chainlink-cre-skill

Handle CRE (Chainlink Runtime Environment) work: Go/TypeScript workflows, CRE CLI/SDK, triggers (CRON, HTTP, EVM log), HTTP, Confidential HTTP and EVM Read/Write capabilities, Confidential Workflows that run handlers inside a TEE/enclave, secrets, simulation, deployment, and monitoring. Use this skill whenever the user mentions CRE, Chainlink workflows, workflow simulate or deploy, automation with Chainlink, or wants workflow logic to run confidentially in an enclave so node operators cannot see the data it computes over, even if they never say 'CRE'

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

78%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.

A well-architected routing skill: lean, directive, and with excellent progressive disclosure that points to a complete set of real reference files. The body is instruction/routing-oriented (no inline code), which is appropriate but caps actionability and leaves workflow clarity distributed rather than集中的.

Suggestions

Tighten the longest guardrails (#8 secret-custody and #12 confidential-workflows) by moving the enumerated sub-conditions into a reference file, keeping only the rule in SKILL.md.

Add one short inline code snippet or a minimal 'cre init && cre workflow simulate' quick-start block so implementation prompts have a copy-paste starting point without loading a reference.

Consolidate the destructive-operation lifecycle into a single explicit validate→confirm→execute→verify sequence (or point to one in operations.md) so the workflow checkpoint chain is visible end-to-end.

Dimension	Reasoning	Score
Conciseness	The body is a dense, directive routing/guardrail layer with no padding and no explanation of concepts Claude already knows; a couple of guardrails (notably #8 on secrets and #12 on confidential workflows) are long and could be tightened, keeping it just below a 5.	4 / 5
Actionability	Provides concrete, actionable guidance — specific commands ('cre init', 'cre workflow simulate', 'cre login', 'gh issue create'), reference files, and SDK symbols ('runtime.Now()', 'handlerInTee') — but the body itself contains no copy-paste code (deferred to references), so it stops short of a 5.	4 / 5
Workflow Clarity	Sequenced rules with validation checkpoints are present (read reference before CLI command, default to simulation before deploy, approval/second-confirmation for destructive ops, feedback-loop draft→redact→confirm sequence), but workflows are distributed across routing rules rather than presented as a single explicit validate→fix→retry loop.	4 / 5
Progressive Disclosure	Exemplary one-level-deep structure: the body is an explicit decision layer with 16 clearly signaled reference files, each gated by concrete trigger conditions, and all referenced paths exist in ./references/.	5 / 5
	Total	17 / 20 Passed

Description

95%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, comprehensive description that explicitly covers both capabilities and trigger conditions in third person, with excellent natural-language trigger coverage. The only minor weakness is that capabilities are listed as noun-phrase areas rather than discrete concrete actions.

Dimension	Reasoning	Score
Specificity	Lists many specific concrete capabilities (CRON/HTTP/EVM log triggers, Confidential HTTP, EVM Read/Write, TEE/enclave handlers, simulation, deployment, monitoring) with comprehensive coverage, but they are enumerated as capability areas under a single verb ('Handle CRE work') rather than as distinct concrete actions, leaving a minor gap relative to the action-verb anchor at 5.	4 / 5
Completeness	Clearly and explicitly answers both what ('Handle CRE ... work: ...') and when ('Use this skill whenever the user mentions ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger terms including synonyms and paraphrases ('CRE', 'Chainlink workflows', 'workflow simulate or deploy', 'automation with Chainlink', 'confidentially in an enclave so node operators cannot see the data'), and explicitly catches users who 'never say CRE'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Chainlink Runtime Environment workflows) with distinct triggers and minimal conflict risk; the broad 'automation with Chainlink' phrasing is anchored by the specific CRE/enclave context.	5 / 5
	Total	19 / 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-cre-skill/SKILL.md
Commit: 6ea4b1a

Reviewed: about 12 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.