← Back to Skills Marketplace
rubengarciam

TrainingPeaks

by rubengarciam · GitHub ↗ · v1.0.1
cross-platform ✓ Security Clean
1785
Downloads
4
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install trainingpeaks
Description
Pull real-time training plans, workouts, fitness metrics (CTL/ATL/TSB), and personal records from TrainingPeaks. Uses cookie-based authentication (no API key needed). Use in conjunction with other endurance, cycling, running or swimming triathlon coach skills for best results.
Usage Guidance
This skill appears to do what it says, but it requires you to copy/paste your TrainingPeaks session cookie (Production_tpAuth) — a long-lived secret that grants access to your account. Only paste that cookie into this tool if you trust the skill and the environment where the agent runs. Recommendations before installing: 1) Review the included scripts/tp.py (already done) — it only talks to https://tpapi.trainingpeaks.com and stores data under ~/.trainingpeaks. 2) If you proceed, store the cookie only on a trusted machine, or use the TP_AUTH_COOKIE env var for short-lived CI runs. 3) To revoke local access, delete ~/.trainingpeaks (cookie, token.json, config.json). 4) Prefer official API keys if TrainingPeaks offers them — copying a session cookie is more sensitive. 5) Note the package source is anonymous (no homepage/unknown owner); if you have concerns about provenance, run the script in an isolated environment (container/VM) or avoid using it.
Capability Analysis
Type: OpenClaw Skill Name: trainingpeaks Version: 1.0.1 The OpenClaw AgentSkills bundle for TrainingPeaks is benign. The `SKILL.md` provides clear, legitimate instructions for cookie-based authentication and usage, without any prompt injection attempts or deceptive phrasing. The `scripts/tp.py` Python code uses only standard library modules, communicates exclusively with the official `tpapi.trainingpeaks.com` endpoint, and stores credentials (`cookie`, `token.json`, `config.json`) securely in `~/.trainingpeaks/` with `0o600` permissions. There is no evidence of data exfiltration to unauthorized destinations, malicious execution, persistence mechanisms, or other high-risk behaviors.
Capability Assessment
Purpose & Capability
The name/description match the implementation: the code calls tpapi.trainingpeaks.com endpoints to fetch profile, workouts, fitness, and PRs. No extraneous services, binaries, or credentials are requested. The functionality a TrainingPeaks scraper/CLI would need (cookie → token exchange, API requests, local cache) is present and appropriate.
Instruction Scope
SKILL.md explicitly instructs the user to copy the Production_tpAuth browser cookie (or set TP_AUTH_COOKIE) and run the included Python CLI. That is necessary for this cookie-based approach, but it requires the user to expose a sensitive session cookie. The instructions do not request or read unrelated files or other credentials. The skill stores the cookie and token in ~/.trainingpeaks (described in the docs).
Install Mechanism
There is no install spec and the single Python script is included in the bundle. The script uses only Python stdlib (urllib, json, pathlib, etc.) and performs no external downloads or package installs; this is low-risk from an install perspective.
Credentials
The skill declares no required env vars; TP_AUTH_COOKIE is optional and is reasonable for CI/use. No unrelated secrets or high-privilege environment variables are requested. Local storage of cookie/token in ~/.trainingpeaks is the only persistence of credentials.
Persistence & Privilege
The skill does persist credentials and tokens to ~/.trainingpeaks with attempted 0600 permissions (as stated). always is false and autonomous invocation is allowed (platform default). Because the skill handles an account session cookie, you should be mindful of allowing autonomous invocation if you don't want the agent to use that cookie without explicit prompts.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install trainingpeaks
  3. After installation, invoke the skill by name or use /trainingpeaks
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added a note in the description recommending use with other endurance, cycling, running, or swimming triathlon coach skills for best results. - No functional or technical changes; documentation update only.
v1.0.0
TrainingPeaks Skill 1.0.0 — Initial Release - Provides CLI access to TrainingPeaks data without pip dependencies. - Supports cookie-based authentication (no API key required). - Commands to view athlete profile, workouts, workout details, fitness metrics (CTL/ATL/TSB), and personal records. - Human-readable and JSON output options available for all data. - Credentials and tokens securely stored and managed in user home directory. - Designed for both interactive use and automation (CI/scripts) via environment variables.
Metadata
Slug trainingpeaks
Version 1.0.1
License
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is TrainingPeaks?

Pull real-time training plans, workouts, fitness metrics (CTL/ATL/TSB), and personal records from TrainingPeaks. Uses cookie-based authentication (no API key needed). Use in conjunction with other endurance, cycling, running or swimming triathlon coach skills for best results. It is an AI Agent Skill for Claude Code / OpenClaw, with 1785 downloads so far.

How do I install TrainingPeaks?

Run "/install trainingpeaks" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is TrainingPeaks free?

Yes, TrainingPeaks is completely free (open-source). You can download, install and use it at no cost.

Which platforms does TrainingPeaks support?

TrainingPeaks is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created TrainingPeaks?

It is built and maintained by rubengarciam (@rubengarciam); the current version is v1.0.1.

💬 Comments