Skill 11 Oracle Data Feeds
Integrates oracle and data feed services including Chainlink and Pyth price feeds, VRF randomness, and Chainlink Automation keepers. Use when consuming on-chain price data, random numbers, or conditional automation.
Install
$ agentstack add skill-vaquarkhan-web3-agent-skills-skill-11-oracle-data-feeds ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-vaquarkhan-web3-agent-skills-skill-11-oracle-data-feeds) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Oracle & Data Feeds
When to Use
- Reading price feeds for DeFi calculations
- Requesting verifiable random numbers (VRF)
- Setting up Chainlink Automation (keepers)
- Validating oracle freshness and deviation thresholds
- Comparing multi-oracle prices for manipulation detection
Prerequisites
- MCP:
price-feed-server,blockchain-rpc-server - Skill-08 for oracle manipulation risk assessment
Workflow
1. Chainlink Price Feeds
AggregatorV3Interface feed = AggregatorV3Interface(aggregatorAddress);
(, int256 price, , uint256 updatedAt, ) = feed.latestRoundData();Validation checks:
updatedAtwithin heartbeat (varies: 1h ETH/USD, 24h long-tail)price > 0- Compare with Pyth/CoinGecko — flag if deviation > 2%
Feed addresses: see knowledge-base/protocols/ and Chainlink docs per chain.
2. Pyth Network
- Pull model: update price feeds in same tx via
getUpdateData() - Hermes API for off-chain price reads
- Lower latency than push oracles for L2s
3. Chainlink VRF v2.5
- Subscribe or direct funding
- Request randomness:
requestRandomWords(keyHash, subId, minConfirmations, callbackGasLimit, numWords) - Fulfill in callback:
fulfillRandomWords(requestId, randomWords) - Never use block variables (
blockhash,timestamp) for randomness
4. Chainlink Automation
| Type | Use Case | |------|----------| | Time-based | Periodic harvest, rebalance | | Custom logic | checkUpkeep() returns upkeepNeeded | | Log trigger | React to specific events |
Register upkeep with LINK funding; monitor balance.
5. Oracle Security
- Use multiple sources for critical decisions (liquidations, minting)
- Implement staleness checks and circuit breakers
- TWAP for AMM-derived prices (minimum 30-minute window)
- Never use spot DEX price as sole oracle for high-value ops
References
references/chainlink-feeds.mdreferences/pyth-integration.mdprice-feed-serverMCP tools
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: vaquarkhan
- Source: vaquarkhan/web3-agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.