Skip to content

Add Build with AI getting started page #3574

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
dev-dist merged 6 commits into from
Mar 19, 2026
Merged

Add Build with AI getting started page #3574

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
963521e
Add Build with AI getting started page for CRE docs
wentzeld Mar 19, 2026
1a56cf5
Split Build with AI page into language-specific variants
wentzeld Mar 19, 2026
4dcb066
sidebar fix
wentzeld Mar 19, 2026
09772ef
Delete src/content/cre/getting-started/build-with-ai.mdx
wentzeld Mar 19, 2026
206d5a0
various changes, references to docs, more info
dev-dist Mar 19, 2026
a3b967a
Merge branch 'main' into build-with-ai-page
dev-dist Mar 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions src/config/sidebar.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,6 +145,11 @@ export const SIDEBAR: Partial<Record<Sections, SectionEntry[]>> = {
url: "cre/getting-started/before-you-build",
highlightAsCurrent: ["cre/getting-started/before-you-build-ts", "cre/getting-started/before-you-build-go"],
},
{
title: "Build with AI (Skill, Prompting)",
url: "cre/getting-started/build-with-ai",
highlightAsCurrent: ["cre/getting-started/build-with-ai-ts", "cre/getting-started/build-with-ai-go"],
},
],
},
{
Expand Down
110 changes: 110 additions & 0 deletions src/content/cre/getting-started/build-with-ai-go.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,110 @@
---
section: cre
date: Last Modified
title: "Build with AI (Skill, Prompting)"
pageId: "getting-started-build-with-ai"
sdkLang: "go"
metadata:
title: "Build CRE Workflows with AI (Skill, Prompting) | Chainlink CRE"
description: "Use AI coding assistants to build Chainlink CRE workflows in Go. Install the CRE agent skill for Cursor, Claude Code, and Codex, or use LLM prompting to generate workflows, debug issues, and explore the SDK."
keywords:
[
"CRE skill",
"agent skill",
"AI coding assistant",
"LLM prompting",
"Cursor skill",
"Claude Code skill",
"Chainlink CRE Go",
"CRE workflow generation",
"AI workflow builder",
"Codex skill",
"Gemini skill",
]
datePublished: "2026-03-19"
lastModified: "2026-03-19"
---

import { Aside, CopyText } from "@components"

You can use AI coding assistants to generate, debug, and explore CRE workflows. There are two approaches: install a skill in your code editor agent or load CRE context into any LLM chat and prompt from there.

## Code editor skill

Agent skills are structured instruction sets that give an AI coding agent domain-specific knowledge and a defined approach for a task. When you install a skill, your agent reads it at the start of a session and uses it to guide how it fetches docs, generates code, and debugs — without you having to repeat that context every time. See the [Agent Skills specification](https://agentskills.io/specification) for the full format and best practices.

### Supported agent tools

The skill works with any agent-capable AI coding tool that implements the [Agent Skills specification](https://agentskills.io/specification). Verified with Claude Code, Cursor, Codex, Gemini, Copilot, and Cline.

### Install the skill

Run the following command to add the CRE skill to your code editor agent:

```shell
npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill cre-skills
```

### Prompt your agent

Once installed, your agent will automatically discover and activate the skill based on your task. For best results across tools, explicitly reference it in your prompt:

```
Use the /cre-skills skill and [describe what you want to build]
```

In Claude Code, you can invoke it directly as a slash command: `/cre-skills`.

### What the skill covers

The skill is organized into focused reference areas, each covering a specific part of CRE. When you ask a question, your agent matches it to the most relevant area and fetches only what it needs — so you get a targeted answer without the agent reading the entire SDK. The areas the skill covers:

| Topic | What it helps with |
| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Getting started](/cre/getting-started/overview) | [CLI installation](/cre/getting-started/cli-installation), [project setup](/cre/getting-started/part-1-project-setup), tutorial walkthrough |
| [Account setup](/cre/account) | [Creating accounts](/cre/account/creating-account), [CLI login](/cre/account/cli-login), [managing authentication](/cre/account/managing-auth) |
| Workflow building | [Secrets](/cre/guides/workflow/secrets), [triggers](/cre/guides/workflow/using-triggers/overview) (cron/HTTP/EVM log), [HTTP client](/cre/guides/workflow/using-http-client), [EVM client](/cre/guides/workflow/using-evm-client/overview), onchain read/write |
| [SDK reference](/cre/reference/sdk/overview) | [Core SDK](/cre/reference/sdk/core), [consensus/aggregation](/cre/reference/sdk/consensus), [EVM client](/cre/reference/sdk/evm-client), [HTTP client](/cre/reference/sdk/http-client), [trigger APIs](/cre/reference/sdk/triggers/overview) |
| [CLI reference](/cre/reference/cli) | [Accounts](/cre/reference/cli/account), [authentication](/cre/reference/cli/authentication), [secrets](/cre/reference/cli/secrets), [workflows](/cre/reference/cli/workflow), [utilities](/cre/reference/cli/utilities) |
| [Capabilities](/cre/capabilities) | [EVM read/write](/cre/capabilities/evm-read-write), [HTTP](/cre/capabilities/http), [triggers overview](/cre/capabilities/triggers) |
| Operations | [Deploying](/cre/guides/operations/deploying-workflows), [simulating](/cre/guides/operations/simulating-workflows), [monitoring](/cre/guides/operations/monitoring-workflows), [activating/pausing](/cre/guides/operations/activating-pausing-workflows), [updating](/cre/guides/operations/updating-deployed-workflows), [deleting workflows](/cre/guides/operations/deleting-workflows) |
| Concepts | [Consensus computing](/cre/concepts/consensus-computing), [finality](/cre/concepts/finality), [non-determinism](/cre/concepts/non-determinism) |
| [Templates](/cre/templates) | CRE workflow templates and usage |

### Workflow generation

When you ask the skill to build a workflow, it will:

1. Confirm whether you want Go or TypeScript
2. Ask whether HTTP requests should use regular or Confidential HTTP (for privacy-preserving API calls via enclave execution)
3. Generate the complete workflow scaffold immediately — no speculative fetching
4. Give you a `cre workflow simulate` command to test it
5. Iterate on errors by fetching exactly what the error names, fixing it, and asking you to re-run

### Debugging

When diagnosing errors, the skill identifies the capability involved, fetches the relevant doc page, checks repo examples if needed, and proposes a fix based on CRE-specific constraints — not general programming assumptions.

## Prompting

If you prefer to work directly in an AI assistant, you can load the full CRE Go documentation into the context window and prompt from there. This is useful for broad exploration, but loads the entire SDK reference upfront — the skill approach above keeps your context window focused on your current task.

**Context file**: <CopyText text="https://docs.chain.link/cre/llms-full-go.txt" code />

Alternatively, you can click the "Copy Page" button in the top right corner of any Chainlink docs page to load the full page content into the context window of your preferred AI assistant. Loading a single page — for example, just the triggers reference or the EVM client page — rather than the entire SDK consumes fewer tokens (lower cost per request for pay-per-token APIs), keeps you within the limits of smaller context windows, and gives the model more relevant signal to attend to, which tends to produce more accurate output.

Copy the starter prompt below, replace the placeholder at the end with your use case, and paste it into your preferred AI assistant.

```
I'm building a Chainlink CRE workflow using the Go SDK.

Here is the full CRE Go documentation:
https://docs.chain.link/cre/llms-full-go.txt

Please fetch and read that file. After you've read it, please:
- Help me build a CRE workflow based on what I describe
- Answer any questions I have about the CRE Go SDK
- Guide me through implementation step by step

I want to build: [describe your use case]
```
110 changes: 110 additions & 0 deletions src/content/cre/getting-started/build-with-ai-ts.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,110 @@
---
section: cre
date: Last Modified
title: "Build with AI (Skill, Prompting)"
pageId: "getting-started-build-with-ai"
sdkLang: "ts"
metadata:
title: "Build CRE Workflows with AI (Skill, Prompting) | Chainlink CRE"
description: "Use AI coding assistants to build Chainlink CRE workflows in TypeScript. Install the CRE agent skill for Cursor, Claude Code, and Codex, or use LLM prompting to generate workflows, debug issues, and explore the SDK."
keywords:
[
"CRE skill",
"agent skill",
"AI coding assistant",
"LLM prompting",
"Cursor skill",
"Claude Code skill",
"Chainlink CRE TypeScript",
"CRE workflow generation",
"AI workflow builder",
"Codex skill",
"Gemini skill",
]
datePublished: "2026-03-19"
lastModified: "2026-03-19"
---

import { Aside, CopyText } from "@components"

You can use AI coding assistants to generate, debug, and explore CRE workflows. There are two approaches: install a skill in your code editor agent or load CRE context into any LLM chat and prompt from there.

## Code editor skill

Agent skills are structured instruction sets that give an AI coding agent domain-specific knowledge and a defined approach for a task. When you install a skill, your agent reads it at the start of a session and uses it to guide how it fetches docs, generates code, and debugs — without you having to repeat that context every time. See the [Agent Skills specification](https://agentskills.io/specification) for the full format and best practices.

### Supported agent tools

The skill works with any agent-capable AI coding tool that implements the [Agent Skills specification](https://agentskills.io/specification). Verified with Claude Code, Cursor, Codex, Gemini, Copilot, and Cline.

