Agent skill

Nutritional Specialist

by ailabs-393 in ailabs-393/ai-labs-claude-skills

This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning.

MITAuto-check passedProductivity & Automation

Install Nutritional Specialist

skills CLI
$ npx skills add ailabs-393/ai-labs-claude-skills --skill nutritional-specialist -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ailabs-393/ai-labs-claude-skills nutritional-specialist --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ailabs-393/ai-labs-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills/nutritional-specialist .claude/skills/nutritional-specialist && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nutritional-specialist
GitHub stars
455
Token cost
~2.8k tokens
SKILL.md length
698 words
Files
4 (incl. scripts)
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning.

  • Works in 4 steps: Check for Existing Preferences → Initial Setup (First Run Only) → Load and Use Preferences → …
  • Tasks that involve Health and fitness tracking
  • SKILL.md covers Overview, When to Use This Skill, Workflow and Best Practices, plus 3 more sections
  • Runs JavaScript and Python scripts from its folder; calls python3

What it does

Nutritional Specialist is an agent skill from ailabs-393/ai-labs-claude-skills. This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning. On first use, the skill collects comprehensive user preferences (allergies, dietary restrictions, goals, likes/dislikes) and stores them in a persistent database. All subsequent food-related responses are personalized based on these stored preferences.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `index.js`, `package.json` and `scripts/preferences_manager.py`).

It sits in Productivity & Automation, covering Health and fitness tracking. The repository describes itself as: This package is use to remove the hustle of finding claudeskills and shift them into any of the user project. This project become a bridge between user's usage and claude skills. The licence is MIT.

When your agent uses it

  • Tasks that involve Health and fitness tracking

Example prompts

  • “/nutritional-specialist”

Requirements

  • Python 3
  • Node.js

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Check for Existing Preferences
  2. Initial Setup (First Run Only)
  3. Load and Use Preferences
  4. Updating Preferences

What it can do on your machine

Read from SKILL.md and the folder at commit 1a12bc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nutritional Specialist loads about 2.8k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 698 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ailabs-393/ai-labs-claude-skills at commit 1a12bc7, republished under its MIT licence (© ailabs-393). 698 words, ~2,755 tokens.

Download SKILL.mdSave it as .claude/skills/nutritional-specialist/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
nutritional-specialist
description
This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning. On first use, the skill collects comprehensive user preferences (allergies, dietary restrictions, goals, likes/dislikes) and stores them in a persistent database. All subsequent food-related responses are personalized based on these stored preferences.

Nutritional Specialist

Overview

This skill transforms Claude into a personalized nutritional advisor by maintaining a persistent database of user food preferences, allergies, goals, and dietary restrictions. The skill ensures all food-related advice is tailored to the individual user's needs and constraints.

When to Use This Skill

Invoke this skill for any food-related query, including:

  • Meal planning and suggestions
  • Recipe recommendations
  • Nutritional advice and information
  • Dietary planning for specific goals (weight loss, muscle gain, etc.)
  • Food substitution ideas
  • Restaurant recommendations
  • Grocery shopping lists
  • Cooking tips and techniques

Workflow

Step 1: Check for Existing Preferences

Before providing any food-related advice, always check if user preferences exist:

bash
python3 scripts/preferences_manager.py has

If the output is "false", proceed to Step 2 (Initial Setup). If "true", proceed to Step 3 (Load Preferences).

Step 2: Initial Setup (First Run Only)

When no preferences exist, collect comprehensive information from the user using the AskUserQuestion tool or through conversational prompts. Gather the following information:

Essential Information:

  1. Dietary Goals: What are the primary nutritional or health goals? (e.g., weight loss, muscle gain, maintenance, better energy, disease management)
  2. Allergies: Any food allergies that must be strictly avoided?
  3. Dietary Restrictions: Any dietary restrictions or philosophies? (vegetarian, vegan, halal, kosher, low-carb, keto, paleo, etc.)
  4. Dislikes: Foods or ingredients strongly disliked
  5. Preferences: Favorite foods, cuisines, or ingredients

Optional Information: 6. Health Conditions: Any health conditions affecting diet? (diabetes, hypertension, IBS, celiac, etc.) 7. Cuisine Preferences: Preferred or avoided cuisines 8. Meal Timing: Eating schedule preferences (intermittent fasting, number of meals, etc.) 9. Cooking Skill Level: Beginner, intermediate, or advanced 10. Budget Considerations: Any budget constraints 11. Additional Notes: Any other relevant information

Collecting Preferences:

Use a conversational, friendly approach to gather this information. Frame the questions in an engaging way:

Example approach:

To provide you with the most helpful and personalized nutritional advice, let me learn about your food preferences and goals. This will help me tailor all my recommendations specifically to you.

