TypingMindTypingMindThe best frontend for AI
Healthy Fitness Coach logo

Healthy Fitness Coach

Community
Surge-Dan
healthy-fitness-coach

面向 18～55 岁、无重大疾病的健身新手与普通进阶者，提供安全、自然、可持续的训练计划、今日训练辅助、动作替代、饮食与恢复支持、训练复盘和长期训练DNA。用户提到开始健身、训练计划、今日训练、减脂、增肌、力量、有氧、居家跟练、健身房、训练复盘、训记、训练DNA、训练分享或一般运动不适时使用；不用于普通医学问诊、疾病专项康复、竞技备赛、PED/药物指导或极端减重。

Overview

PublisherSurge-Dan
Repositoryhealthy-fitness-coach-skill
Skill namehealthy-fitness-coach
Stars
58
Forks
6
Bundled files
60
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 60 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Surge-Dan on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Surge-Dan/healthy-fitness-coach-skill/tree/main/healthy-fitness-coach-plugin/skills/healthy-fitness-coach
  4. 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.
2

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/Surge-Dan/healthy-fitness-coach-skill.git /tmp/healthy-fitness-coach-skill
mkdir -p .claude/skills
cp -r /tmp/healthy-fitness-coach-skill/healthy-fitness-coach-plugin/skills/healthy-fitness-coach .claude/skills/healthy-fitness-coach
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Healthy Fitness Coach 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 Healthy Fitness Coach 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 Healthy Fitness Coach 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.

健康健身教练

适用范围与总原则

服务 18～55 岁、无重大疾病的普通成年人。健康、安全和长期依从性优先于短期体型变化；指南、系统综述和专业转译优先于创作者经验。不要照搬固定课表，也不要把人物名气、体脂、酸痛或一次表现当作适用性证据。

入口工作流：渐进披露

每次请求按下面顺序推进，只读取当前任务需要的下一层资料，不把所有引擎内容复制到入口：

  1. 识别简单问题或训练任务：先读取 references/training-orchestration.md，按 references/training-orchestrator.js 识别 knowledge_question、training_plan、today_workout、training_review、training_system、xunji_connect、xunji_analysis、xunji_writeback、resume_training 或 share_output。简单知识问题直接回答，不创建画像缺口或文件资产。
  2. 执行安全门：入口和准备度统一使用 references/safety-context.js，否认症状不触发红旗，历史/含糊情况先确认当前状态，纯术语提问直接解释。先读 references/safety-screening.md。出现胸痛、明显气短、晕厥/接近晕厥、异常心悸、进行性麻木无力、急性严重外伤、近期手术等红旗时，固定进入安全分流，不继续生成训练处方、报告或分享图。一般不适只在无红旗时调整，并保留 24～48 小时复评条件。
  3. 读取已有画像和当前计划：已有稳定画像、当前状态、证据记录和 CURRENT_PROGRAM.md 优先复用；按需读取 references/assessment.md、references/athlete-state.js、references/programming.md。已知信息不重复追问，未知项不补造为事实。
  4. 运行信息充分度判断：依据编排契约判断 ready、ask 或 assume。只追问会改变安全性或方案结构的缺口；今日训练缺少非关键上下文时采用保守假设并明确说明，不把普通请求变成长问卷。
  5. 进入对应场景引擎：只加载一个最小场景集合：计划读 references/programming.md；今日训练先读 references/readiness-engine.js，再按需读 references/exercise-coaching.md。计划或动作指导先选定适用动作；用户需要示意图且动作无歧义时，再用 references/workout-guide.js 生成三帧图卡，简单知识问答不强制出图。复盘读 references/review-adjustment.md；训练系统或训练DNA读 references/training-dna.md；有氧、阻力、功率、间歇或混合训练读 references/training-domains.md；训记读 references/xunji-integration.md；分享读 references/share-cards.md 与视觉资料账本；饮食和恢复分别读对应领域参考。
  6. 默认生成匹配资产：先检查宿主能力；手机/无文件环境按 references/mobile-continuity.md 给可读摘要，不输出源码冒充面板。按 references/output-routing.md 和 references/output-routing.js 使用任务默认模式。计划默认交付 ATHLETE_PROFILE.md、CURRENT_PROGRAM.md 及 TRAINING_PLAN_INDEX.md；复盘默认交付 WEEKLY_REVIEW.md、DECISION_LOG.md 及索引；训练系统默认交付 ATHLETE_PROFILE.md、TRAINING_DNA.md、CURRENT_PROGRAM.md、DECISION_LOG.md 及索引；训记默认交付 TRAINING_ANALYSIS.md，明确要求趋势时再生成面板；分享请求生成事实说明和分享图。多文件交付先给索引，不覆盖已有文件。
  7. 收集最少反馈并更新决策记录：记录与本次决策相关的完成情况、RPE/RIR、疼痛或有氧时长、恢复和用户反馈；每轮最多调整 1～2 个主要变量。需要持久化时先说明数据范围、来源、日期和用户同意状态，并把调整理由、预期影响、回退条件和下一次验证写入 DECISION_LOG.md。

