fit

Your personal fitness operating system. Not a workout plan. A complete system that figures out what your body actually needs, builds training around your real life, tracks what is working, and adapts when life gets in the way. Trigger for any fitness goal: losing fat, building muscle, running faster, getting stronger, recovering from injury, or simply moving better than you did last year.

3,891 stars

Best use case

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

Your personal fitness operating system. Not a workout plan. A complete system that figures out what your body actually needs, builds training around your real life, tracks what is working, and adapts when life gets in the way. Trigger for any fitness goal: losing fat, building muscle, running faster, getting stronger, recovering from injury, or simply moving better than you did last year.

Teams using fit 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/fit/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/agimodel/fit/skill.md"

Manual Installation

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

How fit Compares

Feature / AgentfitStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Your personal fitness operating system. Not a workout plan. A complete system that figures out what your body actually needs, builds training around your real life, tracks what is working, and adapts when life gets in the way. Trigger for any fitness goal: losing fat, building muscle, running faster, getting stronger, recovering from injury, or simply moving better than you did last year.

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

# Fit

## What Most Fitness Advice Gets Wrong

Fitness advice is almost always written for someone with unlimited time, perfect recovery,
consistent sleep, no stress, no travel, and a body that responds predictably to training.

That person does not exist.

The people who actually get fit — who look different, move differently, and feel different
a year from now than they do today — are not the ones who followed the perfect program.
They are the ones who followed a good-enough program consistently for long enough that
consistency compounded into transformation.

This skill is built for real people with real constraints.

---

## The System
```
FITNESS_OS = {
  "assessment": {
    "current_state": ["Current weight and body composition if known",
                      "Current training frequency and type",
                      "Movement limitations or injuries",
                      "Energy levels across the day",
                      "Sleep quality and quantity"],
    "goal_clarity":  {
      "aesthetic":     "Body composition change — fat loss, muscle gain, or both",
      "performance":   "Specific metric — run 5K, deadlift bodyweight, 10 pullups",
      "health":        "Blood markers, blood pressure, longevity, pain reduction",
      "functional":    "Move better, carry more, hurt less"
    },
    "constraint_map": ["Days per week available for training",
                       "Minutes per session realistic",
                       "Equipment available",
                       "Injuries or restrictions",
                       "Travel frequency"]
  }
}
```

---

## Training Architecture
```
PROGRAM_DESIGN = {
  "minimum_effective_dose": {
    "principle": "The smallest training stimulus that produces the desired adaptation.
                  More is not better. Enough is better.",
    "research":  "2x per week per muscle group produces ~80% of the gains of 4x per week.
                  3x per week per muscle group captures nearly all available adaptation.",
    "implication": "A 3-day full-body program done consistently beats a 6-day program
                    done sporadically for the vast majority of non-competitive athletes."
  },

  "progressive_overload": {
    "definition": "Systematically increasing training stimulus over time to force adaptation",
    "methods":    ["Add weight to the bar",
                   "Add reps at same weight",
                   "Add sets",
                   "Reduce rest period",
                   "Improve movement quality"],
    "tracking":   """
      def log_workout(exercise, sets, reps, weight):
          session = {
              "date": today,
              "exercise": exercise,
              "volume": sets * reps * weight,
              "top_set": max_weight_lifted
          }
          compare_to_last_session(session)
          if no_progress_in_3_weeks:
              flag_for_program_adjustment()
    """
  },

  "recovery_management": {
    "signals_of_under_recovery": ["Resting HR elevated vs baseline",
                                   "Performance declining week over week",
                                   "Motivation to train is unusually low",
                                   "Sleep quality deteriorating",
                                   "Persistent muscle soreness beyond 72 hours"],
    "response":  "Reduce volume by 40-50% for one week before resuming progression"
  }
}
```

---

## Nutrition for Fitness Goals
```
NUTRITION_FRAMEWORK = {
  "fat_loss": {
    "principle":  "Caloric deficit is required. Protein is non-negotiable.",
    "target":     "0.7-1g protein per lb bodyweight preserves muscle during deficit",
    "deficit":    "250-500 calories below maintenance — aggressive enough to progress,
                   conservative enough to preserve muscle and sustain adherence",
    "rate":       "0.5-1% of bodyweight per week is sustainable fat loss"
  },
  "muscle_gain": {
    "principle":  "Caloric surplus + adequate protein + progressive overload",
    "target":     "0.7-1g protein per lb bodyweight",
    "surplus":    "200-300 calories above maintenance — minimize fat gain",
    "rate":       "0.25-0.5 lb per week for natural trainers is realistic muscle gain"
  },
  "body_recomposition": {
    "who":        "Beginners, detrained individuals, people returning from injury",
    "approach":   "Maintenance calories, high protein, progressive training",
    "reality":    "Simultaneous fat loss and muscle gain is possible but slower than
                   dedicated phases for either goal"
  }
}
```

---

## When Life Disrupts the Plan
```
DISRUPTION_PROTOCOLS = {
  "travel": {
    "hotel_gym":     "Minimum: 30 min, compound movements, maintain frequency",
    "no_gym":        "Bodyweight protocol — push, pull, hinge, squat, carry variations",
    "principle":     "Maintenance beats nothing. One session per week prevents detraining."
  },
  "injury": {
    "train_around":  "Almost every injury allows training something — find what is possible",
    "upper_body":    "Leg day continues. Lower body injury is not a rest day.",
    "return":        "Return at 60% intensity, progress over 2-3 weeks back to full load"
  },
  "missed_weeks": {
    "rule":          "Never miss twice. One disruption is life. Two is a pattern.",
    "return":        "Reduce weight by 20-30%, rebuild over 1-2 weeks — prevents injury"
  }
}
```

---

## Progress Tracking
```
METRICS_THAT_MATTER = {
  "performance":    "Weight lifted, reps completed, pace, distance — objective and motivating",
  "body":           "Weekly average weight, monthly measurements, photos every 4 weeks",
  "habits":         "Training sessions completed vs planned — consistency is the metric",
  "energy":         "Subjective energy and mood — leading indicator of program sustainability",
  "avoid":          "Daily scale weight as primary metric — noise overwhelms signal"
}
```

---

## Quality Check

- [ ] Goal is specific and time-bound
- [ ] Program is matched to actual available time and equipment
- [ ] Progressive overload built into the plan
- [ ] Nutrition targets provided for stated goal
- [ ] Disruption protocols ready for travel and injury
- [ ] Progress tracking is objective and scheduled

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation