CtrlK
BlogDocsLog inGet started
Tessl Logo

chainlink-data-streams-skill

Help developers build with Chainlink Data Streams, including credentials guidance, report decoding, REST and WebSocket report retrieval with official Go/Rust/TypeScript SDKs, High Availability streaming, on-chain report verification, real-time frontend displays, report schema guidance, SQLite persistence, and timestamp lookback. Use this skill whenever the user mentions Chainlink Data Streams, Streams Direct, Data Streams reports, report schemas, report decoding, data-streams-sdk, or real-time low-latency market data from Chainlink.

88

2.72x
Quality

93%

Does it follow best practices?

Impact

98%

2.72x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

The content is a well-structured, token-efficient routing and guardrail layer that delegates detail to verified one-level reference files and gates destructive onchain writes behind a non-custodial preflight. Its only weakness is that executable SDK code lives entirely in the references rather than inline.

Suggestions

Add one small inline copy-paste example per major path (e.g., a minimal REST report fetch and a WebSocket subscribe snippet) so the SKILL.md is actionable without opening a reference.

For the non-custodial preflight, add an explicit validate→fix→retry step (e.g., re-check addresses/feed IDs/schema version before preparing the artifact) to push workflow_clarity toward 5.

Surface a one-line 'how to verify an onchain report locally with Chainlink Local' pointer inline so users get a safe executable path before reaching for mainnet writes.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — routing rules, safety guardrails, and a compact preflight template — with no padding or explanation of concepts Claude already knows; every line earns its place.

5 / 5

Actionability

Concrete directives and a copy-paste preflight package template make the guidance mostly executable, but no runnable SDK code is inline (it is deferred to reference files), leaving minor gaps for an otherwise actionable instruction skill.

4 / 5

Workflow Clarity

Routing and the non-custodial onchain-write workflow are clearly sequenced with an explicit user-sign/broadcast checkpoint and a destructive-action cap, though recovery is framed as a hard boundary rather than a validate→fix→retry feedback loop.

4 / 5

Progressive Disclosure

A clear overview points to eight one-level-deep reference files, all of which exist on disk, each signaled with a specific read-condition and reinforced by 'Do not load reference files speculatively.'

5 / 5

Total

18

/

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.

The description is specific, comprehensive, and well-triggered, clearly stating both what the skill does and when to use it with natural trigger terms. It is highly distinctive and unlikely to fire for unrelated skills.

DimensionReasoningScore

Specificity

Enumerates many concrete actions — 'credentials guidance, report decoding, REST and WebSocket report retrieval', 'on-chain report verification, real-time frontend displays, report schema guidance, SQLite persistence, and timestamp lookback' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (build with Data Streams across the listed capabilities) and 'when' via a concrete 'Use this skill whenever the user mentions...' trigger clause.

5 / 5

Trigger Term Quality

The 'Use this skill whenever the user mentions Chainlink Data Streams, Streams Direct, Data Streams reports, report schemas, report decoding, data-streams-sdk, or real-time low-latency market data from Chainlink' clause covers natural terms, synonyms, and the SDK package name.

5 / 5

Distinctiveness Conflict Risk

Triggers are tightly scoped to Chainlink Data Streams, Streams Direct, and data-streams-sdk, carving a clear niche with minimal overlap risk against other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.