claude-running-coach

Name: claude-running-coach
Author: colineberhardt

Stars

How to install claude-running-coach?

colineberhardt/claude-running-coach

$git clone https://github.com/colineberhardt/claude-running-coach

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install claude-running-coach by running `git clone https://github.com/colineberhardt/claude-running-coach`, then use it for the current task and follow its documentation at https://github.com/colineberhardt/claude-running-coach.

Files · 1

View on GitHub

README.md

1	# Claude Running Race Coach
2
3	An AI-powered running coach built for [Claude Code](https://code.claude.com/) and [Claude Desktop](https://claude.ai/download) using the [Skills framework](https://code.claude.com/docs/skills). This project demonstrates how to combine Claude's capabilities with specialized training knowledge and training data to provide personalized running coaching assistance. Distributed as a plugin for easy installation.
4
5	For usage instructions, see [running-race-coach/README.md](running-race-coach/README.md).
6
7	## Overview
8
9	Claude Running Race Coach uses Claude Code's Skills framework to provide intelligent running coaching that includes:
10	- Evidence-based training plan generation
11	- Multi-platform training data integration (Strava, Garmin, manual entry, conversational)
12	- Weekly training analysis and coaching feedback
13	- Scientific pace calculation and workout planning
14
15	## Project Structure
16
17	```
18	claude-coach/
19	├── running-race-coach/ # Main plugin package
20	│ ├── README.md # User-facing documentation
21	│ └── skills/ # Skill definitions
22	│ ├── training-plan/ # Training plan generation skill
23	│ │ ├── SKILL.md # Skill definition and workflow
24	│ │ ├── references/ # Coaching guides and principles
25	│ │ │ └── coaches-guide.md
26	│ │ └── scripts/ # Pace and distance calculators
27	│ │ ├── calculate_paces.py
28	│ │ └── interval_calculator.py
29	│ ├── strava-sync/ # Strava data synchronization skill
30	│ │ └── SKILL.md # Sync workflow and formatting
31	│ ├── training-dashboard/ # Training progress visualization
32	│ │ └── SKILL.md # Dashboard generation workflow
33	│ └── running-coach/ # Weekly coaching analysis skill
34	│ └── SKILL.md # Coaching workflow and principles
35	├── training-log/ # Generated weekly training summaries
36	├── coaching-log/ # Coaching session notes
37	├── training-plan.md # Generated training plans
38	├── package.py # Plugin packaging script
39	└── README.md # This file
40	```
41
42	## Skills Architecture
43
44	This project leverages Claude Code's [Skills framework](https://code.claude.com/docs/skills), which allows Claude to follow structured workflows for specific domains. Each skill is a combination of:
45
46	### 1. Skill Definition (`SKILL.md`)
47
48	Each `SKILL.md` file defines:
49	- Invocation patterns: Keywords and phrases that trigger the skill
50	- Workflow steps: Structured process Claude follows
51	- Best practices: Domain-specific knowledge and principles
52	- Tool usage: When to use Python scripts or MCP servers
53	- Output format: How to structure the results
54
55	### 2. Reference Documentation
56
57	The `references/` directory contains in-depth knowledge that Claude loads into context when needed. For example:
58	- coaches-guide.md: Comprehensive training principles, periodization strategies, and workout guidelines
59
60	### 3. Executable Tools
61
62	Python scripts in the `scripts/` directories provide:
63	- calculate_paces.py: Calculates training pace zones from race goal times
64	- interval_calculator.py: Computes total distances for interval workouts
65
66	These are executed via Claude Code's terminal integration.
67
68	### 4. Integration with MCP Servers
69
70	Skills can leverage Model Context Protocol (MCP) servers for external data:
71	- Strava MCP server: Fetches activity data, athlete info, and statistics
72	- Extensible to other platforms (Garmin, Apple Health, etc.)
73
74	## How It Works
75
76	### Training Plan Generation
77
78	When a user requests a training plan:
79	1. training-plan skill is invoked
80	2. Claude gathers requirements (race distance, goal time, current mileage, race date)
81	3. Executes `calculate_paces.py` to determine training zones
82	4. Applies periodization principles from `coaches-guide.md`
83	5. Generates structured markdown training plan
84	6. Uses `interval_calculator.py` to calculate workout distances
85	7. Saves plan to `training-plan.md`
86
87	### Training Data Synchronization
88
89	The strava-sync skill:
90	1. Connects to Strava MCP server
91	2. Fetches recent activities (configurable time range)
92	3. Extracts detailed metrics (pace, heart rate, power, cadence, elevation)
93	4. Parses lap data for interval workouts
94	5. Formats data as structured markdown
95	6. Saves to `training-log/week-n.md`
96
97	The system is flexible and also supports:
98	- Manual markdown file creation
99	- Data import from other platforms (Garmin, Apple Health, Polar Flow)
100	- Conversational data input (describe workouts verbally)
101
102	### Weekly Coaching Analysis
103
104	The running-coach skill:
105	1. Loads the user's training plan
106	2. Retrieves training log (from any source)
107	3. Asks for subjective feedback (energy, fatigue, challenges)
108	4. Compares planned vs. actual execution for each workout
109	5. Analyzes:
110	- Pace accuracy (easy, threshold, intervals, race pace)
111	- Heart rate zones and effort levels
112	- Workout execution quality
113	- Weekly volume and progression

6 picks

Type

Install claude-running-coach by running `git clone https://github.com/colineberhardt/claude-running-coach`, then use it for the current task and follow its documentation at https://github.com/colineberhardt/claude-running-coach.

claude-running-coach

How to install claude-running-coach?

Related

claude-running-coach

How to install claude-running-coach?

Related