Agent skill

Fitness Analyzer

by huifer in 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.

MITAuto-check passedProductivity & Automation

Install Fitness Analyzer

skills CLI
$ npx skills add huifer/WellAlly-health --skill fitness-analyzer -a claude-code

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

GitHub CLI
$ gh skill install huifer/WellAlly-health fitness-analyzer --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/huifer/WellAlly-health.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fitness-analyzer .claude/skills/fitness-analyzer && 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
fitness-analyzer
GitHub stars
960
Used in
5 other repos
Token cost
~1.3k tokens
SKILL.md length
273 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 9 steps: 运动趋势分析 → 运动进步追踪 → 运动习惯分析 → …
  • Tasks that involve Health and fitness tracking
  • SKILL.md covers 功能, 输出格式, 数据源 and 算法说明, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fitness Analyzer is an agent skill from 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。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Health and fitness tracking. The repository describes itself as: Ally-Health is an intelligent healthcare assistant that harnesses advanced AI technology and medical expertise to transform personal health management. Through natural language…. The licence is MIT.

When your agent uses it

  • Tasks that involve Health and fitness tracking

Example prompts

  • “/fitness-analyzer”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Write

Workflow steps

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

  1. 运动趋势分析
  2. 运动进步追踪
  3. 运动习惯分析
  4. 相关性分析
  5. 个性化建议生成
  6. 线性回归趋势分析
  7. Pearson相关系数
  8. 配速计算
  9. MET能量代谢计算

What it can do on your machine

Read from SKILL.md and the folder at commit f604350. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).

    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

Fitness Analyzer loads about 1.3k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 273 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from huifer/WellAlly-health at commit f604350, republished under its MIT licence (© huifer). 273 words, ~1,315 tokens.

Download SKILL.mdSave it as .claude/skills/fitness-analyzer/SKILL.md (or your agent's skills folder).
name
fitness-analyzer
description
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。
allowed-tools
Read, Grep, Glob, Write

运动分析器技能

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。

功能

1. 运动趋势分析

分析运动量、频率、强度的变化趋势,识别改善或需要调整的方面。

分析维度:

  • 运动量趋势(时长、距离、卡路里)
  • 运动频率趋势(每周运动天数)
  • 强度分布变化(低/中/高强度占比)
  • 运动类型偏好变化

输出:

  • 趋势方向(改善/稳定/下降)
  • 变化幅度和百分比
  • 趋势显著性
  • 改进建议
2. 运动进步追踪

追踪特定运动类型的进步情况,量化健身效果。

支持的进步追踪:

  • 跑步进步:配速提升、距离增加、心率改善
  • 力量训练进步:重量增加、容量提升、RPE变化
  • 耐力进步:运动时长增加、距离延长
  • 柔韧性进步:关节活动度改善

输出:

  • 开始值 vs 当前值
  • 改善百分比
  • 进步可视化
  • 达成的里程碑
3. 运动习惯分析

识别用户的运动习惯和模式。

分析内容:

  • 常用运动时间(早晨/下午/晚上)
  • 运动频率模式(每周几天)
  • 运动类型偏好
  • 休息日分布
  • 运动一致性评分

输出:

  • 习惯总结
  • 一致性评分(0-100)
  • 优化建议
  • 习惯养成建议
4. 相关性分析

分析运动与其他健康指标的相关性。

支持的相关性分析:

  • 运动 ↔ 体重:运动消耗与体重变化的关系
  • 运动 ↔ 血压:运动对血压的长期影响
  • 运动 ↔ 血糖:运动对血糖控制的效果
  • 运动 ↔ 情绪/睡眠:运动对情绪和睡眠的影响

输出:

  • 相关系数(-1到1)
  • 相关性强度(弱/中/强)
  • 统计显著性
  • 因果关系推断
  • 实践建议
5. 个性化建议生成

基于用户数据生成个性化运动建议。

建议类型:

  • 运动频率建议:是否需要增加/减少运动频率
  • 运动强度建议:强度调整建议
  • 运动类型建议:推荐尝试的运动类型
  • 运动时间建议:最佳运动时间
  • 恢复建议:休息和恢复建议

建议依据:

