chainlink-ccip-skill

Handle Chainlink CCIP requests including read-only route, token, message-status, and lane lookups; fee-estimation guidance; user-run cross-chain transfer and messaging artifacts; sender and receiver contract development; and CCT setup guidance. The skill never signs or broadcasts transactions. Use whenever the user mentions CCIP, Chainlink cross-chain messaging, CCIP token transfers, CCTs, or CCIP monitoring.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body is a well-structured, lean overview that routes requests, enforces safety guardrails, and delegates detail to a verified set of one-level-deep reference files. Actionability and workflow clarity are strong, with minor gaps only where executable code is deferred to the reference bundle.

Suggestions

Inline one small executable snippet (e.g., a curl example for a CCIP API read or a single sender-contract skeleton) directly in SKILL.md so the overview layer is self-sufficient for the most common case.

Convert the Non-Custodial Action Protocol into an explicit validate->fix->retry checklist so the feedback loop for failed preflight reviews is enumerated rather than implied.

Add a one-line "if X then stop and ask" decision table summarizing the missing-input and unsafe-action branching so Claude can resolve routing without re-reading every section.

Dimension	Reasoning	Score
Conciseness	Lean, instruction-dense body that assumes Claude's competence; it states routing, guardrails, and a preflight template without explaining what CCIP or a blockchain is, so every token earns its place.	5 / 5
Actionability	Concrete guidance includes a copy-ready preflight "Prepared on-chain action" template and specific routing rules, but most executable code lives in the referenced files rather than inline in SKILL.md, leaving minor gaps for the overview layer.	4 / 5
Workflow Clarity	Sequenced routing and safety steps with explicit validation for risky operations (refuse write, emit user-run preflight, ask one focused question), though a few checkpoints are implied rather than enumerated as a validate->fix->retry loop.	4 / 5
Progressive Disclosure	Clear overview with 12 well-signaled, one-level-deep references (all verified to exist) and an explicit "do not load reference files speculatively" rule, making navigation easy.	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, complete, and well-triggered, covering concrete read-only and artifact-generation capabilities alongside an explicit boundary statement. It clearly distinguishes the skill from adjacent Chainlink skills and provides natural user-facing trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions (read-only route/token/message-status/lane lookups, fee-estimation guidance, user-run transfer/messaging artifacts, sender and receiver contract development, CCT setup) with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (the enumerated read-only/artifact/contract/CCT capabilities) and when (the "Use whenever..." clause) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms and synonyms via "Use whenever the user mentions CCIP, Chainlink cross-chain messaging, CCIP token transfers, CCTs, or CCIP monitoring."	5 / 5
Distinctiveness Conflict Risk	Clear CCIP-specific niche with distinct triggers and an explicit credential/broadcast boundary ("never signs or broadcasts transactions") that minimizes overlap with sibling Chainlink skills.	5 / 5
	Total	20 / 20 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
Path: chainlink-ccip-skill/SKILL.md
Commit: 6ea4b1a

Reviewed: about 10 hours 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.