Not in the top 1,000 by GitHub stars
ColinEberhardt/claude-running-coach
An AI-powered running coach that provides personalized training plans, analyzes your workouts, and offers evidence-based coaching guidance.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
running-race-coach/skills/running-coach/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c1546f47712f
No earlier version was observed for comparison.
running-race-coach/skills/strava-sync/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c1546f47712f
No earlier version was observed for comparison.
running-race-coach/skills/training-dashboard/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c1546f47712f
No earlier version was observed for comparison.
running-race-coach/skills/training-plan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → c1546f47712f
No earlier version was observed for comparison.
Verified commit c1546f47712ff3100d7443cd032963edd54ddb1f
git clone --filter=blob:none --no-checkout https://github.com/ColinEberhardt/claude-running-coach.git .hotskills/colineberhardt-claude-running-coach && git -C .hotskills/colineberhardt-claude-running-coach checkout --detach c1546f47712ff3100d7443cd032963edd54ddb1f
# Copy each selected skill directory from .hotskills/colineberhardt-claude-running-coach into .claude/skills/<skill-name>/Heat
2.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- running-coach
running-race-coach/skills/running-coach - strava-sync
running-race-coach/skills/strava-sync - training-dashboard
running-race-coach/skills/training-dashboard - training-plan
running-race-coach/skills/training-plan
How it works
running-coach
When your agent uses it
Weekly running coaching sessions that analyze training logs against the training plan, with primary focus on running and secondary analysis of cross-training activities. Works with multiple data sources including Strava, other platforms (Garmin, Apple Health, etc.), manual logs, or conversational input. Use when the athlete wants to review their training week, get coaching feedback, analyze how they performed, or check if they're on track with their training plan. Trigger phrases include "review my training", "coach me", "how did I do this week", or any request for training analysis or coaching feedback.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
3,528 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Coaching Style
- Coaching Session Workflow
- Key Coaching Principles
- Conversational Dos and Don'ts
- Red Flags to Watch For (But Address Gently)
Files
../../.claude-plugin/plugin.jsonasset372 bytesSKILL.mdcore15,656 bytesSKILL.mdcore15,656 bytes
Read SKILL.md
# Running Coach
Weekly coaching sessions that compare actual training against the planned training schedule, analyze performance metrics (primarily running, with complementary cross-training analysis), and provide guidance on progress and adjustments.
**Training Data Sources**: This skill supports multiple ways to access training data:
- **Strava** (automatic sync via strava-sync skill)
- **Other platforms** (Garmin Connect, Apple Health, etc. - provided by athlete)
- **Manual logs** (athlete creates/updates markdown files)
- **Conversational** (athlete describes training verbally)
## Coaching Style
**BE CONVERSATIONAL AND CHATTY!** This isn't a formal report - it's a chat between coach and athlete. Use:
- Casual language and encouragementView the complete source on GitHubstrava-sync
When your agent uses it
Downloads and syncs training data from Strava using the Strava MCP server. This is ONE option for importing training data - athletes can also use manual logs, other platforms (Garmin, Apple Health), or provide data conversationally. Use this skill specifically when the athlete wants to sync from Strava or when the running-coach indicates Strava as the chosen data source. Stores activities in the training-log folder as markdown summaries, including lap details for workout runs.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
2,212 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- MCP Tools Used
- Error Handling
- Notes
Files
SKILL.mdcore8,515 bytesSKILL.mdcore8,515 bytesSKILL.mdcore8,515 bytesSKILL.mdcore8,515 bytes
Read SKILL.md
# Strava Training Log Sync
## Overview
This skill downloads training data from Strava using the Strava MCP server and creates weekly markdown summaries in the `training-log` folder. Each week is stored as a single markdown file with detailed activity summaries, including lap details for runs marked as workouts.
**Note**: This is a Strava-specific data import tool. The running coach system also supports:
- Other platforms (Garmin Connect, Apple Health, Polar Flow, etc.) - athlete provides data
- Manual training logs - athlete creates markdown files directly
- Conversational input - athlete describes training verbally
This skill uses MCP tools specific to Strava (`mcp__strava__*`). Similar skills could be created for other platforms using their respective APIs or MCP servers.
## WorkflowView the complete source on GitHubtraining-dashboard
When your agent uses it
Generate a comprehensive HTML training dashboard showing progress toward half marathon training goals. Outputs a single self-contained HTML file with retro styling, ASCII charts, weekly mileage tracking, session completion rates, pace adherence, phase progress, and coaching commentary. Use when the athlete wants to see their training progress, check if they're on track, view their training statistics, or get an overview of their plan progress. Trigger phrases include "show my dashboard", "training progress", "how am I doing", "show my stats", or any request for a training overview.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,924 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Dashboard Configuration
- Dashboard Generation Workflow
- Tips for Customization
- Notes
Files
SKILL.mdcore22,712 bytes
Read SKILL.md
# Training Dashboard
Generate an HTML dashboard with retro styling showing comprehensive training progress toward the half marathon goal. Outputs a single HTML file saved to `dashboard.html` that can be opened in any browser.
