Recipe Finder

Community

coleam00

recipe_finder

Search recipes by ingredients, cuisine, or dietary needs. Get nutrition info, meal plans, and cooking instructions. Use when user asks about cooking, recipes, meals, or food.

Overview

Publisher	coleam00
Repository	`custom-agent-with-skills`
Skill name	`recipe_finder`
Stars	107
Forks	42
Bundled files	2
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by coleam00 on GitHub. Read the source before you install it.

Installation

Install the Recipe Finder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/coleam00/custom-agent-with-skills/tree/main/skills/recipe_finder
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/coleam00/custom-agent-with-skills.git /tmp/custom-agent-with-skills
mkdir -p .claude/skills
cp -r /tmp/custom-agent-with-skills/skills/recipe_finder .claude/skills/recipe_finder

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Recipe Finder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Recipe Finder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Recipe Finder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Recipe Finder Skill

Find recipes, get nutrition information, and create meal plans using free recipe APIs. Supports searching by ingredients, dietary restrictions, cuisine type, and more.

When to Use

User asks for recipe suggestions
User wants to know what to cook with specific ingredients
User has dietary restrictions (vegetarian, gluten-free, keto, etc.)
User asks about nutrition or calories in a recipe
User wants meal planning help
User asks about cooking instructions or techniques
User asks "what can I make with..."

Available Operations

Recipe Search: Find recipes by keyword, ingredient, or cuisine
Ingredient-Based Search: "What can I make with chicken and broccoli?"
Dietary Filtering: Filter by diet (vegan, keto, paleo) or intolerances
Nutrition Analysis: Get calorie and nutrient breakdown
Random Recipe: Get a random recipe for inspiration
Recipe Details: Get full instructions, ingredients, and nutrition

Instructions

When a user asks about recipes or cooking:

Step 1: Understand the Query

Identify what the user needs:

Ingredient-based: "What can I make with [ingredients]?"
Cuisine search: "Give me Italian recipes"
Dietary needs: "Keto dinner ideas"
Specific dish: "How do I make chicken parmesan?"
Nutrition focused: "Low calorie lunch ideas"

Step 2: Load API Reference

ALWAYS read references/api_reference.md before making API calls. The APIs have specific parameter formats.

Step 3: Choose the Right API

Option A: TheMealDB (Simpler, Completely Free)

Good for: Basic recipe search, random recipes, category browsing
URL: https://www.themealdb.com/api/json/v1/1/
No API key needed (use "1" as the key)

Option B: Spoonacular (More Powerful, Free Tier)

Good for: Ingredient search, nutrition, dietary filters
Requires API key (free tier: 150 points/day)
More detailed data but limited calls

Step 4: Make the API Call

TheMealDB Example (search by name):


https://www.themealdb.com/api/json/v1/1/search.php?s=chicken

Spoonacular Example (search by ingredients):


https://api.spoonacular.com/recipes/findByIngredients?ingredients=chicken,broccoli&number=5&apiKey=YOUR_KEY

Step 5: Present Results

Format recipes clearly with:

Recipe name
Brief description or cuisine type
Key ingredients
Cooking time (if available)
Dietary info (vegetarian, gluten-free, etc.)
Link to full recipe or instructions

Dietary Restriction Mappings

User Says...	API Parameter
"vegetarian"	`diet=vegetarian`
"vegan"	`diet=vegan`
"gluten-free"	`intolerances=gluten`
"dairy-free"	`intolerances=dairy`
"keto" or "low-carb"	`diet=ketogenic`
"paleo"	`diet=paleo`
"nut-free"	`intolerances=tree nut,peanut`
"healthy"	`maxCalories=500` or `diet=whole30`

Cuisine Types

TheMealDB categories: American, British, Canadian, Chinese, Croatian, Dutch, Egyptian, Filipino, French, Greek, Indian, Irish, Italian, Jamaican, Japanese, Kenyan, Malaysian, Mexican, Moroccan, Polish, Portuguese, Russian, Spanish, Thai, Tunisian, Turkish, Vietnamese

Resources

ALWAYS read these before making API calls:

references/api_reference.md - Complete API documentation for both services
references/dietary_guide.md - Detailed dietary restriction information

Examples

Example 1: Ingredient-Based Search

User asks: "What can I make with chicken, garlic, and lemon?"

Load API reference
Use TheMealDB search or Spoonacular findByIngredients
Return 3-5 recipe suggestions with names and key details

Example 2: Dietary Restriction

User asks: "I need gluten-free dinner ideas"

Load API reference
Use Spoonacular with intolerances=gluten
Or use TheMealDB and filter results manually
Highlight that recipes are gluten-free in response

Example 3: Quick Recipe

User asks: "Give me an easy pasta recipe"

Search TheMealDB for "pasta"
Pick a result with simple ingredients
Provide full recipe with ingredients and instructions

Example 4: Nutrition Query

User asks: "How many calories in chicken alfredo?"

Search for chicken alfredo recipe
Use Spoonacular nutrition endpoint or estimate
Provide calorie and macro breakdown per serving

Example 5: Random Inspiration

User asks: "What should I cook tonight?"

Use TheMealDB random endpoint: /random.php
Present the recipe with ingredients and instructions
Offer to find alternatives if they don't like it

Notes

TheMealDB is completely free with no limits - prefer it for basic searches
Spoonacular free tier is 150 points/day (searches cost ~1 point each)
Always check dietary restrictions before recommending recipes
Cooking times are estimates - actual time varies by skill level
Ingredient quantities may need scaling based on servings
When nutrition data isn't available, note that it's an estimate

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Recipe Finder AI skill do?

Search recipes by ingredients, cuisine, or dietary needs. Get nutrition info, meal plans, and cooking instructions. Use when user asks about cooking, recipes, meals, or food.

Why use Recipe Finder on TypingMind?

Because you install it once and use it with any model. Recipe Finder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Recipe Finder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coleam00/custom-agent-with-skills/tree/main/skills/recipe_finder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Recipe Finder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Recipe Finder?

As many as you like. As long as a model supports skills, you can use Recipe Finder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Recipe Finder AI skill free?

It is published on GitHub by coleam00. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Brand Discovery

affaan-m

CommunityPopular

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Bun Runtime

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.

Competitive Report Structure

affaan-m

CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Recipe Finder Skill

When to Use

Available Operations

Instructions

Step 1: Understand the Query

Step 2: Load API Reference

Step 3: Choose the Right API

Step 4: Make the API Call

Step 5: Present Results

Dietary Restriction Mappings

Cuisine Types

Resources

Examples

Example 1: Ingredient-Based Search

Example 2: Dietary Restriction

Example 3: Quick Recipe

Example 4: Nutrition Query

Example 5: Random Inspiration

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now