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.

94

1.21x
Quality

Does it follow best practices?

Impact

96%

1.21x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, actionable routing-and-guardrails skill with strong workflow checkpoints and excellent progressive disclosure of its eight reference files. The main weakness is redundancy between the Progressive Disclosure and Routing sections, which inflates the body.

Suggestions

Merge or cross-reference the Progressive Disclosure and Routing sections: both enumerate the same eight paths with overlapping trigger conditions — consolidate the load-conditions and path-selection logic into a single table to remove redundancy.

Tighten the Safety Guardrails list, which overlaps the Approval Protocol and Routing rules (e.g., mainnet-write refusal and approval requirements appear in multiple places); deduplicate so each rule lives in one canonical location.

Consider collapsing the numbered Working Rules into the relevant sections (Routing, SDK Defaults) rather than a separate catch-all list, reducing the body length while preserving the same guidance.

DimensionReasoningScore

Conciseness

The body is dense and free of concept-explanation fluff, but the Progressive Disclosure (steps 1–10) and Routing (steps 1–12) sections enumerate the same eight paths with largely overlapping trigger conditions, which is redundant and could be consolidated; this fits the mostly-efficient-but-could-be-tightened anchor.

2 / 3

Actionability

As an instruction-only skill it gives concrete, specific guidance — a copy-paste Approval Protocol preflight template, explicit routing rules, and SDK defaults — so code absence is not penalized per the scoring notes; the guidance is directly executable.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced with explicit validation checkpoints — the Approval Protocol, Second Confirmation Rule, and a documentation-fetch fallback chain — providing feedback loops for destructive onchain operations, matching the top anchor.

3 / 3

Progressive Disclosure

Clear overview with well-signaled one-level-deep references; all eight referenced reference files exist and each has an explicit load condition, with content appropriately split out of the main file.

3 / 3

Total

11

/

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.

A strong, third-person description that pairs a comprehensive list of concrete capabilities with an explicit "Use this skill whenever..." trigger clause covering natural user phrasings. It is distinctive and low conflict-risk.

DimensionReasoningScore

Specificity

Lists many concrete actions — "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" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly answers both what (the enumerated capabilities) and when ("Use this skill whenever the user mentions...") with explicit triggers, hitting the top anchor.

3 / 3

Trigger Term Quality

Includes natural user-facing terms — "Chainlink Data Streams, Streams Direct, Data Streams reports, report schemas, report decoding, data-streams-sdk, or real-time low-latency market data from Chainlink" — with good coverage of phrasings a developer would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Chainlink Data Streams) with distinct, product-specific triggers unlikely to fire for unrelated skills; not generic.

3 / 3

Total

12

/

12

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.