An automated integration for the Concept2 Logbook API that provides deep analytical insights into rowing, biking, and skiing performance.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install concept2
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install concept2 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Concept2 Logbook Analyzer?
The Concept2 Logbook Analyzer is a specialized tool within the Openclaw Skills ecosystem designed to programmatically access and evaluate workout data from the Concept2 platform. It allows athletes and developers to move beyond basic logging by providing a technical framework for analyzing pulse zones, pace consistency, and long-term training trends. By utilizing Openclaw Skills to interface with the Concept2 API, users can transform raw workout metrics into structured, actionable intelligence.
This skill is particularly valuable for those looking to automate their fitness tracking workflows. Whether you are monitoring aerobic capacity or assessing anaerobic thresholds, the integration provides a robust foundation for building personalized coaching tools or detailed performance dashboards.
Concept2 Logbook Analyzer Use Cases
- Automated retrieval of rowing, skiing, and biking workout history
- Heart rate distribution analysis across five intensity zones
- Long-term trend tracking to measure aerobic improvement
- Stroke-level granularity analysis for technique refinement
- Generation of personalized training recommendations based on historical data
How Concept2 Logbook Analyzer Works
- Authentication: The skill uses a Bearer token to securely connect to the Concept2 Logbook API.
- Data Extraction: It fetches user profile information and paginated workout results, including specific stroke-level metrics.
- Normalization: Raw data is processed into standardized units like meters, seconds, and tenths of seconds.
- Analysis: The system calculates heart rate zones using the Tanaka formula or profile data and assesses pace consistency.
- Output Generation: Results are formatted into tables, JSON, or summaries for easy consumption through Openclaw Skills scripts.
Concept2 Logbook Analyzer Setup
- Obtain an API access token from the Concept2 Developer portal.
- Ensure Python 3 is installed in your local environment.
- Execute the fetch script using your token and desired date range:
python3 scripts/fetch_workouts.py --token <YOUR_API_TOKEN> --from-date 2026-03-01 --format table
Concept2 Logbook Analyzer Data Schema & Taxonomy
The skill organizes data into several core entities as part of the Openclaw Skills data processing layer:
- User Profile: Contains age, weight, and birthdate for accurate HR zone calculations.
- Workout Results: A paginated list including distance, duration, calories, and specific workout types (e.g., FixedDistance, VariableInterval).
- Stroke Data: High-resolution incremental data for time, distance, and pace per stroke.
| Pagination Field | Description |
|---|---|
| total | Total number of workouts available |
| per_page | Results per API request (max 250) |
| current_page | The index of the current data set |
Concept2 Logbook Analyzer Advanced Features
- Multi-equipment support including RowErg, SkiErg, and BikeErg
- Automatic Max HR estimation based on the Tanaka formula (208 - 0.7 x age)
- Eight-week rolling trend analysis for tracking pace improvement and volume
- Detailed pace consistency ratings to evaluate workout quality
- High-intensity balance monitoring using the 20% rule for pulse zones 4 and 5
SKILL.md
Loading
Related Openclaw Skills
Moltiverse Among
A competitive AI social deduction arena where agents play Among Us to win crypto prizes on the Monad network.
Moltiverse Among
A competitive AI social deduction arena where autonomous agents play Among Us to win MON prizes on the Monad network.
Web Searcher
An autonomous research agent that executes multi-angle searches, extracts deep-page content, and synthesizes data into structured, cited reports.
n8n Workflow Builder
A programmatic interface for designing, deploying, and managing n8n automation workflows using a specialized API-driven agent.
ACP Job Submitter
A powerful bridge for delegating tasks and crypto services between AI agents to earn from service spreads.
AI Agent Helper
A comprehensive framework for designing, optimizing, and deploying high-performance AI agents through advanced prompt engineering and loop architecture.
Featured*
