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。

来源仓库内路径:skills/chainlink-data-feeds-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-data-feeds-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-data-feeds-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-data-feeds-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-data-feeds-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-data-feeds-skill 用的人多吗?

公开数据是累计安装 264 次,近一周安装 11 次,下载 88 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-data-feeds-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-data-feeds-skill

chainlink 数据馈送技能 · 本页

26495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 Data Feeds Skill

Overview

Route Data Feed requests to the simplest valid path. Generate working code on first attempt when possible. Fetch documentation only when a specific gap blocks progress.

Progressive Disclosure

  1. Keep this file as the default guide.
  2. Read references/reading-price-feeds.md only when the user wants to read a price feed on EVM, write a consumer contract, read off-chain, look up AggregatorV3Interface, or debug a price feed integration.
  3. Read references/mvr-feeds.md only when the user asks about Multiple-Variable Response feeds, bundle feeds, or BundleAggregatorProxy.
  4. Read references/svr-feeds.md only when the user asks about Smart Value Recapture, OEV recapture, or searcher onboarding.
  5. Read references/feed-types.md only when the user asks about feed categories, SmartData/RWA, rates/volatility, tokenized equity feeds, or needs help choosing a feed type.
  6. Read references/multi-chain.md only when the user targets Solana, StarkNet, Aptos, or Tron.
  7. Read references/feed-operations.md only when the user asks about L2 sequencer uptime checks, feed deprecation, contract registry, developer responsibilities, or data sources.
  8. Read references/official-sources.md only when the answer depends on live data that the reference files do not contain — feed addresses for a specific chain, current deprecation schedules, specific network parameters.
  9. Read references/source-code.md only when debugging interface mismatches or the user needs to inspect contract source code on GitHub.
  10. Do not load reference files speculatively.

Routing

  1. Use reading-price-feeds.md as the default for any EVM price feed request — this covers the vast majority of Data Feeds use cases.
  2. Route to the chain-specific section of multi-chain.md for non-EVM chains (Solana, Aptos, StarkNet, Tron).
  3. Route to mvr-feeds.md for bundle or multi-variable feed requests.
  4. Route to svr-feeds.md for OEV or MEV recapture requests.
  5. Route to feed-operations.md for operational concerns (L2 sequencer checks, deprecation, monitoring).
  6. Ask one focused question if the chain, feed type, or integration method is unclear.
  7. Proceed without asking for read-only work: explanations, code generation, debugging.

Safety Defaults

These are non-negotiable in generated code. Every consumer contract or integration must include them.

  1. Always validate freshness: check updatedAt against a staleness threshold based on the feed's heartbeat. Never skip this.
  2. Always call decimals() on the feed: never hardcode decimal counts. Different feeds use different decimals.
  3. On L2 chains (Arbitrum, Optimism, Base, Scroll, etc.): always include an L2 Sequencer Uptime Feed check with a grace period after recovery.
  4. Never use answeredInRound for freshness validation — this field is deprecated.
  5. Remind users that example code is unaudited and not for production use without a security review.
  6. If the user is targeting mainnet, emphasize developer responsibilities and recommend a security audit.

Documentation Access

This skill references official Data Feeds 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 Data Feeds 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/reading-price-feeds.md over generating patterns from memory.

Working Rules

  1. Generate working code from knowledge and reference files first. Fetch only when a specific detail is missing.
  2. Treat 0-1 fetches as normal, 2-3 as the ceiling. Most questions need no fetches because the reference files contain the implementation guidance.
  3. When a fetch is needed, apply the cascade: WebFetch first; if it returns <1000 chars of useful content, fall back to curl -s -L -A "Mozilla/5.0..." "<url>"; if both fail, report the URL to the user.
  4. Keep answers proportional — a simple "read a price feed" question gets a code block and brief explanation, not a full tutorial.
  5. Generate code only when code is actually needed.
  6. Keep unsupported or out-of-scope features out of the answer rather than speculating.

平台分布

Codex

37.27%
按下载量换算33

Claude

27.23%
按下载量换算24

Cursor

20.11%
按下载量换算18

Gemini CLI

8.62%
按下载量换算8

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