mcpbeat Sign in

Chainlink Data Feeds Skill

Help developers integrate Chainlink Data Feeds into smart contracts and applications. Use for price feed integration, feed address lookup, consumer contract generation, multi-chain data feeds (EVM, Solana, Aptos, StarkNet, Tron), MVR bundle feeds, SVR/OEV feeds, feed monitoring, historical data, L2 sequencer checks, rates/volatility feeds, SmartData/RWA feeds, or debugging feed integrations. Trigger on any mention of Chainlink price feeds, oracle data, AggregatorV3Interface, latestRoundData, or feed addresses.

64k tokens
context cost
the whole folder, loaded on every use
19
files
instructions only
0
copies elsewhere
how many repositories repackaged it
122
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill chainlink-data-feeds-skill

What comes with it

251 173 bytes besides the instruction
agents/openai.yaml
assets/chainlink-icon.png
assets/data-feeds-docs-index.md
references/feed-operations.md
references/feed-types.md
references/multi-chain.md
references/mvr-feeds.md
references/official-sources.md
references/reading-price-feeds.md
references/source-code.md
references/svr-feeds.md
templates/starter-kit/README.md
templates/starter-kit/foundry.toml
templates/starter-kit/remappings.txt
templates/starter-kit/script/PriceFeedConsumer.s.sol
templates/starter-kit/src/PriceFeedConsumer.sol
templates/starter-kit/test/PriceFeedConsumer.t.sol
templates/starter-kit/test/mocks/MockV3Aggregator.sol

What it tells the agent to use

found in the instruction text
Read reads your files
WebFetch fetches pages from the network

The instruction itself

7 sections, as written by the author

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

  • Keep this file as the default guide.
  • 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.
  • Read templates/starter-kit/README.md and the files in templates/starter-kit when the user asks for a working example project, Foundry starter kit, runnable Data Feeds example, or says something like "give me a working example of a data feeds project." Use this starter-kit template instead of inventing project scaffolding.
  • Read references/mvr-feeds.md only when the user asks about Multiple-Variable Response feeds, bundle feeds, or BundleAggregatorProxy.
  • Read references/svr-feeds.md only when the user asks about Smart Value Recapture, OEV recapture, or searcher onboarding.
  • 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.
  • Read references/multi-chain.md only when the user targets Solana, StarkNet, Aptos, or Tron.
  • Read references/feed-operations.md only when the user asks about L2 sequencer uptime checks, feed deprecation, contract registry, developer responsibilities, or data sources.
  • 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.

10. Read references/source-code.md only when debugging interface mismatches or the user needs to inspect contract source code on GitHub.

11. Do not load reference files speculatively.

Routing

  • Use reading-price-feeds.md as the default for any EVM price feed request — this covers the vast majority of Data Feeds use cases.
  • Use templates/starter-kit for project-level example requests, especially Foundry starter requests. Return a concise file tree, the relevant template files, install/test commands, and the Sepolia ETH/USD feed configuration unless the user asks for another chain.
  • Route to the chain-specific section of multi-chain.md for non-EVM chains (Solana, Aptos, StarkNet, Tron).
  • Route to mvr-feeds.md for bundle or multi-variable feed requests.
  • Route to svr-feeds.md for OEV or MEV recapture requests.
  • Route to feed-operations.md for operational concerns (L2 sequencer checks, deprecation, monitoring).
  • Ask one focused question if the chain, feed type, or integration method is unclear.
  • 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.

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

  • If WebFetch, a browser tool, or an MCP server that can retrieve documentation is available, use it to fetch the referenced URL before answering.
  • 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.
  • 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

  • Generate working code from knowledge and reference files first. Fetch only when a specific detail is missing.
  • Treat 0-1 fetches as normal, 2-3 as the ceiling. Most questions need no fetches because the reference files contain the implementation guidance.
  • 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.
  • Keep answers proportional — a simple "read a price feed" question gets a code block and brief explanation, not a full tutorial.
  • Generate code only when code is actually needed.
  • Keep unsupported or out-of-scope features out of the answer rather than speculating.
  • When using the starter-kit template, preserve its Foundry layout and contract names unless the user asks for a different framework. The template is based on the Chainlink Foundry Starter Kit PriceFeedConsumer.sol example, with the required Data Feeds validation added for safer generated code.

Other skills for the same job

different authors, same section of the catalogue
MCP Deploy Manage Agents
by github
vendor ×1

Skill converted from mcp-deploy-manage-agents.prompt.md

2k tokens
Cloud Claw Launch Agent
by internet-court
×1

Use this skill when the user wants to launch a new AltClaw, OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw. Covers the same user-facing fields and constraints exposed in the Cloud Claw UI, using the local altllm cloud-claw-* commands. Do NOT use for post-launch lifecycle tasks like start/stop/delete/logs; use cloud-claw-manage-vm.

1k tokens
Hosted Agents V2 Py
by lingxling
×1

Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents in Azure AI Foundry.

2k tokens
Cloudflare MCP Server
by ComeOnOliver
×1

Build MCP (Model Context Protocol) servers on Cloudflare Workers with tools, resources, and prompts.

49k tokens scripts
When Chaining Agent Pipelines Use Stream Chain
by ComeOnOliver
×1

Chain agent outputs as inputs in sequential or parallel pipelines for data flow orchestration

5k tokens
Clone Audit Mrlv3nl4
by nexu-io

Audit cloned or reimplemented websites for fidelity gaps, tracking scripts, source-brand and language residue, placeholders, and risky external dependencies. Use before handoff or deployment, or when asked to review a website clone for cleanup and readiness.

2k tokens
Hermes Tweet
by wshobson

> Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated tweet actions. Use this skill when installing Hermes Tweet, researching X/Twitter accounts, monitoring launch signals, investigating mentions, auditing giveaways, or preparing guarded tweet actions. Use proactively when a Hermes Agent workflow needs current X/Twitter context. Requires XQUIK_API_KEY for read and action tools.

2k tokens
Arize Evaluator
by github
vendor

Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.

10k tokens

How to use it

Copy the folder

Take smartcontractkit/chainlink-data-feeds-skill from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.