CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, well-structured routing skill: lean overview, explicit per-reference trigger conditions, concrete safety defaults, and a defined fetch cascade. The main defect is a dangling reference to a templates/starter-kit directory that is absent from the bundle.

Suggestions

Resolve the templates/starter-kit references: either add the templates/starter-kit/ files (README.md, PriceFeedConsumer.sol, Foundry config, install/test commands) to the bundle, or remove the three mentions in the Progressive Disclosure, Routing, and Working Rules sections and route those requests to references/reading-price-feeds.md instead.

Tighten Working Rules items 2-3 (fetch-count guidance and the WebFetch→curl→report cascade) into a single compact cascade so the fetch policy reads as one rule rather than two overlapping ones.

Add an explicit validation step to the main code-generation workflow (e.g., "after generating a consumer, re-check it against every Safety Default before returning") so the primary flow has a clear validate→fix→retry checkpoint.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — it does not explain what Chainlink or oracles are — but a few Working Rules (e.g., "Treat 0-1 fetches as normal, 2-3 as the ceiling") and some Safety Defaults phrasing could be tightened, keeping it just below the lean/5 anchor.

4 / 5

Actionability

Concrete, specific guidance throughout — named reference files with exact trigger conditions, a literal fetch cascade ("WebFetch first... curl -s -L -A ... <url>... report the URL"), and a promised file-tree/install-command output for the starter kit — though the executable code itself lives in the reference files rather than the body, leaving minor gaps.

4 / 5

Workflow Clarity

Routing and Progressive Disclosure sections give a clear, sequenced decision path, and the fetch cascade plus Safety Defaults act as validation checkpoints; however there is no explicit validate→fix→retry loop for the main code-generation workflow, so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

A clear overview with well-signaled, one-level-deep references — each of the 8 reference files has an explicit read-condition — but the body references templates/starter-kit/README.md and templates/starter-kit/ (3 mentions) and that directory does not exist in the bundle, a navigation gap that holds it below 5.

4 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description: concrete capabilities, explicit trigger guidance, and a clear niche. It is written in the imperative third-person voice consistent with the good examples and avoids fluff.

DimensionReasoningScore

Specificity

Lists many concrete actions — "price feed integration", "feed address lookup", "consumer contract generation", "multi-chain data feeds", "MVR bundle feeds", "SVR/OEV feeds", "feed monitoring", "historical data", "L2 sequencer checks", "rates/volatility feeds", "SmartData/RWA feeds", "debugging feed integrations" — giving comprehensive coverage rather than vague domain naming.

5 / 5

Completeness

Explicitly answers both "what" ("Help developers integrate Chainlink Data Feeds...") and "when" ("Use for..." plus "Trigger on any mention of...") with concrete trigger phrases, satisfying the top anchor.

5 / 5

Trigger Term Quality

Uses an explicit "Trigger on any mention of..." clause with natural developer-facing terms ("Chainlink price feeds", "oracle data", "AggregatorV3Interface", "latestRoundData", "feed addresses") that a user would actually say, covering synonyms and interface/function names.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (Chainlink Data Feeds only) with Data-Feeds-specific triggers, minimizing overlap with adjacent Chainlink skills (CCIP, Automation, Functions).

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
smartcontractkit/chainlink-agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.