Let's start with the essentials:
1. What are your main dietary or health goals?
2. Do you have any food allergies I should be aware of?
3. Do you follow any dietary restrictions or philosophies?
4. Are there any foods you really dislike?
5. What are some of your favorite foods or cuisines?

After collecting the information, save it using the preferences manager script:

python
import json
import subprocess

preferences = {
    "goals": ["list", "of", "goals"],
    "allergies": ["list", "of", "allergies"],
    "dietary_restrictions": ["vegetarian", "gluten-free"],
    "dislikes": ["list", "of", "dislikes"],
    "food_preferences": ["favorite", "foods"],
    "health_conditions": ["if", "any"],
    "cuisine_preferences": ["preferred", "cuisines"],
    "meal_timing": "description of meal timing preferences",
    "cooking_skill": "beginner/intermediate/advanced",
    "budget": "budget constraints if any",
    "notes": "any additional notes"
}

# Save using Python's subprocess
import subprocess
result = subprocess.run(
    ["python3", "scripts/preferences_manager.py", "set"],
    input=json.dumps(preferences),
    capture_output=True,
    text=True,
    cwd="[SKILL_DIR]"
)

Or by creating a temporary Python script that imports and uses the module:

python
import sys
sys.path.append('[SKILL_DIR]/scripts')
from preferences_manager import set_preferences

preferences = {
    # ... preference data as shown above
}

set_preferences(preferences)

Replace [SKILL_DIR] with the actual path to the skill directory.

After saving, confirm with the user:

Great! I've saved your preferences. From now on, all my food recommendations will be personalized based on your goals, dietary restrictions, and preferences. You can update these anytime by asking me to modify your nutritional preferences.
Step 3: Load and Use Preferences

For all food-related queries after initial setup, load the user's preferences:

bash
python3 scripts/preferences_manager.py get

Or display in a readable format:

bash
python3 scripts/preferences_manager.py display

Apply Preferences to Responses:

Every food-related response must:

  1. Respect allergies absolutely - Never suggest foods containing allergens
  2. Align with dietary restrictions - Only suggest appropriate foods
  3. Consider goals - Tailor advice to support the user's objectives
  4. Avoid dislikes - Don't recommend disliked foods unless explicitly requested
  5. Incorporate preferences - Favor liked foods and cuisines when possible
  6. Reference health conditions - Adjust recommendations accordingly

Example Application:

User query: "What should I have for lunch?"

Without preferences: Generic lunch suggestions

With preferences (e.g., vegan, nut allergy, weight loss goal, loves Mediterranean food):

Based on your preferences, here are some lunch ideas that align with your vegan diet, avoid nuts, support your weight loss goals, and incorporate your love for Mediterranean cuisine:

1. Chickpea and Quinoa Bowl with Tahini Dressing
   - High protein, satisfying, and nutrient-dense
   - Approx 400 calories

2. Mediterranean Lentil Soup with whole grain pita
   - Fiber-rich and filling
   - Approx 350 calories

3. Grilled Vegetable Wrap with hummus
   - Fresh, light, and packed with vegetables
   - Approx 320 calories

All options are completely plant-based, nut-free, and portion-controlled to support your weight loss journey!
Show full SKILL.md (255 more words)Show less
Step 4: Updating Preferences

When users want to update their preferences, use the same script:

bash
python3 scripts/preferences_manager.py get

Load the current preferences, ask what they'd like to change, and save the updated version.

For complete reset:

bash
python3 scripts/preferences_manager.py reset

Then proceed with the initial setup again.

Best Practices

  1. Always check preferences first - Make this the first step in any food-related query
  2. Be proactive about allergies - Double-check ingredient lists for hidden allergens
  3. Explain personalization - Occasionally remind users why specific recommendations were made
  4. Offer alternatives - Provide multiple options when possible
  5. Update incrementally - If users mention new preferences in conversation, offer to update their profile
  6. Cultural sensitivity - Respect religious and cultural dietary restrictions
  7. Evidence-based advice - Base nutritional guidance on scientific evidence
  8. Practical suggestions - Consider cooking skill level and time constraints

Example Interactions

Example 1: First-time user

User: "Can you suggest a healthy dinner recipe?"

Claude: [Checks preferences - finds none]

To provide you with the most helpful and personalized nutritional advice, let me learn about your food preferences and goals first. This will help me tailor all my recommendations specifically to you.

Let's start with the essentials:
1. What are your main dietary or health goals?
2. Do you have any food allergies I should be aware of?
3. Do you follow any dietary restrictions or philosophies?
4. Are there any foods you really dislike?
5. What are some of your favorite foods or cuisines?

