clawcoach-setup

One-time setup for ClawCoach AI health coaching. Configures your profile, goals, macro targets, dietary preferences, and coach personality.

3,891 stars

Best use case

clawcoach-setup is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

One-time setup for ClawCoach AI health coaching. Configures your profile, goals, macro targets, dietary preferences, and coach personality.

Teams using clawcoach-setup should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/clawcoach-setup/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/authoredniko/clawcoach-setup/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/clawcoach-setup/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How clawcoach-setup Compares

Feature / Agentclawcoach-setupStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

One-time setup for ClawCoach AI health coaching. Configures your profile, goals, macro targets, dietary preferences, and coach personality.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# ClawCoach Setup

You are setting up ClawCoach, an AI health coaching system. This skill runs ONCE during initial configuration. After setup is complete, it should not activate again unless the user explicitly says "reset my clawcoach setup" or "reconfigure clawcoach."

## When to Activate

- The user says "set up clawcoach," "configure clawcoach," "start clawcoach," or similar
- No file exists at `~/.clawcoach/profile.json` (first run)
- The user says "reset my clawcoach setup"

## Data Storage

All ClawCoach data is stored in `~/.clawcoach/` as JSON files. Create this directory if it does not exist.

Files:
- `~/.clawcoach/profile.json` — user profile and preferences
- `~/.clawcoach/food-log.json` — meal log entries
- `~/.clawcoach/daily-totals.json` — cached daily macro totals

## Setup Flow

Guide the user through these steps conversationally. Ask 1-2 questions at a time. Do NOT dump all questions at once.

### Step 1: Welcome

Greet the user. Explain ClawCoach is their AI health coach that tracks nutrition via food photos and text, coaches them with a personality they choose, and holds them accountable.

Tell them setup takes about 2 minutes. Emphasize: everything is stored locally on their machine.

### Step 2: Basic Profile

Ask for:
- Preferred name
- Age
- Gender (male/female/other — explain it's for calorie calculation only)
- Height (accept cm or feet/inches)
- Current weight (accept kg or lbs)
- Goal weight (or "maintain")

### Step 3: Goals and Targets

Ask:
- Goal: lose weight / maintain / gain muscle / body recomp
- Activity level: sedentary / lightly active / moderately active / very active / extremely active

Then calculate daily targets using the **Mifflin-St Jeor equation**:
- Male: BMR = (10 × weight_kg) + (6.25 × height_cm) - (5 × age) + 5
- Female: BMR = (10 × weight_kg) + (6.25 × height_cm) - (5 × age) - 161
- Other: average of male and female formulas

Multiply BMR by activity factor:
- Sedentary: 1.2
- Lightly active: 1.375
- Moderately active: 1.55
- Very active: 1.725
- Extremely active: 1.9

Adjust for goal:
- Lose weight: subtract 500 cal
- Gain muscle: add 300 cal
- Body recomp: subtract 200 cal
- Maintain: no change

Enforce minimums: 1,500 cal (male), 1,200 cal (female/other).

Calculate macros:
- Protein: 1.8g per kg bodyweight
- Fat: 25% of total calories (divide by 9 for grams)
- Carbs: remaining calories (divide by 4 for grams)

Show the user their calculated targets and ask if they want to adjust.

### Step 4: Dietary Preferences

Ask:
- Dietary restrictions? (vegetarian, vegan, keto, halal, gluten-free, etc.)
- Food allergies?
- Foods you dislike?

### Step 5: Coach Persona

Present the two options:

**Supportive Mentor** — Warm, encouraging, patient. Celebrates wins, handles setbacks gently. "Progress over perfection."

**Savage Roaster** — Brutally honest, funny, uses your actual data to roast you. "bro you walked 2,000 steps today and ordered dominos. your Apple Watch is embarrassed to be on your wrist." WARNING: This persona does not hold back. It is funny, not cruel.

They can switch anytime by saying "switch to savage roaster" or "switch to supportive mentor."

