diff --git a/src/config/sidebar.ts b/src/config/sidebar.ts index 9a152b5f4d7..0cffebbd133 100644 --- a/src/config/sidebar.ts +++ b/src/config/sidebar.ts @@ -145,6 +145,11 @@ export const SIDEBAR: Partial> = { 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"], + }, ], }, { diff --git a/src/content/cre/getting-started/build-with-ai-go.mdx b/src/content/cre/getting-started/build-with-ai-go.mdx new file mode 100644 index 00000000000..6f746e59e6b --- /dev/null +++ b/src/content/cre/getting-started/build-with-ai-go.mdx @@ -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**: + +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] +``` diff --git a/src/content/cre/getting-started/build-with-ai-ts.mdx b/src/content/cre/getting-started/build-with-ai-ts.mdx new file mode 100644 index 00000000000..7c82b27c4a5 --- /dev/null +++ b/src/content/cre/getting-started/build-with-ai-ts.mdx @@ -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**: + +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] +``` diff --git a/src/content/cre/llms-full-go.txt b/src/content/cre/llms-full-go.txt index 7f0fe89589c..04b66fb09a3 100644 --- a/src/content/cre/llms-full-go.txt +++ b/src/content/cre/llms-full-go.txt @@ -9568,6 +9568,94 @@ Dive deeper into concepts from this guide: --- +# Build with AI (Skill, Prompting) +Source: https://docs.chain.link/cre/getting-started/build-with-ai-go +Last Updated: 2026-03-19 + +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**: https\://docs.chain.link/cre/llms-full-go.txt + +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] +``` + +--- + # Part 1: Project Setup & Simulation Source: https://docs.chain.link/cre/getting-started/part-1-project-setup-go Last Updated: 2026-01-14 diff --git a/src/content/cre/llms-full-ts.txt b/src/content/cre/llms-full-ts.txt index cad7ef0a141..5c87be7d7f7 100644 --- a/src/content/cre/llms-full-ts.txt +++ b/src/content/cre/llms-full-ts.txt @@ -9045,6 +9045,94 @@ Dive deeper into concepts from this guide: --- +# Build with AI (Skill, Prompting) +Source: https://docs.chain.link/cre/getting-started/build-with-ai-ts +Last Updated: 2026-03-19 + +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**: https\://docs.chain.link/cre/llms-full-ts.txt + +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] +``` + +--- + # Part 1: Project Setup & Simulation Source: https://docs.chain.link/cre/getting-started/part-1-project-setup-ts Last Updated: 2026-01-20