chainlink-ccip-skill

Handle Chainlink CCIP requests including cross-chain token transfers, cross-chain messaging, fund bridging, sender and receiver contract development, message status lookup, route connectivity checks, supported token discovery, and CCT standard. Use this skill whenever the user mentions CCIP, Chainlink cross-chain, cross-chain token bridges on Chainlink, or wants to move tokens or data between blockchains using Chainlink infrastructure, even if they do not say 'CCIP' explicitly.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

57%

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

A well-organized, lean instruction body with excellent progressive disclosure and a concrete preflight template, slightly weakened by repeated safety messaging and the absence of explicit validation feedback loops. Strongest dimension is reference structure; weakest are conciseness and workflow feedback.

Suggestions

Consolidate the overlapping 'never execute/sign/broadcast on-chain actions' guidance from Safety Guardrails, Non-Custodial Action Protocol, and Execution Boundary into a single section to reduce redundancy.

Add an explicit validation step in the preflight workflow (e.g., 're-confirm route, token, and amount against live discovery before handing the artifact to the user') so the destructive-context path has a verify-fix-retry loop.

Inline one minimal executable example (e.g., a read-only status-lookup command or SDK call) in the body so the skill has copy-paste-ready guidance without forcing a reference load for common cases.

Dimension	Reasoning	Score
Conciseness	The prose is lean and assumes Claude's competence without explaining basics, but the 'never execute on-chain actions' message is repeated across Safety Guardrails, Non-Custodial Action Protocol, and Execution Boundary, so it could be tightened.	2 / 3
Actionability	Provides a concrete, copy-paste-ready preflight template and specific routing rules, but the actual executable commands and contract code live in the referenced files rather than the body, leaving the body's guidance partially complete.	2 / 3
Workflow Clarity	Routing and the preflight package form a clear sequenced checklist, but there is no explicit validate-then-fix-then-retry feedback loop for destructive-context operations, which caps this dimension per the rubric.	2 / 3
Progressive Disclosure	Fourteen one-level-deep references, each gated by a specific trigger condition, all pointing to real files, with an explicit 'Do not load reference files speculatively' instruction — a textbook progressive-disclosure structure.	3 / 3
	Total	9 / 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 description: concrete action list, natural trigger terms, explicit 'Use when' guidance, and a clear distinctive niche, all in third person. No meaningful weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'cross-chain token transfers, cross-chain messaging, fund bridging, sender and receiver contract development, message status lookup, route connectivity checks, supported token discovery, and CCT standard' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly states what it does (the action list) and when to use it via 'Use this skill whenever the user mentions...', satisfying both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural user terms ('CCIP', 'Chainlink cross-chain', 'cross-chain token bridges', 'move tokens or data between blockchains') and even notes triggering 'even if they do not say CCIP explicitly', giving good natural-language coverage.	3 / 3
Distinctiveness Conflict Risk	The Chainlink CCIP cross-chain niche is specific with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: smartcontractkit/chainlink-agent-skills
Commit: 6a60106

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.