  • WHO/ACSM/AHA运动指南
  • 用户运动历史数据
  • 用户健康状况
  • 用户健身目标

输出格式

趋势分析报告
markdown
# 运动趋势分析报告

## 分析周期
2025-03-20 至 2025-06-20(3个月)

## 运动量趋势

### 运动时长
- 趋势:⬆️ 上升
- 开始:平均120分钟/周
- 当前:平均180分钟/周
- 变化:+50%(+60分钟/周)
- 解读:运动量显著增加,表现优秀

### 卡路里消耗
- 趋势:⬆️ 上升
- 开始:平均960卡/周
- 当前:平均1440卡/周
- 变化:+50%
- 解读:运动消耗增加,有助于体重管理

### 运动距离
- 趋势:⬆️ 上升
- 开始:平均10公里/周
- 当前:平均20公里/周
- 变化:+100%
- 解读:耐力显著提升

## 运动频率

- 当前频率:4天/周
- 目标频率:4-5天/周
- 状态:✅ 达标
- 建议:保持当前频率

## 强度分布

| 强度 | 占比 | 变化 |
|------|------|------|
| 低强度 | 25% | +5% |
| 中等强度 | 55% | -10% |
| 高强度 | 20% | +5% |

**分析**:强度分布合理,中等强度占主导,符合有氧运动建议。

## 运动类型分布

| 运动类型 | 占比 |
|---------|------|
| 跑步 | 50% |
| 瑜伽 | 25% |
| 力量训练 | 25% |

**建议**:可以适当增加力量训练比例至30-40%。

## 洞察与建议

### 优势
1. ✅ 运动量稳定增长,(+50%)
2. ✅ 运动频率稳定,每周4天
3. ✅ 休息日充足,恢复良好

### 改进建议
1. 📈 每周增加2次力量训练
2. 📈 尝试不同运动类型避免单调
3. 📈 适当增加高强度间歇训练(HIIT)

### 警示
1. ⚠️ 注意运动强度不宜过高,控制在中等强度为主
相关性分析报告
markdown
# 运动与血压相关性分析

## 数据来源
- 运动数据:fitness-logs (2025-03-20 至 2025-06-20)
- 血压数据:hypertension-tracker (同期)

## 分析结果

### 相关系数
- 变量:每周运动时长 ↔ 收缩压
- 相关系数:r = -0.68
- 相关性强度:**强负相关**
- 统计显著性:p < 0.01 **高度显著**

### 解读
运动时长与收缩压呈强负相关,意味着:
- 运动越多,血压越低
- 每增加30分钟运动,收缩压平均下降3-5 mmHg

### 实践建议
1. ✅ 继续保持规律运动,每周5-7天
2. ✅ 每次运动30-60分钟,中等强度
3. ✅ 优先选择有氧运动(快走、慢跑、骑行)
4. ⚠️ 避免憋气动作和突然爆发性运动

### 医学参考
- AHA声明:规律有氧运动可降低收缩压5-7 mmHg
- 您的运动效果:降低约10 mmHg,效果显著!
进步追踪报告
markdown
# 跑步进步追踪

## 分析周期
2025-01-01 至 2025-06-20(6个月)

## 配速进步

| 指标 | 开始 | 当前 | 改善 |
|------|------|------|------|
| 平均配速 | 7:30 min/km | 6:00 min/km | +20% ⬆️ |
| 最快配速 | 7:00 min/km | 5:30 min/km | +22% ⬆️ |
| 5公里用时 | 37:30 | 30:00 | +20% ⬆️ |

**趋势**:配速持续稳定提升,进步显著!

## 距离进步

| 指标 | 开始 | 当前 | 改善 |
|------|------|------|------|
| 最长单次距离 | 3 km | 12 km | +300% ⬆️ |
| 月度总距离 | 40 km | 86 km | +115% ⬆️ |
| 平均距离 | 5 km | 6 km | +20% ⬆️ |

**趋势**:耐力大幅提升,可以完成更长距离。

## 心率改善

| 指标 | 开始 | 当前 | 改善 |
|------|------|------|------|
| 静息心率 | 78 bpm | 72 bpm | -6 bpm ⬇️ |
| 相同配速心率 | 155 bpm | 145 bpm | -10 bpm ⬇️ |

**分析**:心肺功能显著改善,相同配速下心率降低。

## 里程碑

- ✅ 2025-03-15:首次完成5公里跑
- ✅ 2025-05-20:首次完成10公里跑
- ✅ 2025-06-10:配速突破6:00 min/km

## 下一步目标

- 🎯 完成半程马拉松(21公里)
- 🎯 配速提升至5:30 min/km
- 🎯 尝试间歇训练提升速度

数据源

主要数据源
  1. 运动日志

    • 路径:data/fitness-logs/YYYY-MM/YYYY-MM-DD.json
    • 内容:运动记录(类型、时长、强度、心率、距离等)
    • 频率:每次运动后更新
  2. 用户档案