### Install the skill

Run the following command to add the CRE skill to your code editor agent:

```shell
npx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill cre-skills
```

### Prompt your agent

Once installed, your agent will automatically discover and activate the skill based on your task. For best results across tools, explicitly reference it in your prompt:

```
Use the /cre-skills skill and [describe what you want to build]
```

In Claude Code, you can invoke it directly as a slash command: `/cre-skills`.

### What the skill covers

The skill is organized into focused reference areas, each covering a specific part of CRE. When you ask a question, your agent matches it to the most relevant area and fetches only what it needs — so you get a targeted answer without the agent reading the entire SDK. The areas the skill covers:

| Topic | What it helps with |
| ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Getting started](/cre/getting-started/overview) | [CLI installation](/cre/getting-started/cli-installation), [project setup](/cre/getting-started/part-1-project-setup), tutorial walkthrough |
| [Account setup](/cre/account) | [Creating accounts](/cre/account/creating-account), [CLI login](/cre/account/cli-login), [managing authentication](/cre/account/managing-auth) |
| Workflow building | [Secrets](/cre/guides/workflow/secrets), [triggers](/cre/guides/workflow/using-triggers/overview) (cron/HTTP/EVM log), [HTTP client](/cre/guides/workflow/using-http-client), [EVM client](/cre/guides/workflow/using-evm-client/overview), onchain read/write |
| [SDK reference](/cre/reference/sdk/overview) | [Core SDK](/cre/reference/sdk/core), [consensus/aggregation](/cre/reference/sdk/consensus), [EVM client](/cre/reference/sdk/evm-client), [HTTP client](/cre/reference/sdk/http-client), [trigger APIs](/cre/reference/sdk/triggers/overview) |
| [CLI reference](/cre/reference/cli) | [Accounts](/cre/reference/cli/account), [authentication](/cre/reference/cli/authentication), [secrets](/cre/reference/cli/secrets), [workflows](/cre/reference/cli/workflow), [utilities](/cre/reference/cli/utilities) |
| [Capabilities](/cre/capabilities) | [EVM read/write](/cre/capabilities/evm-read-write), [HTTP](/cre/capabilities/http), [triggers overview](/cre/capabilities/triggers) |
| Operations | [Deploying](/cre/guides/operations/deploying-workflows), [simulating](/cre/guides/operations/simulating-workflows), [monitoring](/cre/guides/operations/monitoring-workflows), [activating/pausing](/cre/guides/operations/activating-pausing-workflows), [updating](/cre/guides/operations/updating-deployed-workflows), [deleting workflows](/cre/guides/operations/deleting-workflows) |
| Concepts | [Consensus computing](/cre/concepts/consensus-computing), [finality](/cre/concepts/finality), [non-determinism](/cre/concepts/non-determinism), [TypeScript WASM runtime](/cre/concepts/typescript-wasm-runtime) |
| [Templates](/cre/templates) | CRE workflow templates and usage |

### Workflow generation

When you ask the skill to build a workflow, it will:

1. Confirm whether you want Go or TypeScript
2. Ask whether HTTP requests should use regular or Confidential HTTP (for privacy-preserving API calls via enclave execution)
3. Generate the complete workflow scaffold immediately — no speculative fetching
4. Give you a `cre workflow simulate` command to test it
5. Iterate on errors by fetching exactly what the error names, fixing it, and asking you to re-run

### Debugging

When diagnosing errors, the skill identifies the capability involved, fetches the relevant doc page, checks repo examples if needed, and proposes a fix based on CRE-specific constraints — not general programming assumptions.

## Prompting

If you prefer to work directly in an AI assistant, you can load the full CRE TypeScript documentation into the context window and prompt from there. This is useful for broad exploration, but loads the entire SDK reference upfront — the skill approach above keeps your context window focused on your current task.

**Context file**: <CopyText text="https://docs.chain.link/cre/llms-full-ts.txt" code />

Alternatively, you can click the "Copy Page" button in the top right corner of any Chainlink docs page to load the full page content into the context window of your preferred AI assistant. Loading a single page — for example, just the triggers reference or the EVM client page — rather than the entire SDK consumes fewer tokens (lower cost per request for pay-per-token APIs), keeps you within the limits of smaller context windows, and gives the model more relevant signal to attend to, which tends to produce more accurate output.

Copy the starter prompt below, replace the placeholder at the end with your use case, and paste it into your preferred AI assistant.

```
I'm building a Chainlink CRE workflow using the TypeScript SDK.

Here is the full CRE TypeScript documentation:
https://docs.chain.link/cre/llms-full-ts.txt

Please fetch and read that file. After you've read it, please:
- Help me build a CRE workflow based on what I describe
- Answer any questions I have about the CRE TypeScript SDK
- Guide me through implementation step by step

I want to build: [describe your use case]
```
Loading
Loading