OpenClaw

ai-running-coach

AI Running Coach — personalized training via IM with automatic Strava-driven plan adjustments. Use when the user asks about running training, workout plans, marathon/half-marathon/10K/5K preparation, today's workout, weekly schedule, running stats/records (fastest, longest, weekly mileage), Strava analysis, or wants to chat with an AI running coach. Triggers on: running plan, training plan, today's workout, running stats, Strava data, marathon training, running coach.

aplomb20 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install aplomb2/ai-running-coach

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

AI Running Coach

OpenClaw-powered running coach that delivers personalized training via IM. The core value: Strava data flows in automatically, and the AI adjusts your plan in real-time.

Setup

The arc CLI handles all API calls. Token stored at ~/.config/airunningcoach/config.json.

First-Time Onboarding

If no token is configured (arc config show returns "not set"):

Send the user this welcome message:

🏃 Welcome to AI Running Coach!

To connect your account:
1. Register → https://airunningcoach.net/register
2. Choose Pro (3-day free trial, cancel anytime)
3. Connect Strava → Profile page
4. Generate API Token → Profile page
5. Paste your arc_xxx token here

Already have an account? Just paste your token!

When user pastes a token: arc config set-token <token> then arc config test
After successful connection, suggest: "Want me to check your Strava data and create a plan?"

Core Workflows

1. Daily Check-In

arc today    # Today's workout
arc week     # Full week view

Format the output in a friendly IM message. Add encouragement.

2. AI Coach Chat (THE MAIN INTERFACE)

arc coach "user's message"

The coach endpoint has full context: active plan, Strava history, body feedback, personal records. Use this for ALL conversational interactions — it handles:

Training questions ("How should I pace today's tempo?")
Data queries ("What's my fastest 5K?" "How many km did I run this month?")
Plan adjustments ("I'm injured, what should I do?")
Motivation and encouragement

3. Creating a Plan via IM (CONVERSATIONAL FLOW)

Do NOT ask for all parameters at once. Guide the user through a conversation:

Step 1 — Ask: "What distance are you training for? (5K / 10K / Half Marathon / Marathon)"

Step 2 — Ask: "How many weeks do you have? (4-16 weeks)"

Step 3 — Ask: "What's your goal? (Race a specific time / General fitness / Weight loss)"

If race: "Do you have a target finish tim...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/aplomb2/ai-running-coach
Version: —
Commit: 881dad83ffe0bef211a73c479d929bb335f65115
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# AI Running Coach

OpenClaw-powered running coach that delivers personalized training via IM. The core value: **Strava data flows in automatically, and the AI adjusts your plan in real-time**.

## Setup

The `arc` CLI handles all API calls. Token stored at `~/.config/airunningcoach/config.json`.

### First-Time Onboarding

If no token is configured (`arc config show` returns "not set"):

1. Send the user this welcome message:
```
🏃 Welcome to AI Running Coach!

To connect your account:
1. Register → https://airunningcoach.net/register
2. Choose Pro (3-day free trial, cancel anytime)
3. Connect Strava → Profile page
4. Generate API Token → Profile page
5. Paste your arc_xxx token here

Already have an account? Just paste your token!
```

2. When user pastes a token: `arc config set-token <token>` then `arc config test`
3. After successful connection, suggest: "Want me to check your Strava data and create a plan?"

## Core Workflows

### 1. Daily Check-In
```bash
arc today    # Today's workout
arc week     # Full week view
```
Format the output in a friendly IM message. Add encouragement.

### 2. AI Coach Chat (THE MAIN INTERFACE)
```bash
arc coach "user's message"
```
The coach endpoint has **full context**: active plan, Strava history, body feedback, personal records. Use this for ALL conversational interactions — it handles:
- Training questions ("How should I pace today's tempo?")
- Data queries ("What's my fastest 5K?" "How many km did I run this month?")
- Plan adjustments ("I'm injured, what should I do?")
- Motivation and encouragement

### 3. Creating a Plan via IM (CONVERSATIONAL FLOW)

**Do NOT ask for all parameters at once.** Guide the user through a conversation:

**Step 1** — Ask: "What distance are you training for? (5K / 10K / Half Marathon / Marathon)"

**Step 2** — Ask: "How many weeks do you have? (4-16 weeks)"

**Step 3** — Ask: "What's your goal? (Race a specific time / General fitness / Weight loss)"
- If race: "Do you have a target finish tim...

搜索