← Back to Skills Marketplace
popstarxu-spec

Running Coach

by popstarxu-spec · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
339
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install runningcoach
Description
基于全频训练法为跑者生成和管理训练计划,支持自动同步到Intervals.icu并提供配速区间指导。
Usage Guidance
This skill appears to do what it says (generate weekly running plans and POST them to intervals.icu) and the code is small and readable. The main issue is metadata: the registry did not declare the environment variables the code and SKILL.md require (INTERVALS_API_KEY, INTERVALS_ATHLETE_ID, optionally INTERVALS_THRESHOLD_PACE). Before installing or granting access: 1) Verify and supply an Intervals.icu API key and Athlete ID only via environment variables or a config file you control (avoid pasting keys into third-party UIs). 2) Run the included script locally first with --dry-run to confirm behavior: python3 weekly_plan.py --dry-run --config config.json. 3) Inspect weekly_plan.py yourself (it only contacts https://intervals.icu/api/v1) and confirm network calls are limited to that host. 4) Use a least-privilege API key if Intervals.icu supports scoping, or be prepared to rotate/regenerate the key after testing. 5) If you rely on automated permission checks, request the publisher to update the package metadata to declare required env vars and primary credential so permissions are explicit. These steps will reduce the risk posed by the metadata omission.
Capability Analysis
Type: OpenClaw Skill Name: runningcoach Version: 1.0.1 The 'Running Coach' skill bundle is a legitimate tool designed to manage and sync running training plans with the Intervals.icu platform. The core logic in 'weekly_plan.py' uses standard Python libraries to interact with the service's API, and the documentation in 'SKILL.md' provides clear instructions for users to configure their own API credentials securely via environment variables or a local configuration file. No evidence of malicious intent, data exfiltration to unauthorized endpoints, or prompt injection was found.
Capability Assessment
Purpose & Capability
The name/description, SKILL.md and weekly_plan.py all consistently implement a running-plan generator that uploads to intervals.icu. However the registry metadata declared no required env vars or primary credential while both the SKILL.md and the Python code clearly require INTERVALS_API_KEY and INTERVALS_ATHLETE_ID (and optionally INTERVALS_THRESHOLD_PACE). The implementation is coherent with the stated purpose but the metadata omission is misleading.
Instruction Scope
SKILL.md instructions stay within scope: they explain how to obtain an Intervals.icu API key, set env vars or edit config.json, and how to format workouts. There are no instructions to read unrelated system files, harvest other credentials, or contact services other than Intervals.icu.
Install Mechanism
There is no install spec (instruction-only skill) and the code file included is a small Python script using only stdlib (urllib, base64). No remote downloads, package installs, or executable payloads are present, which lowers install risk.
Credentials
Requesting an Intervals.icu API key and Athlete ID is appropriate for uploading workouts and calculating load. The concern is the manifest/registry did not declare these as required (primaryEnv was none), which could mislead automated permission checks or users. The code reads INTERVALS_API_KEY, INTERVALS_ATHLETE_ID and INTERVALS_THRESHOLD_PACE from env or config.json — these env names appear in _meta.json but were not presented as required in the registry metadata.
Persistence & Privilege
always:false (no forced inclusion). The skill does not request system-wide privileges or modify other skills. It stores configuration in a local config.json (user-controlled). Autonomous invocation is allowed by default (normal) but is not combined with any other elevated privilege here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install runningcoach
  3. After installation, invoke the skill by name or use /runningcoach
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Clarified the setup instructions, providing separate sections for environment variable and config file configuration. - No functional or interface changes; updated documentation only.
v1.0.0
- Initial release of Running Coach (跑步教练助手) skill. - Provides guidance for percentage-based training plans and syncs them automatically to Intervals.icu. - Supports easy setup with detailed instructions for Intervals.icu API and wearables integration. - Defines strict workout formatting rules to ensure correct syncing and training load calculation. - Includes comprehensive pacing zone references, weekly template workflows, and example workout uploads. - Offers training load goal ranges and practical notices for users to optimize their training management.
Metadata
Slug runningcoach
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Running Coach?

基于全频训练法为跑者生成和管理训练计划,支持自动同步到Intervals.icu并提供配速区间指导。 It is an AI Agent Skill for Claude Code / OpenClaw, with 339 downloads so far.

How do I install Running Coach?

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

Is Running Coach free?

Yes, Running Coach is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Running Coach support?

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

Who created Running Coach?

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

💬 Comments