[User provides answers, Claude saves preferences]

Great! I've saved your preferences. Now let me suggest some dinner recipes perfect for you...

Example 2: Returning user

User: "I need a quick breakfast idea"

Claude: [Loads preferences - finds: gluten-free, high-protein goal, loves eggs, dislikes bananas]

Here are some quick, high-protein, gluten-free breakfast ideas for you:

1. Veggie Egg Scramble (10 min)
   - 3 eggs with spinach, tomatoes, and feta
   - 25g protein, naturally gluten-free

2. Greek Yogurt Parfait (5 min)
   - Plain Greek yogurt with berries and gluten-free granola
   - 20g protein

3. Protein Smoothie Bowl (7 min)
   - Protein powder, berries, almond butter (no bananas!)
   - 30g protein

All options align with your high-protein goals and are completely gluten-free!

Example 3: Preference update

User: "I've decided to go pescatarian, can you update my profile?"

Claude: [Loads current preferences]

I'll update your dietary restrictions to include pescatarian. This means you'll eat fish and seafood but no other meat, correct?

[User confirms]

Perfect! I've updated your preferences. From now on, my meal suggestions will include fish and seafood options but exclude poultry, beef, and pork. Your other preferences remain the same.

Technical Notes

Preference Storage Location:

  • Preferences are stored at ~/.claude/nutritional_preferences.json
  • The file is automatically created on first use
  • Uses JSON format for easy reading and modification

Script Commands:

  • python3 scripts/preferences_manager.py has - Check if preferences exist (returns "true" or "false")
  • python3 scripts/preferences_manager.py get - Get all preferences as JSON
  • python3 scripts/preferences_manager.py display - Display preferences in readable format
  • python3 scripts/preferences_manager.py reset - Clear all preferences

Data Structure:

json
{
  "initialized": true,
  "goals": ["weight loss", "better energy"],
  "allergies": ["peanuts", "shellfish"],
  "dietary_restrictions": ["vegetarian", "gluten-free"],
  "dislikes": ["cilantro", "olives"],
  "food_preferences": ["Italian cuisine", "Mexican food", "pasta"],
  "health_conditions": ["type 2 diabetes"],
  "cuisine_preferences": ["Italian", "Mexican", "Thai"],
  "meal_timing": "intermittent fasting 16:8",
  "cooking_skill": "intermediate",
  "budget": "moderate",
  "notes": "Prefers quick weeknight meals"
}

Resources

scripts/preferences_manager.py

Python script that manages the persistent user preferences database. Provides functions to:

  • Check if preferences exist
  • Load existing preferences
  • Save new or updated preferences
  • Display preferences in readable format
  • Reset preferences

The script can be used both from the command line and imported as a Python module.

© ailabs-393, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in packages/skills/nutritional-specialist of ailabs-393/ai-labs-claude-skills.

  • SKILL.md
  • index.js
  • package.json
  • scripts/preferences_manager.py

Open the folder on GitHubat commit 1a12bc7

Compare with similar skills

Nutritional Specialist next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nutritional Specialist compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nutritional Specialist this skillailabs-393/ai-labs-claude-skills455—~2.8kAutomated safety check: PassMIT
Coachfelixrieseberg/claude-coach1991 repos~4.9kAutomated safety check: PassMIT
Fitness Analyzerhuifer/WellAlly-health9605 repos~1.3kAutomated safety check: PassMIT
Master Ajahn Chahxr843/Master-skill4471 repos~2kAutomated safety check: PassCC-BY-NC-SA-4.0
Mental Health Analyzerhuifer/WellAlly-health9605 repos~3.2kAutomated safety check: PassMIT
Nutrition Analyzerhuifer/WellAlly-health9605 repos~3.3kAutomated safety check: PassMIT

Similar skills

  • Coach

    felixrieseberg/claude-coach

    Create personalized triathlon, marathon, and ultra-endurance training plans.

    199 GitHub starsUsed in 1 repo~4.9k tokens
    Productivity & AutomationAuto-check passed
  • Fitness Analyzer

    huifer/WellAlly-health

    分析运动数据、识别运动模式、评估健身进展,并提供个性化训练建议。支持与慢性病数据的关联分析. An agent skill from huifer/WellAlly-health.

    960 GitHub starsUsed in 5 repos~1.3k tokens
    Productivity & AutomationAuto-check passed
  • Master Ajahn Chah

    xr843/Master-skill

    A skill your agent uses when user asks about 南传佛教, 上座部, Theravada, 巴利经典, 正念 sati, 放下, 三法印, 四念处, 出入息念 anapanasati, 戒定慧, 毗婆舍那, 森林禅林派, 巴蓬寺, 阿姜查, 杜多行, 中道, or wants teaching in 阿姜查 Ajahn Chah's voice.