    • 路径:data/fitness-tracker.json
    • 内容:用户档案、健身目标、统计数据
    • 更新:定期更新
  3. 健康数据关联

    • data/hypertension-tracker.json(血压数据)
    • data/diabetes-tracker.json(血糖数据)
    • data/profile.json(体重、BMI等)
数据质量检查
  • 数据完整性:检查必要字段是否存在
  • 数据合理性:检查数值是否在合理范围内
  • 时间一致性:检查时间戳是否合理
  • 重复数据:检测并处理重复记录

算法说明

1. 线性回归趋势分析

使用线性回归分析运动数据的时间趋势。

公式: y = a + bx

其中:

  • y:运动指标(时长、卡路里、距离等)
  • x:时间
  • a:截距
  • b:斜率(趋势方向和速度)

解释:

  • b > 0:上升趋势
  • b < 0:下降趋势
  • b ≈ 0:稳定
2. Pearson相关系数

用于分析两个变量之间的线性相关性。

公式: r = Σ[(xi - x̄)(yi - ȳ)] / √[Σ(xi - x̄)² × Σ(yi - ȳ)²]

范围:-1 ≤ r ≤ 1

解释:

  • r = 1:完全正相关
  • r = -1:完全负相关
  • r = 0:无线性相关

强度判断:

  • |r| < 0.3:弱相关
  • 0.3 ≤ |r| < 0.7:中等相关
  • |r| ≥ 0.7:强相关
3. 配速计算

配速 = 运动时长 / 距离

单位:min/km 或 min/mile

示例:

  • 30分钟跑5公里
  • 配速 = 30 / 5 = 6 min/km
4. MET能量代谢计算

卡路里消耗 = MET × 体重(kg) × 时间(小时)

常见运动的MET值:

  • 走路(3-5 km/h):3.5-5 MET
  • 慢跑(8 km/h):8 MET
  • 快跑(10 km/h):10 MET
  • 游泳:6-10 MET
  • 骑行(休闲):4 MET
  • 力量训练:5 MET
  • 瑜伽:3 MET

医学安全边界

⚠️ 重要声明 本分析仅供健康参考,不构成医疗建议。

分析能力范围

✅ 能做到:

  • 运动数据统计和分析
  • 趋势识别和可视化
  • 相关性计算和解释
  • 一般性运动建议

❌ 不做到:

  • 疾病诊断
  • 运动风险评估
  • 具体运动处方设计
  • 运动损伤诊断和治疗
危险信号检测

在分析过程中检测以下危险信号:

  1. 心率异常

    • 运动心率 > 95%最大心率
    • 静息心率 > 100 bpm
  2. 血压异常

    • 收缩压 ≥ 180 mmHg
    • 舒张压 ≥ 110 mmHg
  3. 过度训练迹象

    • 连续7天高强度运动
    • 运动感受持续下降(RPE > 17)
  4. 体重快速下降

    • 每周减重 > 1kg(可能不健康)
建议分级

Level 1: 一般性建议

  • 基于WHO/ACSM指南
  • 适用于一般人群

Level 2: 参考性建议

  • 基于用户数据
  • 需结合个人情况

Level 3: 医疗建议

  • 涉及疾病管理
  • 需医生确认

使用示例

示例1:生成运动趋势报告
bash
/fitness trend 3months

输出:

  • 3个月运动趋势分析
  • 运动量、频率、强度变化
  • 洞察和建议
示例2:追踪跑步进步
bash
/fitness analysis progress running

输出:

  • 配速进步
  • 距离进步
  • 心率改善
  • 里程碑达成
示例3:分析运动与血压相关性
bash
/fitness analysis correlation blood_pressure

输出:

  • 相关系数
  • 相关性强度
  • 显著性检验
  • 实践建议

技能版本: v1.0 最后更新: 2026-01-02 维护者: WellAlly Tech

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

Files

Just SKILL.md in skills/fitness-analyzer of huifer/WellAlly-health.

Open the folder on GitHubat commit f604350

Used in 5 other repositories

We found 15 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 5 other GitHub owners. This page covers the copy in huifer/WellAlly-health, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Fitness Analyzer 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.

Fitness Analyzer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fitness Analyzer this skillhuifer/WellAlly-health9605 repos~1.3kAutomated safety check: PassMIT
Coachfelixrieseberg/claude-coach1991 repos~4.9kAutomated safety check: PassMIT
Master Ajahn Chahxr843/Master-skill4471 repos~2kAutomated safety check: PassCC-BY-NC-SA-4.0
GhealthGoogle-Health-API/google-health-cli266—~2.3kAutomated safety check: PassApache-2.0
Crisis Detection Intervention AIcuriositech/some_claude_skills2442 repos~3.8kAutomated safety check: PassMIT
Section 11CrankAddict/section-11156—~5.2kAutomated 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
  • 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
  • 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
  • Crisis Detection Intervention AI

    curiositech/some_claude_skills

    Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.

