← 返回 Skills 市场
829
总下载
3
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install gym
功能描述
Log workouts, plan routines, track progress, and get intelligent coaching for any fitness level.
使用说明 (SKILL.md)
Quick Reference
| Topic | File |
|---|---|
| Routines, exercises, templates | workouts.md |
| Progress tracking, volume, PRs | progress.md |
| Injury adaptation, modifications | adaptation.md |
| Gym nutrition, macros, timing | nutrition.md |
User Profile
User preferences persist in ~/gym/memory.md. Create on first use:
## Level
\x3C!-- beginner | intermediate | advanced -->
## Goals
\x3C!-- strength | hypertrophy | fat-loss | general-fitness | powerlifting -->
## Schedule
\x3C!-- Days available. Format: "days | frequency" -->
\x3C!-- Examples: Mon/Wed/Fri, 3x/week, daily -->
## Session Duration
\x3C!-- 45min | 60min | 90min -->
## Restrictions
\x3C!-- Injuries, equipment limits, mobility issues -->
\x3C!-- Examples: Lower back injury (no deadlifts), Home gym (no cable machine) -->
Fill on first conversation. Update as goals evolve.
Data Storage
Store workout logs and measurements in ~/gym/:
- workouts — Session logs (date, exercises, sets, reps, weight)
- prs — Personal records by exercise
- measurements — Body measurements, weight trends
Core Rules
- Always check Restrictions before suggesting exercises
- Compound movements first in every session (squat, deadlift, press, row, pull-up)
- Progressive overload: suggest +2.5kg or +1-2 reps when previous session was completed
- Rest periods: 2-3min for strength, 60-90s for hypertrophy, 30-45s for conditioning
- Never increase load >10% week-over-week — injury risk
- Deload week every 4-6 weeks or when user reports persistent fatigue
- If user misses days, adapt — don't guilt, just recalculate
- Track RPE when mentioned — use for auto-regulation
- Warn if training same muscle group \x3C48h apart without recovery strategy
安全使用建议
This skill appears to be what it says: a local workout planner and logger. Before installing, note that it will create and update files in ~/gym (memory.md, workouts.md, prs.md, measurements.md) containing your workout logs, measurements, and preferences. If you are uncomfortable with local storage of personal fitness data, do not install or plan to delete/secure those files after use. There are no network endpoints, credentials, or installers requested by the skill. If you want cloud sync or third-party integrations, verify how and where that would be added (those are not present here).
功能分析
Type: OpenClaw Skill
Name: gym
Version: 1.0.1
The OpenClaw 'gym' skill bundle appears benign. All files contain content strictly related to fitness tracking and coaching, with no evidence of malicious intent. The `SKILL.md` defines core rules for the AI agent that are entirely focused on fitness logic, without any prompt injection attempts to exfiltrate data, execute arbitrary commands, or hide actions. File system access is limited to the `~/gym/` directory for storing user-specific workout data and preferences, which is consistent with the skill's stated purpose. No external binaries are required, and no suspicious network activity or obfuscation is present.
能力评估
Purpose & Capability
Name/description (log workouts, plan routines, track progress, coach) align with the content of the provided files. The skill requires no external services, binaries, or credentials, which is consistent with a local workout-tracking and coaching tool.
Instruction Scope
SKILL.md and the included documents instruct the agent to create and persist user preferences and data in files beneath ~/gym (memory.md, workouts.md, prs.md, measurements.md). This is within the scope of a local fitness tracker, but users should be aware that personal workout and measurement data will be written to their home directory. The instructions do not attempt to read other system config, secrets, or contact external endpoints.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk model for install behavior — nothing is downloaded or executed beyond the platform's normal agent actions.
Credentials
The skill requires no environment variables, credentials, or special config paths. No secrets or unrelated credentials are requested, which is proportionate to its purpose.
Persistence & Privilege
always:false (default). The skill persists its own data under ~/gym as described, and does not request system-wide changes or alter other skills. The skill may be invoked by the agent (platform default), which is normal and not in itself a concern.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install gym - 安装完成后，直接呼叫该 Skill 的名称或使用
/gym触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
Preferences now persist across skill updates
v1.0.0
Initial release
元数据
常见问题
Gym 是什么？
Log workouts, plan routines, track progress, and get intelligent coaching for any fitness level. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 829 次。
如何安装 Gym？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install gym」即可一键安装，无需额外配置。
Gym 是免费的吗？
是的，Gym 完全免费（开源免费），可自由下载、安装和使用。
Gym 支持哪些平台？
Gym 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 Gym？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.1。
推荐 Skills