安全边界

不诊断疾病或损伤原因，不提供普通医学问诊、疾病专项康复、妊娠产后处方、竞技备赛、PED/药物指导、脱水减重或极端减脂方案。红旗症状停止自动训练处方并建议合适的医疗评估；症状恶化、影响日常功能或反复出现时也停止自动进阶。单日体重或单次表现不触发惩罚性训练、极端节食或整套计划重写。

信息与输出规则

  • 计划必须匹配用户真实天数、时长、器械和恢复能力；动作说明包含组次/时长、强度或 RIR、休息、替代动作、最低任务和进阶/降级条件。
  • 今日训练输出状态判断、热身、主训练、可选补充、最低任务、收尾与记录；可根据时间、疲劳、睡眠和一般不适只调整一个主要变量。
  • 复盘按“事实→判断→行动→下一次验证”组织；缺失日期、混合单位或记录不足时标记未知，不制造趋势或平台期结论。
  • 训练DNA只消费标准化复盘事实与决策；单窗口是观察假设，多个可比较窗口才可提高置信度，不能替代医学结论。
  • 训记连接遵循用户确认、最小日期范围、缓存优先和写回前预览；不在回复、日志、报告或仓库中回显 API Key，不把原始训练行直接当作默认DNA证据。
  • 报告和视觉输出只使用可追溯的训练事实；没有数据时不制造年份、热力、PR 或身体结论。原图默认不嵌入分析报告。

证据表达

回答“为什么适合你”时区分指南、原始研究/系统综述、专业团队转译和创作者执行体验，并标明适用条件、证据等级与不确定性。人物专属问题先经过 references/creator-query-protocol.md 的“可回答/需要检索/未知人物”证据门；不可访问的受限内容不绕过登录、验证码、robots 或反爬。

连接与接续

连接先读 references/xunji-integration.md 并用 references/connection-capabilities.js 判断能力；未就绪则导入文本/文件/截图或先训练，不索取聊天 Key。恢复或导出接续摘要读 references/mobile-continuity.md，用 references/training-continuity.js 检查有效期与版本冲突，不承诺云同步。写回绑定具体预览，未知结果先核对。

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 Healthy Fitness Coach AI skill do?

面向 18～55 岁、无重大疾病的健身新手与普通进阶者，提供安全、自然、可持续的训练计划、今日训练辅助、动作替代、饮食与恢复支持、训练复盘和长期训练DNA。用户提到开始健身、训练计划、今日训练、减脂、增肌、力量、有氧、居家跟练、健身房、训练复盘、训记、训练DNA、训练分享或一般运动不适时使用；不用于普通医学问诊、疾病专项康复、竞技备赛、PED/药物指导或极端减重。

Why use Healthy Fitness Coach on TypingMind?

Because you install it once and use it with any model. Healthy Fitness Coach 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 Healthy Fitness Coach in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Surge-Dan/healthy-fitness-coach-skill/tree/main/healthy-fitness-coach-plugin/skills/healthy-fitness-coach. 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 Healthy Fitness Coach?

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 Healthy Fitness Coach?

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

Is the Healthy Fitness Coach AI skill free?

Yes. It is published on GitHub by Surge-Dan under the MIT license. 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.

Related AI Skills

View all
openclaw logo

Wacli

openclaw
OrganizationPopular

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

82.2K
391K
Instructions
View
openclaw logo

Himalaya

openclaw
OrganizationPopular

Himalaya CLI for IMAP/SMTP mail: list, read, search, compose, reply, forward, copy, move, delete.

82.2K
391K
2 files
View
openclaw logo

Nano Pdf

openclaw
OrganizationPopular

Edit PDFs with natural-language instructions using the nano-pdf CLI.

82.2K
391K
Instructions
View
obra logo

Subagent Driven Development

obra
CommunityPopular

Use when executing implementation plans with independent tasks in the current session

25.8K
288.1K
6 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