    447 GitHub starsUsed in 1 repo~2k tokens
    Productivity & AutomationAuto-check passed
  • Mental Health Analyzer

    huifer/WellAlly-health

    分析心理健康数据、识别心理模式、评估心理健康状况、提供个性化心理健康建议。支持与睡眠、运动、营养等其他健康数据的关联分析。

    960 GitHub starsUsed in 5 repos~3.2k tokens
    Productivity & AutomationAuto-check passed
  • Nutrition Analyzer

    huifer/WellAlly-health

    分析营养数据、识别营养模式、评估营养状况,并提供个性化营养建议。支持与运动、睡眠、慢性病数据的关联分析. An agent skill from huifer/WellAlly-health.

    960 GitHub starsUsed in 5 repos~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Ghealth

    Google-Health-API/google-health-cli

    Query Google Health API v4 — steps, heart rate, exercise, sleep, weight, SpO2, HRV, ECG, blood glucose, nutrition, and 40 total data types

    266 GitHub stars~2.3k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed

More from ailabs-393/ai-labs-claude-skills

All 22 skills in this repo
  • SEO Optimizer

    ailabs-393/ai-labs-claude-skills

    This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices.

    455 GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • Tech Debt Analyzer

    ailabs-393/ai-labs-claude-skills

    This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability.

    455 GitHub starsUsed in 1 repo~3.9k tokens
    Auto-check passed
  • Business Document Generator

    ailabs-393/ai-labs-claude-skills

    This skill should be used when the user requests to create professional business documents (proposals, business plans, or budgets) from templates.

    455 GitHub stars~2k tokensUpdated 11 mo ago
    Auto-check passed
  • Startup Validator

    ailabs-393/ai-labs-claude-skills

    Comprehensive startup idea validation and market analysis tool.

    455 GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check passed
  • Docker Containerization

    ailabs-393/ai-labs-claude-skills

    This skill should be used when containerizing applications with Docker, creating Dockerfiles, docker-compose configurations, or deploying containers to various platforms.

    455 GitHub stars~2.1k tokensUpdated 11 mo ago
    Auto-check: notes
  • Storyboard Manager

    ailabs-393/ai-labs-claude-skills

    Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking.

    455 GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Questions about Nutritional Specialist

What does Nutritional Specialist do?

This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning. Nutritional Specialist is an agent skill from ailabs-393/ai-labs-claude-skills. This skill should be used whenever users ask food-related questions, meal suggestions, nutrition advice, recipe recommendations, or dietary planning.

When should I use Nutritional Specialist?

Nutritional Specialist fits situations like: tasks that involve Health and fitness tracking.

How do I install Nutritional Specialist in Claude Code?

Run `npx skills add ailabs-393/ai-labs-claude-skills --skill nutritional-specialist -a claude-code`. Or copy the skill folder (packages/skills/nutritional-specialist in ailabs-393/ai-labs-claude-skills) into .claude/skills/nutritional-specialist in your project. Claude Code loads it when a task matches its description.

How do I install Nutritional Specialist in Codex?

Run `npx skills add ailabs-393/ai-labs-claude-skills --skill nutritional-specialist -a codex`. Or copy the skill folder (packages/skills/nutritional-specialist in ailabs-393/ai-labs-claude-skills) into .agents/skills/nutritional-specialist in your project. Codex loads it when a task matches its description.

Can I use Nutritional Specialist in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ailabs-393/ai-labs-claude-skills --skill nutritional-specialist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nutritional-specialist, .gemini/skills/nutritional-specialist, .github/skills/nutritional-specialist and .opencode/skills/nutritional-specialist in your project.

What does Nutritional Specialist need to run?

Going by SKILL.md and its folder, Nutritional Specialist needs JavaScript and Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; Node.js.

Does Nutritional Specialist access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nutritional Specialist safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Nutritional Specialist use?

Nutritional Specialist is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nutritional Specialist use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nutritional Specialist?

Skills that share tags, products or a category with Nutritional Specialist: Coach (felixrieseberg/claude-coach, 199 stars), Fitness Analyzer (huifer/WellAlly-health, 960 stars), Master Ajahn Chah (xr843/Master-skill, 447 stars) and Mental Health Analyzer (huifer/WellAlly-health, 960 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nutritional Specialist?

ailabs-393 (a GitHub user) maintains it in ailabs-393/ai-labs-claude-skills, which has 455 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on November 11, 2025.

Source: ailabs-393/ai-labs-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.