goose-recipes

Create and validate Goose recipe YAML/JSON configurations for AI agent workflows.

1|Updated Sep 17, 2025
One-click install
npx skills add https://github.com/mpazaryna/claude-toolkit --skill goose-recipes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: goose-recipes
Source: https://github.com/mpazaryna/claude-toolkit/tree/main/generated-skills/goose-recipes
Command: npx skills add https://github.com/mpazaryna/claude-toolkit --skill goose-recipes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires goose-ai, and includes assets (resource) and references (resource) components.

What problem does it solve?

Creating and managing Goose recipes (YAML/JSON configurations for AI agents) can be complex, involving syntax, parameter definitions, and extension configurations. This skill simplifies the process by helping users create, configure, validate, and debug recipes, making AI agent setup more accessible and efficient.

Core Features & Use Cases

  • Recipe Creation: Generates recipe.yaml/recipe.json files from basic, advanced, or MCP server templates.
  • Configuration Assistance: Helps configure parameters, extensions (like MCP servers), retry logic, and structured JSON outputs.
  • Validation & Debugging: Assists in identifying and fixing validation errors in recipes.
  • Use Case: A developer wants to create a Goose recipe to automate code reviews. They can use this skill to generate a basic recipe, then add parameters for file input, configure retry logic for robust execution, and define a structured JSON output for review findings.

Quick Start

Create a basic Goose recipe for code review.

Frequently Asked Questions about goose-recipes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Goose AI recipe to automate workflows?

Create a Goose recipe by defining YAML or JSON configurations that specify agent behaviors, tools, and workflows. Include required fields (version, title, description), then add parameters, extensions, retry logic, and structured outputs to match your automation use case.

What fields are required in a Goose recipe configuration?

Goose recipes require version, title, and description fields. Optional fields include instructions, prompt, parameters, extensions for MCP servers, retry logic, and response formatting. All must comply with the recipe schema for validation.

Can I extend Goose recipes with MCP servers?

Yes. Goose recipes support MCP server extensions in the extensions field, allowing you to integrate additional capabilities and tools into your AI agent workflows beyond the base recipe configuration.

How do I validate and debug a Goose recipe?

Validate recipes against the schema to catch syntax and field errors. Debug by checking required fields are present, parameter definitions are correct, extensions are properly configured, and retry logic matches your workflow requirements.

What's the best way to structure parameters and outputs in Goose recipes?

Define parameters in the parameters field with types and defaults for dynamic inputs. Structure JSON outputs using the response field to ensure consistent, machine-readable results across code analysis, data processing, and automation pipelines.

Do I need coding experience to create Goose recipes?

No. This skill guides you through recipe creation using templates for basic and advanced scenarios. You configure existing fields rather than write code, making AI agent setup accessible without deep technical knowledge.