## Dashboard Configuration
When generating the dashboard, you will prompt the user for their preferences. If the user has previously provided preferences in the conversation, use those. Otherwise, ask for the following:
### Configuration Prompts
**1. Layout Style**
Ask: "What level of detail would you like?"
- `detailed` (default): Full metrics, large charts, extensive commentaryView the complete source on GitHubtraining-plan
When your agent uses it
Create personalized training plans for 5K, 10K, Half Marathon, and Marathon races. Use when the user requests a training plan for any of these distances, wants to prepare for a race, or asks for a structured running program. This skill generates comprehensive markdown training plans that include race goals, training paces, phased progression, and week-by-week workout schedules.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
3,410 tokensWhen the skill is activated
Reference documents
3,898 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Output Guidelines
- References
Scripts executed separately
scripts/calculate_paces.pyscripts/interval_calculator.py
Files
SKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesSKILL.mdcore13,542 bytesreferences/coaches-guide.mddoc17,043 bytesscripts/calculate_paces.pyruns5,853 bytesscripts/interval_calculator.pyruns9,578 bytes
Read SKILL.md
# Training Plan Creator
## Overview
This skill creates personalized, evidence-based training plans for 5K, 10K, Half Marathon, and Marathon distances. Plans are delivered as structured markdown documents with clear progression, appropriate training intensities, and race-specific preparation.
## Workflow
### 1. Gather Essential Information
Before creating a plan, collect these key details from the user:
**Required:**
- **Race distance**: 5K, 10K, Half Marathon, or MarathonView the complete source on GitHubSkills included
- running-coach
- strava-sync
- training-dashboard
- training-plan
Repository facts
- License
- MIT
- Created
- Jan 31, 2026
- Last pushed
- May 18, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 8 notes
running-race-coach/skills/running-coach/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/strava-sync/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/strava-sync/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/strava-sync/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/training-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/training-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/training-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedrunning-race-coach/skills/training-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 11 network referencesin 2 files: training-dashboard/SKILL.md:128 running-race-coach/.claude-plugin/plugin.json:6
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: training-plan/scripts/calculate_paces.py:1 training-plan/scripts/interval_calculator.py:1
- No access to secrets
- No requests to vote in Hot
Show all 13 signals by file
running-race-coach/.claude-plugin/plugin.json
- Network accessline 6
"name": "Colin Eberhardt" }, "homepage": "https://github.com/ColinEberhardt/claude-running-coach", - Network accessline 7
}, "homepage": "https://github.com/ColinEberhardt/claude-running-coach", "license": "MIT" - Network accessline 8
"homepage": "https://github.com/ColinEberhardt/claude-running-coach",
running-race-coach/skills/training-dashboard/SKILL.md
- Network accessline 128
Create a single self-contained HTML file with: - Tailwind CSS loaded from CDN (https://cdn.tailwindcss.com) - Network accessline 129
- Tailwind CSS loaded from CDN (https://cdn.tailwindcss.com) - Network accessline 141
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Half Marathon Training Dashboard</title> <script src="https://cdn.tailwindcss.com"></script> - Network accessline 142
<title>Half Marathon Training Dashboard</title> <script src="https://cdn.tailwindcss.com"></script> <style> - Network accessline 143
<script src="https://cdn.tailwindcss.com"></script> - Network accessline 361
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Half Marathon Training Dashboard</title> <script src="https://cdn.tailwindcss.com"></script> - Network accessline 362
<title>Half Marathon Training Dashboard</title> <script src="https://cdn.tailwindcss.com"></script> <style> - Network accessline 363
<script src="https://cdn.tailwindcss.com"></script>
running-race-coach/skills/training-plan/scripts/calculate_paces.py
- Executable scriptline 1
#!/usr/bin/env python3
running-race-coach/skills/training-plan/scripts/interval_calculator.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 10 facts
- Network access in prose of the SKILL.mdtraining-dashboard/SKILL.md:128Low confidence
- Network access in prose of the SKILL.mdtraining-dashboard/SKILL.md:129Low confidence
- Network access in code of the SKILL.mdtraining-dashboard/SKILL.md:141High confidence
- Network access in code of the SKILL.mdtraining-dashboard/SKILL.md:142High confidence
- Network access in code of the SKILL.mdtraining-dashboard/SKILL.md:143High confidence
- Network access in code of the SKILL.mdtraining-dashboard/SKILL.md:361High confidence
- Network access in code of the SKILL.mdtraining-dashboard/SKILL.md:362High confidence
- Network access in code of the SKILL.mdtraining-dashboard/SKILL.md:363High confidence
- Executable script in code of a file that runstraining-plan/scripts/calculate_paces.py:1High confidence
- Executable script in code of a file that runstraining-plan/scripts/interval_calculator.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest running-race-coach/.claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md running-race-coach/skills/running-coach/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md running-race-coach/skills/running-coach/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md running-race-coach/skills/running-coach/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md running-race-coach/skills/running-coach/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md running-race-coach/skills/running-coach/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.