rehabilitation-analyzer-v2

Rehabilitation Training Analysis Skill

Overview

This public intake copy packages plugins/antigravity-awesome-skills/skills/rehabilitation-analyzer from https://github.com/sickn33/antigravity-awesome-skills into the native Omni Skills editorial shape without hiding its origin.

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses the external_source block in metadata.json plus ORIGIN.md as the provenance anchor for review.

Rehabilitation Training Analysis Skill

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Core Functions, Trigger Conditions, Execution Steps, Output Format, 1. Rehabilitation Progress Summary, 2. Functional Improvement Trends.

When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

Use when it is necessary to analyze rehabilitation training records, functional recovery trends, or rehabilitation phase progress.
The task involves analysis of ROM, muscle strength, pain, adherence, or rehabilitation goal achievement rate.
Use when the user requests rehabilitation reports, trend analysis, or training plan optimization recommendations.
Use when the request clearly matches the imported source intent: analyze rehabilitation training data, identify rehabilitation patterns, assess rehabilitation progress, and provide personalized rehabilitation recommendations.
Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.
Use when provenance needs to stay visible in the answer, PR, or review packet.

Operating Table

Situation	Start here	Why it matters
First-time use	`metadata.json`	Confirms repository, branch, commit, and imported path through the `external_source` block before touching the copied workflow
Provenance review	`ORIGIN.md`	Gives reviewers a plain-language audit trail for the imported source
Workflow execution	`SKILL.md`	Starts with the smallest copied file that materially changes execution
Supporting context	`SKILL.md`	Adds the next most relevant copied source file without loading the entire package
Handoff decision	`## Related Skills`	Helps the operator switch to a stronger native skill when the task drifts

Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

Confirm the user goal, the scope of the imported workflow, and whether this skill is still the right router for the task.
Read the overview and provenance files before loading any copied upstream support files.
Load only the references, examples, prompts, or scripts that materially change the outcome for the current request.
Execute the upstream workflow while keeping provenance and source boundaries explicit in the working notes.
Validate the result against the upstream expectations and the evidence you can point to in the copied files.
Escalate or hand off to a related skill when the work moves out of this imported workflow's center of gravity.
Before merge or closure, record what was used, what changed, and what the reviewer still needs to verify.

Imported Workflow Notes

Imported: Core Functions

The Rehabilitation Training Analysis Skill provides comprehensive rehabilitation data analysis capabilities to help users track rehabilitation progress, identify improvement patterns, and optimize training plans.

Main functional modules:

Rehabilitation Progress Analysis - Assess functional improvement trends and rehabilitation outcomes
Functional Improvement Curves - Visualize changes in functional indicators such as ROM, muscle strength, and balance
Pain Pattern Recognition - Analyze pain score change trends and triggering factors
Goal Achievement Rate Assessment - Track the completion status of rehabilitation goals
Rehabilitation Phase Analysis - Assess progress in the current phase and readiness for phase transition
Training Adherence Assessment - Analyze the execution status of training plans

Examples

Example 1: Ask for the upstream workflow directly

Use @rehabilitation-analyzer-v2 to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.

Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

Example 2: Ask for a provenance-grounded review

Review @rehabilitation-analyzer-v2 against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.

Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

Example 3: Narrow the copied support files before execution

Use @rehabilitation-analyzer-v2 for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.

Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

Example 4: Build a reviewer packet

Review @rehabilitation-analyzer-v2 using the copied upstream files plus provenance, then summarize any gaps before merge.

Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.

Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
Treat generated examples as scaffolding; adapt them to the concrete task before execution.
Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Symptoms: The result ignores the upstream workflow in plugins/antigravity-awesome-skills/skills/rehabilitation-analyzer, fails to mention provenance, or does not use any copied source files at all. Solution: Re-open metadata.json, ORIGIN.md, and the most relevant copied upstream files. Check the external_source block first, then restate the provenance before continuing.

Problem: The imported workflow feels incomplete during review

Symptoms: Reviewers can see the generated SKILL.md, but they cannot quickly tell which references, examples, or scripts matter for the current task. Solution: Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.

Problem: The task drifted into a different specialization

Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

Related Skills

@production-audit-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
@production-scheduling-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
@quality-nonconformance-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
@react-best-practices-v3 - Use when the work is better handled by that native specialization after this imported skill establishes context.

Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

Resource family	What it gives the reviewer	Example path
`references`	copied reference notes, guides, or background material from upstream	`references/n/a`
`examples`	worked examples or reusable prompts copied from upstream	`examples/n/a`
`scripts`	upstream helper scripts that change execution or validation	`scripts/n/a`
`agents`	routing or delegation notes that are genuinely part of the imported package	`agents/n/a`
`assets`	supporting assets or schemas copied from the source package	`assets/n/a`

Imported Reference Notes

Imported: Trigger Conditions

The skill is automatically triggered under the following conditions:

The user uses /rehab progress to view rehabilitation progress
The user uses /rehab analysis to conduct rehabilitation analysis
The user uses /rehab trends to view trend analysis
The user uses /rehab report to generate a rehabilitation report

Imported: Execution Steps

Step 1: Data Reading

Read rehabilitation data files:

data/rehabilitation-tracker.json - Main rehabilitation profile
data/rehabilitation-logs/YYYY-MM/YYYY-MM-DD.json - Daily training log

Data validation:

Check whether the files exist
Verify the integrity of the data structure
Confirm that there are enough data points for analysis (at least 3 assessments or 10 days of training records are recommended)

Step 2: Functional Assessment Trend Analysis

Range of Motion (ROM) analysis:

- 分析不同时间点的ROM测量值
- 计算ROM改善速率（度/周）
- 识别ROM平台期或倒退
- 预测达到目标ROM的时间
- 与目标范围对比

Muscle strength improvement analysis:

- 追踪肌力等级变化（MMT评分）
- 识别肌力提升模式
- 比较不同肌群恢复速度
- 评估肌力不平衡情况

Balance function analysis:

- 平衡测试分数趋势
- 单腿站立时间改善
- 平衡稳定性评估
- 跌倒风险变化

Step 3: Pain Pattern Analysis

Pain temporal analysis:

- 分析晨起疼痛趋势
- 分析活动后疼痛趋势
- 识别疼痛加重/缓解模式
- 关联疼痛与训练强度

Pain trigger factor identification:

- 特定训练项目与疼痛关系
- 训练强度与疼痛相关性
- 活动类型与疼痛关系
- 时间因素对疼痛影响

Step 4: Training Adherence Calculation

Adherence indicators:

依从性 = (实际训练次数 / 计划训练次数) × 100%

Analysis dimensions:

Weekly adherence
Monthly adherence
Overall adherence
Adherence for different training types

Step 5: Goal Achievement Assessment

Goal progress tracking:

Calculate the completion percentage for each goal
Estimate goal achievement time
Identify lagging goals
Provide goal adjustment suggestions

Step 6: Rehabilitation Phase Assessment

Current Phase Analysis:

Phase goal completion status
Whether ready to enter the next phase
Phase transition suggestions

Step 7: Generate Report

Output includes:

Rehabilitation progress summary
Functional improvement trends
Pain control status
Training adherence evaluation
Goal achievement evaluation
Phase progress suggestions
Personalized suggestions

Imported: Output Format

Rehabilitation Progress Report Structure

# 康复进展报告
**报告日期**: YYYY-MM-DD
**康复时长**: X天
**当前阶段**: 第X阶段 - 阶段名称

#### Imported: 1. 康复进展摘要

[整体进展评价：优秀/良好/一般/需改进]
- 康复时长：X天（第X周）
- 完成训练：X次
- 训练依从性：X%
- 当前阶段进展：X%

#### Imported: 2. 功能改善趋势

### 关节活动度（ROM）
- [关节名] [活动类型]: 基线X° → 当前X° → 改善X°
- 改善速率：X°/周
- 达到目标时间预估：X周
- 趋势分析：[改善趋势描述]

### 肌力评估
- [肌群名]: 基线X/5 → 当前X/5 → 改善X级
- 肌力提升模式：[描述]
- 肌力平衡：[评估]

### 平衡功能
- [测试类型]: 基线X → 当前X → 改善X
- 平衡稳定性：[评估]
- 跌倒风险：[评估]

#### Imported: 3. 疼痛控制情况

- 平均疼痛水平：X/10
- 疼痛趋势：[改善/稳定/加重]
- 疼痛模式：[描述]
- 触发因素：[识别出的触发因素]
- 疼痛控制建议：[建议]

#### Imported: 4. 训练依从性

- 整体依从性：X%
- 计划训练：X次
- 实际训练：X次
- 依从性评价：[优秀/良好/一般/需改进]
- 缺训原因分析：[如有]

