CtrlK
BlogDocsLog inGet started
Tessl Logo

chainlink-vrf-skill

Help developers integrate Chainlink VRF into smart contracts. Use for consumer contract generation with VRFConsumerBaseV2Plus, subscription setup and funding (LINK or native), keyHash and gas lane selection, coordinator address lookup and debugging VRF integrations. Trigger on any mention of VRF, verifiable randomness, on-chain random number generation, requestRandomWords, fulfillRandomWords, VRF subscription, VRF coordinator, keyHash, or provably fair randomness in a smart contract, even if the user does not say 'VRF' explicitly.

68

Quality

83%

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

67%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 body is well-structured as a routing/guidance skill with concrete, actionable specifics and a clear decision workflow, but it is held back by repeated safety/non-custodial statements across three sections and a broken bundle reference to a missing templates/starter-kit path.

Suggestions

Consolidate the repeated non-custodial prohibition: 'never execute, sign, broadcast, or deploy' appears in Safety Guardrails, Safety Defaults, and Execution Boundary — merge these into a single section to remove padded repetition and improve conciseness.

Fix or remove the starter-kit references: rules 2a and Routing 1a point to templates/starter-kit/README.md and templates/starter-kit, but no templates/ directory exists in the bundle — either add the starter-kit files or drop those routing instructions.

Tighten Documentation Access and Working Rules, which overlap (both cover fetch cadence and the 'do not improvise from memory' fallback) into one section to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not explain basic concepts Claude already knows, but the non-custodial / 'never execute, sign, broadcast, or deploy' prohibition is restated across Safety Guardrails, Safety Defaults, and Execution Boundary, which is padded repetition that could be consolidated.

3 / 5

Actionability

Guidance is concrete and specific (base contract names VRFConsumerBaseV2Plus / VRFV2PlusWrapperConsumerBase, the RandomWordsRequest struct, uint256 sub IDs, calldata vs memory data locations, a precise legacy-pattern table) with only minor gaps since executable code itself lives in the reference files.

4 / 5

Workflow Clarity

Routing and Progressive Disclosure are clearly sequenced with a clarifying checkpoint ('Ask one focused question if the method or target network is unclear') and a detect/name/migrate feedback step for legacy patterns; the body itself performs no destructive batch operation requiring a validate-fix-retry loop.

4 / 5

Progressive Disclosure

A clear overview with well-signaled one-level-deep references and explicit per-file load conditions, and all seven references/*.md files exist; the gap is that rules 2a and Routing 1a reference templates/starter-kit/README.md and templates/starter-kit, but no templates/ directory is present in the bundle.

4 / 5

Total

15

/

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 strong, dense description that names concrete capabilities, provides comprehensive natural trigger terms, and explicitly covers both what the skill does and when to invoke it. Voice is directive imperative ('Help developers ...') rather than strict third person, but it is neither first nor second person and is not penalized under the rubric.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'consumer contract generation with VRFConsumerBaseV2Plus, subscription setup and funding (LINK or native), keyHash and gas lane selection, coordinator address lookup and debugging' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly answers both 'what' (integrate Chainlink VRF into smart contracts, with concrete actions) and 'when' ('Use for ...' plus an explicit 'Trigger on any mention of ...' clause), matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

The 'Trigger on any mention of VRF, verifiable randomness, on-chain random number generation, requestRandomWords, fulfillRandomWords, VRF subscription, VRF coordinator, keyHash, or provably fair randomness' clause covers natural synonyms and API names comprehensively.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Chainlink VRF v2.5) with distinct, domain-specific triggers unlikely to fire for unrelated skills, keeping conflict risk minimal.

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.