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.

78

2.85x
Quality

Does it follow best practices?

Impact

100%

2.85x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is a well-organized, actionable routing guide with strong safety defaults and a fetch fallback loop, but it duplicates routing logic across two sections and points to a missing templates/starter-kit path. Tightening the overlap and fixing the broken reference would raise quality.

Suggestions

Consolidate the 'Progressive Disclosure' and 'Routing' sections into a single routing table to eliminate the duplicated per-topic mapping.

Add the missing 'templates/starter-kit/' bundle (including README.md) or remove the starter-kit references from SKILL.md so no link points to a non-existent path.

Consider moving the curl fallback command into references/official-sources.md so the body stays a pure overview, reducing token cost on the default path.

DimensionReasoningScore

Conciseness

The body is largely lean and free of concept padding, but the 'Progressive Disclosure' (11 items) and 'Routing' (8 items) sections restate essentially the same per-topic routing map, duplicating tokens that could be consolidated.

2 / 3

Actionability

Gives concrete executable guidance — a real fallback command ('curl -s -L -A "Mozilla/5.0 ..." "<url>"') and precise directives ('check updatedAt against a staleness threshold', 'Always call decimals() on the feed') — rather than vague direction.

3 / 3

Workflow Clarity

The request-to-reference flow is clearly sequenced, the 'Safety Defaults' act as a validation checklist for generated code, and the fetch cascade (WebFetch -> curl -> report URL) is an explicit error-recovery loop.

3 / 3

Progressive Disclosure

Structure is otherwise well-signaled with one-level-deep reference links and 'Read X only when ...' triggers, but the body repeatedly references 'templates/starter-kit/README.md' and 'templates/starter-kit', which do not exist in the bundle, breaking navigation for that path.

2 / 3

Total

10

/

12

Passed

Description

100%

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

The description is specific, trigger-rich, and clearly distinguishes this skill with concrete capabilities and explicit when-to-use guidance in third-person voice. It is a strong, well-targeted description.

DimensionReasoningScore

Specificity

Lists many concrete actions such as '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', matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what ('Help developers integrate Chainlink Data Feeds into smart contracts and applications') and when ('Use for ...', 'Trigger by any mention of ...'), satisfying the explicit-trigger anchor.

3 / 3

Trigger Term Quality

Includes natural terms a developer would actually say ('Chainlink price feeds', 'oracle data', 'feed addresses') plus API-level triggers ('AggregatorV3Interface', 'latestRoundData'), giving strong coverage.

3 / 3

Distinctiveness Conflict Risk

The niche is narrowly scoped to Chainlink Data Feeds and triggers on highly specific identifiers (AggregatorV3Interface, latestRoundData), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.