#### Imported: 5. 目标达成情况

### 已达成目标（X个）
- 目标1：[描述] - 达成日期：YYYY-MM-DD
- ...

### 进行中目标（X个）
- 目标1：[描述] - 当前进度：X% - 预计达成：YYYY-MM-DD
- ...

### 滞后目标（X个）
- 目标1：[描述] - 当前进度：X% - 需要关注

#### Imported: 6. 康复阶段进展

**当前阶段**: 第X阶段 - [阶段名称]
- 阶段目标完成：X/X
- 阶段进度：X%
- 阶段持续时间：X周
- **阶段评价**: [评价]

**是否准备好进入下一阶段**: [是/否]
- [准备好的理由] / [需要继续努力的项目]

#### Imported: 7. 个性化建议

### 训练建议
- [具体训练建议]

### 目标调整建议
- [目标调整建议]

### 阶段转换建议
- [阶段转换建议]

### 注意事项
- [需要注意的事项]

#### Imported: 8. 下次评估

**下次评估日期**: YYYY-MM-DD
**评估重点**: [重点评估项目]

Brief Progress Report


#### Imported: 康复进展简报

📊 **整体进展**: 良好
⏱️ **康复时长**: 第X周（X天）
🎯 **阶段**: 第X阶段 - [阶段名称]

**功能改善**:
- ROM: +X°（改善速率X°/周）✅
- 肌力: 提升X级 ✅
- 平衡: 改善X% ✅

**疼痛控制**: 平均X/10（[趋势]）
**训练依从性**: X%（[评价]）
**目标达成**: X/X（X%）

**当前阶段**: X/X目标完成
**下一阶段准备**: [是/否]

💡 **建议**: [1-2条核心建议]

Imported: Data Sources

Main Data File

File path: data/rehabilitation-tracker.json
Read fields:
- user_profile - User profile and basic rehabilitation information
- rehabilitation_goals - Rehabilitation goal list
- exercise_log - Training log
- functional_assessments - Functional assessment records
- phase_progression - Phase progress records
- pain_diary - Pain diary
- statistics - Statistical data

Log Data File

File path: data/rehabilitation-logs/YYYY-MM/YYYY-MM-DD.json
Read fields:
- daily_summary - Daily training summary
- exercise_sessions - Training details
- pain_entries - Pain records
- assessments - Assessment records
- notes - Daily notes

Imported: Analysis Algorithms

1. Improvement Trend Analysis

Linear regression analysis:

使用最小二乘法拟合功能改善趋势
改善速率 = (当前值 - 基线值) / 时间间隔

Improvement pattern recognition:

Linear improvement: stable and continuous improvement
Stepwise improvement: rapid improvement after plateau
Plateau: improvement stagnation
Regression: functional decline (requires attention)

2. Pain Time Series Analysis

Moving average calculation:

7日移动平均疼痛 = sum(近7天疼痛) / 7

Pain trend determination:

Improvement: pain score decrease ≥20%
Stable: pain score change <20%
Worsening: pain score increase ≥20%

3. Adherence Calculation

总体依从性 = (实际训练天数 / 计划训练天数) × 100%

训练类型依从性 = (某类型实际完成 / 某类型计划完成) × 100%

Adherence evaluation:

Excellent: ≥90%
Good: 75-89%
Fair: 60-74%
Needs improvement: <60%

4. Goal Achievement Prediction

Linear extrapolation:

预测时间 = 当前日期 + ((目标值 - 当前值) / 改善速率)

Considerations:

Recent improvement rate
Plateau history
Training adherence

5. Phase Transition Readiness Assessment

Readiness score:

准备度 = (已达成阶段目标数 / 阶段目标总数) × 100%

准备度 ≥ 80%: 建议进入下一阶段
准备度 60-79%: 可考虑进入下一阶段，需谨慎
准备度 < 60%: 建议继续当前阶段

Imported: Safety and Privacy

Data Security Principles

Local Storage
- All rehabilitation data is stored only on the user's local device
- Not uploaded to any cloud server
- Not shared with third parties
Privacy Protection
- Personal health information is kept strictly confidential
- Data files do not contain personally identifiable information
- Users have full control over data access permissions
Data Integrity
- Raw data is not modified
- Analysis results are based on real data
- Supports data export and backup

Medical Safety Boundaries

What the system cannot do:

❌ Do not provide specific rehabilitation training prescriptions
❌ Do not replace professional guidance from a rehabilitation therapist
❌ Do not diagnose injuries or complications
❌ Do not adjust rehabilitation phase plans
❌ Do not predict rehabilitation prognosis timelines
❌ Do not handle acute pain or injuries