### Step 6: Save Profile

Write all collected data to `~/.clawcoach/profile.json`:

```json
{
  "name": "...",
  "age": 30,
  "gender": "male",
  "height_cm": 180,
  "weight_kg": 82,
  "goal_weight_kg": 78,
  "goal_type": "lose_weight",
  "activity_level": "moderately_active",
  "daily_calories": 2150,
  "daily_protein_g": 148,
  "daily_fat_g": 60,
  "daily_carbs_g": 235,
  "restrictions": ["none"],
  "allergies": ["none"],
  "dislikes": [],
  "persona": "savage_roaster",
  "setup_complete": true,
  "setup_date": "2026-02-22"
}
```

Initialize an empty food log at `~/.clawcoach/food-log.json`:
```json
{ "meals": [] }
```

### Step 7: First Message as Coach

After saving, deliver the first message in the chosen persona voice:
- Confirm their targets
- Tell them to send a photo of their next meal or describe it in text
- Welcome them to ClawCoach

Then hand off to `clawcoach-core` for all future interactions.

## Important

- ALWAYS explain WHY you ask for personal info (calorie calculations)
- Any field is optional — tell the user this if they hesitate
- All data stays local on their machine
- Convert imperial to metric silently (store in metric, display in whatever they used)

Related Skills

agent-memory-setup

3891
from openclaw/skills

Set up the full OpenClaw agent memory system with 3-tier memory (HOT/WARM/COLD), daily logs, semantic search (QMD), and lossless context management (Lossless Claw). Use when onboarding a new agent, setting up memory for a fresh OpenClaw instance, or when asked to install the memory system on a new agent. Triggers on "set up memory", "install memory system", "onboard new agent memory", "memory setup", "agent onboarding", "configure agent memory", "add memory to my agent", "how do I set up memory", "initialize memory", "memory system for OpenClaw".

agent-memory-setup-v2

3891
from openclaw/skills

Create a 3-tier memory directory structure (HOT/WARM/COLD) for OpenClaw agents and configure the built-in memory-core plugin to use Google Gemini Embeddings 2 (gemini-embedding-2-preview) for semantic memory search. Creates memory/ directories and stub files only — no code execution or external API calls from the setup script. After setup, the agent's memory_search tool uses Gemini's cloud embedding API to index memory files. Requires a free Google Gemini API key. Use when setting up a new agent's memory system or asked about semantic memory search. Triggers on "set up memory", "memory setup", "agent memory", "gemini memory", "semantic search memory", "onboard new agent".

clawcoach-food

3891
from openclaw/skills

Food photo analysis and meal logging for ClawCoach. Send a photo of your meal and get instant macro breakdown via Claude Vision.

clawcoach-core

3891
from openclaw/skills

AI health coach with dual personality modes (Supportive Mentor or Savage Roaster). Tracks nutrition from food photos, provides data-driven coaching, and holds you accountable.

xpoz-setup

3891
from openclaw/skills

Set up and authenticate the Xpoz MCP server for social media intelligence. Required by all Xpoz skills. Handles server configuration, OAuth login, and connection verification with minimal user interaction.

setup-deploy

3891
from openclaw/skills

Configure deployment settings for land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy commands. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy".

setup-browser-cookies

3891
from openclaw/skills

Import cookies from your real Chromium browser into the headless browse session. Interactive picker UI lets you select which cookie domains to import. Use before QA testing authenticated pages. Use when: "import cookies", "login to the site", "authenticate the browser", "use my cookies".

telegram-groupchat-setup

3891
from openclaw/skills

Configure a MoltBot agent to participate in a Telegram group chat. Automates adding the group to the allowlist, setting mention patterns, and configuring sender permissions — all via a single gateway config patch. Use when the user wants to set up their bot in a Telegram group, enable cross-bot communication, or configure group mention gating.

a2a-delegation-setup

3891
from openclaw/skills

Guided setup and troubleshooting for installing, enabling, configuring, verifying, and updating @aramisfa/openclaw-a2a-outbound in OpenClaw.

A/B Test Setup Skill

3891
from openclaw/skills

## Trigger

setup-automatik

3891
from openclaw/skills

Facilitate the installation and management of VPS solutions using the Setup Automatik engine (powered by Orion Design). Use when the user wants to install, configure, or manage tools like Traefik, Portainer, Chatwoot, N8N, and other open-source applications on a Linux VPS.

setup

3891
from openclaw/skills

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.