outputai

How to start

1. Paste the command into Claude Code and press Enter.
2. Restart Claude Code so the plugin loads.
3. Just ask Claude. Its skills step in when your request fits.

What it adds

5 agents · 51 skills · 1 hook

Agents Claude hands work to these

• workflow-context-fetcherUse proactively to retrieve and extract relevant information from Output SDK project documentation files. Checks if content is already in context before return…
• workflow-debuggerUse this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze…
• workflow-plannerDesign new workflows for the Output SDK system, plan complex workflow orchestrations, or create comprehensive implementation blueprints. Use at the beginning o…
• workflow-prompt-writerUse this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and…
• workflow-qualityUse this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow…

Skills Claude loads these when the task fits

• output-build-workflowImplement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an existing plan, or after output-pl…
• output-credentials-editView, edit, and set encrypted credentials in an Output.ai project. Use when adding secrets, updating API keys, verifying credential values, or retrieving a spe…
• output-credentials-env-varsWire encrypted credentials to environment variables using the credential: convention. Use when setting up LLM provider keys (ANTHROPIC_API_KEY, OPENAI_API_KEY)…
• output-credentials-initInitialize encrypted credentials for an Output.ai project. Use when setting up credentials for the first time, adding environment-specific credentials, or addi…
• output-debug-workflowDebug Output SDK workflow issues. Use when user reports a workflow failing, erroring, hanging, producing wrong results, or asks to debug, troubleshoot, or inve…
• output-dev-agent-classUse the Agent class for multi-step tool loops, conversation history, streaming progress, and reusable LLM agents. Use when building agents with skills, structu…
• output-dev-code-styleCode style conventions for Output SDK workflow projects. Use when writing or reviewing any TypeScript/JavaScript code. Discovers the project's own linting rule…
• output-dev-cost-hooksSubscribe to cost events (cost:http:request, llm:generation:metering) to forward LLM and API spend to your own observability system. Use when adding cost/spend…
• output-dev-create-skeletonGenerate workflow skeleton files using the Output SDK CLI. Use when starting a new workflow, scaffolding project structure, or understanding the generated file…
• output-dev-credentialsStore and reference encrypted secrets in Output SDK workflows using @outputai/core/credentials. Use when integrating API keys, database passwords, or third-par…
• output-dev-eval-testingCreate offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML file…
• output-dev-evaluator-functionCreate evaluator functions in evaluators.ts for Output SDK workflows. Use when implementing quality assessment, validation logic, or content evaluation.
• …and 39 more in the source.

Hooks Run on their own at these moments

• SessionStartWhen a session starts.

Read from the plugin's own files in growthxai/output, 26 Oct 2026.

What it needs

No keys or settings: its files ask for none.