What the system can do:

✅ Provide data analysis and trend identification
✅ Provide progress tracking and goal management
✅ Provide general rehabilitation advice
✅ Provide reminders for professional rehabilitation medical care
✅ Record training and assessment data
✅ Generate rehabilitation progress reports

Important notes:

All rehabilitation training plans should follow the guidance of a rehabilitation therapist
If there is any worsening of pain or regression in function, seek medical attention promptly
Regular professional assessment is key to successful rehabilitation
System recommendations are for reference only and do not replace professional judgment

Imported: Error Handling

Data Reading Errors

Error Type 1: File does not exist

错误信息: "未找到康复数据文件，请先使用 /rehab start 开始康复追踪"
处理建议: 引导用户开始康复记录

Error Type 2: Insufficient data

错误信息: "数据不足，至少需要3次功能评估或10天训练记录才能生成分析报告"
当前数据: X次评估，X天训练记录
处理建议: 建议用户继续记录更多数据

Error Type 3: Data structure error

错误信息: "数据文件结构异常，请检查数据完整性"
处理建议: 建议用户重新初始化康复档案

Analysis Process Errors

Error type: Calculation exception

错误信息: "数据分析过程中出现异常，请稍后重试"
处理建议: 记录错误日志，提供基础数据展示

Output Generation Errors

Error type: Report generation failed

错误信息: "报告生成失败，请尝试简化查询条件或联系技术支持"
处理建议: 提供简化版报告或原始数据导出

Imported: Usage Examples

Example 1: View rehabilitation progress

User input:

/rehab progress

Skill execution:

Read rehabilitation-tracker.json
Read the rehabilitation log for the past 30 days
Analyze functional improvement trends
Calculate training adherence
Assess goal achievement status
Generate progress report

Output:

# 康复进展报告

#### Imported: 康复进展摘要

📊 整体进展: 良好
⏱️ 康复时长: 第6周（36天）
🎯 当前阶段: 第3阶段 - 强化期

#### Imported: 功能改善

- 膝关节屈曲: 30° → 120° (+90°) ✅
- 膝关节伸直: -10° → 0° (+10°) ✅
- 股四头肌肌力: 3/5 → 4/5 (提升1级) ✅
- 单腿站立: 5秒 → 30秒 (+25秒) ✅

#### Imported: 疼痛控制

- 平均疼痛: 1.5/10（良好控制）
- 疼痛趋势: 稳定 ✅

#### Imported: 训练依从性: 92%（优秀）



#### Imported: 目标达成: 8/14（57%）

- ✅ 已达成: 8个
- 🔄 进行中: 5个
- ⚠️ 滞后: 1个

#### Imported: 阶段进展

第3阶段进度: 2/5目标完成（40%）
下一阶段准备: 需要继续努力

💡 建议: 继续当前训练强度，重点关注股四头肌强化训练

Example 2: Analyze functional improvement trends

User input:

/rehab trends rom

Skill execution:

Extract all ROM assessment records
Plot ROM improvement curve (text description)
Calculate improvement rate
Predict time to reach goal
Identify improvement patterns

Output:

# 关节活动度（ROM）趋势分析

#### Imported: 膝关节屈曲

📈 改善趋势: 良好

时间线:
- 5/15: 30° (基线)
- 5/30: 70° (+40°)
- 6/15: 100° (+30°)
- 6/20: 120° (+20°)

改善速率: 8.6°/周
目标: 135°
预计达成: 2025-08-01（还需2周）
趋势: 持续改善 ✅

#### Imported: 膝关节伸直

✅ 已达成目标

时间线:
- 5/15: -10° (基线)
- 6/10: 0° (达成目标) ✅
- 6/20: 0° (维持)

改善速率: 2.5°/周
目标: 0°
达成日期: 2025-06-10
趋势: 维持目标 ✅

#### Imported: 建议

- 膝关节屈曲进展良好，继续保持
- 注意伸直维持训练，避免屈曲挛缩
- 预计2周内可达到屈曲目标

Example 3: Assess pain patterns

User input:

/rehab analysis pain

Skill execution:

Extract all pain records
Analyze temporal changes in pain
Identify pain triggers
Assess pain control effectiveness

Output:

# 疼痛模式分析

#### Imported: 疼痛趋势

📉 总体趋势: 改善中

- 基线疼痛: 5/10
- 当前疼痛: 2/10
- 改善: 3分（60%改善）✅

#### Imported: 时序模式

- 晨起疼痛: 1/10（轻度）
- 活动后疼痛: 2/10（轻度）
- 休息时疼痛: 0/10（无痛）

#### Imported: 触发因素识别

- 主要触发因素: 延长坐姿、上下楼梯
- 疼痛加剧活动: 下楼梯、深蹲
- 缓解因素: 休息、冰敷、抬高

#### Imported: 训练相关疼痛

- 训练时平均疼痛: 1.2/10（安全范围）
- 训练后疼痛: 2/10（快速缓解）
- 训练依从性不受疼痛影响 ✅

#### Imported: 建议

- 疼痛控制良好，继续当前训练强度
- 注意训练后休息和冰敷
- 避免疼痛加剧活动（深蹲、下楼梯）
- 如疼痛>4/10，及时就医评估

Imported: Correlation Analysis

Association with Exercise Module

Correlation analysis:

Association between rehabilitation training and recovery of exercise capacity
Relationship between rehabilitation training intensity and heart rate changes
Association between functional improvement and daily activity volume

Example:

用户使用 /rehab analysis correlation fitness
技能读取:
- rehabilitation-tracker.json
- fitness-tracker.json
- 分析康复训练与运动指标的相关性

Association with Sleep Module

Correlation analysis:

Relationship between training intensity and sleep quality
Relationship between pain level and sleep duration
Analysis of sleep needs during recovery

Association with Medication Module

Correlation analysis:

Trends in painkiller use
Relationship between medication and training intensity
Pain Control and Medication Adherence

Usage Examples

Scenario 1: A new user starts rehabilitation

用户: /rehab start acl-surgery 2025-05-01
系统: 初始化康复档案，设置基础目标，提供初始建议
技能: rehabilitation-analyzer（可选，用于初步评估）

Scenario 2: Log daily training

用户: /rehab exercise slr 3x15 pain2
系统: 记录训练数据，更新训练日志
技能: 不触发（仅记录）

Scenario 3: View progress reports

用户: /rehab progress
系统: 调用 rehabilitation-analyzer 技能
技能: 完整分析，生成进展报告

Scenario 4: Analyze a specific function

用户: /rehab trends rom
系统: 调用 rehabilitation-analyzer 技能
技能: ROM专项分析，生成趋势报告

Scenario 5: Assess pain patterns

用户: /rehab analysis pain
系统: 调用 rehabilitation-analyzer 技能
技能: 疼痛专项分析，识别模式和触发因素

Skill Version: v1.0 Last Updated: 2026-01-06 Maintainer: WellAlly Tech

Imported: Limitations

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

About this skill

Overview

When to Use This Skill

Operating Table

Workflow

Imported Workflow Notes

Imported: Core Functions

Examples

Example 1: Ask for the upstream workflow directly

Example 2: Ask for a provenance-grounded review

Example 3: Narrow the copied support files before execution

Example 4: Build a reviewer packet

Best Practices

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Problem: The imported workflow feels incomplete during review

Problem: The task drifted into a different specialization

Related Skills

Additional Resources

Imported Reference Notes

Imported: Trigger Conditions

Imported: Execution Steps

Step 1: Data Reading

Step 2: Functional Assessment Trend Analysis

Step 3: Pain Pattern Analysis

Step 4: Training Adherence Calculation

Step 5: Goal Achievement Assessment

Step 6: Rehabilitation Phase Assessment

Step 7: Generate Report

Imported: Output Format

Rehabilitation Progress Report Structure

Brief Progress Report

Imported: Data Sources

Main Data File

Log Data File

Imported: Analysis Algorithms

1. Improvement Trend Analysis

2. Pain Time Series Analysis

3. Adherence Calculation

4. Goal Achievement Prediction

5. Phase Transition Readiness Assessment

Imported: Safety and Privacy

Data Security Principles

Medical Safety Boundaries

Imported: Error Handling

Data Reading Errors

Analysis Process Errors

Output Generation Errors

Imported: Usage Examples

Example 1: View rehabilitation progress

Example 2: Analyze functional improvement trends

Example 3: Assess pain patterns

Imported: Correlation Analysis

Association with Exercise Module

Association with Sleep Module

Association with Medication Module

Usage Examples

Scenario 1: A new user starts rehabilitation

Scenario 2: Log daily training

Scenario 3: View progress reports

Scenario 4: Analyze a specific function

Scenario 5: Assess pain patterns

Imported: Limitations