    244 GitHub starsUsed in 2 repos~3.8k tokens
    Productivity & AutomationAuto-check passed
  • Section 11

    CrankAddict/section-11

    Evidence-based endurance coaching protocol (v11.70). An agent skill from CrankAddict/section-11.

    156 GitHub stars~5.2k tokensUpdated 6 days ago
    Productivity & AutomationAuto-check passed
  • Vipassana LLM

    infranodus/skills

    Apply Vipassana meditation principles to LLM processing — equanimous scanning, non-reactive observation, impermanence awareness (anicca), and breaking the sankhara chain of conditioned reactions.

    119 GitHub stars~3.3k tokensUpdated 20 days ago
    Productivity & AutomationAuto-check passed

More from huifer/WellAlly-health

All 15 skills in this repo
  • Emergency Card

    huifer/WellAlly-health

    生成紧急情况下快速访问的医疗信息摘要卡片。当用户需要旅行、就诊准备、紧急情况或询问"紧急信息"、"医疗卡片"、"急救信息"时使用此技能。提取关键信息(过敏、用药、急症、植入物),支持多格式输出(JSON、文本、二维码),用于急救或快速就医。

    960 GitHub starsUsed in 6 repos~2.7k tokens
    Auto-check passed
  • Health Trend Analyzer

    huifer/WellAlly-health

    分析一段时间内健康数据的趋势和模式。关联药物、症状、生命体征、化验结果和其他健康指标的变化。识别令人担忧的趋势、改善情况,并提供数据驱动的洞察。当用户询问健康趋势、模式、随时间的变化或"我的健康状况有什么变化?"时使用。支持多维度分析(体重/BMI、症状、药物依从性、化验结果、情绪睡眠),相关性分析,变化检测,以及交互式HTML可视化报告(ECharts图表)。

    960 GitHub starsUsed in 6 repos~1.8k tokens
    Auto-check passed
  • AI Analyzer

    huifer/WellAlly-health

    AI驱动的综合健康分析系统,整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。

    960 GitHub starsUsed in 5 repos~1k tokens
    Auto-check passed
  • Goal Analyzer

    huifer/WellAlly-health

    分析健康目标数据、识别目标模式、评估目标进度,并提供个性化目标管理建议。支持与营养、运动、睡眠等健康数据的关联分析. An agent skill from huifer/WellAlly-health.

    960 GitHub starsUsed in 5 repos~2k tokens
    Auto-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
    Auto-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
    Auto-check passed

Questions about Fitness Analyzer

What does Fitness Analyzer do?

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. Fitness Analyzer is an agent skill from huifer/WellAlly-health.

When should I use Fitness Analyzer?

Fitness Analyzer fits situations like: tasks that involve Health and fitness tracking.

How do I install Fitness Analyzer in Claude Code?

Run `npx skills add huifer/WellAlly-health --skill fitness-analyzer -a claude-code`. Or copy the skill folder (skills/fitness-analyzer in huifer/WellAlly-health) into .claude/skills/fitness-analyzer in your project. Claude Code loads it when a task matches its description.

How do I install Fitness Analyzer in Codex?

Run `npx skills add huifer/WellAlly-health --skill fitness-analyzer -a codex`. Or copy the skill folder (skills/fitness-analyzer in huifer/WellAlly-health) into .agents/skills/fitness-analyzer in your project. Codex loads it when a task matches its description.

Can I use Fitness Analyzer 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 huifer/WellAlly-health --skill fitness-analyzer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fitness-analyzer, .gemini/skills/fitness-analyzer, .github/skills/fitness-analyzer and .opencode/skills/fitness-analyzer in your project.

What does Fitness Analyzer need to run?

SKILL.md names no scripts, command-line tools or credentials: Fitness Analyzer is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Write.

Does Fitness Analyzer 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 Fitness Analyzer 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. Review the folder before installing.

What licence does Fitness Analyzer use?

Fitness Analyzer 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 Fitness Analyzer use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Fitness Analyzer?

Skills that share tags, products or a category with Fitness Analyzer: Coach (felixrieseberg/claude-coach, 199 stars), Master Ajahn Chah (xr843/Master-skill, 447 stars), Ghealth (Google-Health-API/google-health-cli, 266 stars) and Crisis Detection Intervention AI (curiositech/some_claude_skills, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fitness Analyzer?

huifer (a GitHub user) maintains it in huifer/WellAlly-health, which has 960 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on July 16, 2026.

Source: huifer/WellAlly-health on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.