Token导航 LogoToken导航

Agent Skill · 开发

bestyou-coach(最好的你教练)

bestyou-coach 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

bestyou-coach 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 7,030。

总安装 4,116周安装 175GitHub Stars 公开资料未说明下载 1,442核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bestyou-coach(最好的你教练)
来源仓库:https://github.com/kentsteffen/bestyou-coach
安装命令:
openclaw skills install bestyou-coach
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install bestyou-coach

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

将健康数据可视化呈现为仪表板。生成每日简报与每周总结辅助决策。支持膳食分析与行动计划制定。bestyou-coach 属于开发类 Skill,可作为该场景下的辅助能力补充。安装命令:openclaw skills install bestyou-coach。数据展示依赖设备同步频率与准确性。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install bestyou-coach;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

bestyou-coach 怎么安装?

在终端执行 openclaw skills install bestyou-coach。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

bestyou-coach 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

bestyou-coach 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

bestyou-coach 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

bestyou-coach 用的人多吗?

公开数据是累计安装 4,116 次,近一周安装 175 次,下载 1,442 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

bestyou-coach 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
bestyou-coach

最好的你教练 · 本页

4,116—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
bestyou-coach
description
>
homepage
https://bestyou.ai/openclaw-setup
metadata
openclaw
requires
env
primaryEnv
BESTYOU_API_KEY

BestYou Coach Widgets

Render BestYou MCP tool responses as rich visual cards using OpenClaw's canvas.

First-Time Setup

Before calling any tools, check that mcporter is installed and the BestYou server is configured:

mcporter --config ~/.openclaw/workspace/config/mcporter.json list
  • If mcporter is not found: npm install -g mcporter
  • If bestyou is not listed: walk the user through setup. See references/setup.md for the full guide.

Setup summary:

  1. User generates an API key in BestYou iOS (More → Connected Apps → OpenClaw)
  2. Create config/mcporter.json with the key in the Authorization Bearer header (see references/setup.md for the exact JSON format)
  3. Restart the OpenClaw gateway

Calling Tools via mcporter

All tools use this syntax:

mcporter --config config/mcporter.json call bestyou.<tool_name> [param=value ...]

If a custom config path is needed (e.g. calling from outside the workspace), use the full path:

mcporter --config ~/.openclaw/workspace/config/mcporter.json call bestyou.<tool_name> [param=value ...]

Examples:

mcporter call bestyou.get_account_link_status
mcporter call bestyou.get_daily_briefing date=2026-03-15
mcporter call bestyou.get_todays_action_plan date=2026-03-15
mcporter call bestyou.get_progress_snapshot date=2026-03-15
mcporter call bestyou.get_weekly_summary weekEndDate=2026-03-15
mcporter call bestyou.generate_workout type=strength duration=20 equipment=bodyweight experienceLevel=Intermediate goal="General strength"
mcporter call bestyou.analyze_meal_text description="chicken burrito bowl" timestamp=2026-03-15T12:30:00-06:00

If a custom mcporter config path is needed, add --config <path>.

Tool-to-Template Map

MCP ToolTemplateDescription
get_account_link_statusassets/account-status.htmlConnection status, scopes
get_daily_briefingassets/daily-briefing.htmlReadiness, insights, priorities
get_todays_action_planassets/action-plan.htmlTimeline of today's blocks
get_progress_snapshotassets/progress-snapshot.htmlDomain scores, recommendations
get_weekly_summaryassets/weekly-summary.htmlWeekly scores, trends, goals
analyze_meal_textassets/meal-analysis.htmlMacro breakdown, components
generate_workoutassets/workout.htmlExercise cards with images

Rendering Workflow

  1. Call the BestYou MCP tool via mcporter
  2. Read the matching template from assets/
  3. Replace the sample data in the HTML with the actual API response values (see data mapping below)
  4. Inline the CSS: copy the contents of assets/shared.css into a <style> tag in the HTML <head> so the output is self-contained
  5. Present the populated HTML via canvas(action="present") or canvas(action="a2ui_push")
  6. Provide a brief text summary alongside the visual

Design System

All templates use the BestYou Dark Glass design system (assets/shared.css):

  • Background: #0a0a0a, cards: #141414, borders: #1e1e1e
  • Font: Inter (Google Fonts)
  • Color coding: green (#4ade80) = good, yellow (#facc15) = moderate, orange (#fb923c) = warning, red (#f87171) = poor
  • Score thresholds: ≥70 green, 40-69 yellow/orange, <40 red

Handling Missing Data

API responses may contain null or missing fields. Rules:

  • If a score field is null, hide the gauge/bar or show "—" instead of a number
  • If an array is empty or missing, omit that section entirely (don't render empty containers)
  • If totalCalories or calorieGoal is null, omit the calorie summary row
  • Never show "null" or "undefined" in rendered HTML

Data Mapping by Template

Daily Briefing

API response structure (nested):

API PathTemplate ElementNotes
headline.headline text
readinessScore.gauge-value + SVG stroke-dashoffsetFormula: 314 - (314 * score / 100)
dayType.day-type .valueCapitalize, add emoji: recovery=🔄, active=💪, rest=😴
yesterday.highlights[].insight-card blocksPositive insights (icon, title, description)
yesterday.areas[].insight-card blocksNegative/improvement insights, render after highlights
today.priorities[].action-item blocksNumbered, with title and description
today.plans[].plan-tag blocksEmoji, plan name, week/day info
insightCards[]Cross-domain sectionFilter for domain: "multi" entries, render as cross-domain insight cards

Action Plan

API PathTemplate ElementNotes
readiness.score.readiness-score + badge
readiness.dayType.rm-type
blocks[].block-card itemsGroup by timePeriod: morning/afternoon/evening

Block icon mapping by blockType:

  • wakeUp → 😴 (recovery icon bg)
  • breakfast → 🍳 (nutrition icon bg)
  • lunch → 🥗 (nutrition icon bg)
  • snack → 🥤 (nutrition icon bg, or 🥑 for second snack)
  • dinner → 🍽️ (nutrition icon bg)
  • workout / cardio / strength → 🏃 (fitness icon bg)
  • goToBed → 🌙 (recovery icon bg)

Block status: completed → ✅, upcoming or pending → ⬜

Progress Snapshot

API PathTemplate ElementNotes
domains[].domain-card gridEach: name, score, color-coded mini bar
insights[].insight-item cardsWith severity badge (high=red, medium=orange, low=blue)
recommendations[].rec-item cardsWith actionSteps[] as list items
crossDomainPatterns[].cross-domain cardsWith domain badges

Weekly Summary

API PathTemplate ElementNotes
overallScoreGauge SVG + label
domains[].domain-section blocksEach: trend badge (improving/declining/stable), stats, insight
achievements[].achievement cardsEmoji + title + description
nextWeekFocus[].next-week-goal itemsWith priority badge

Meal Analysis

API PathTemplate ElementNotes
mealName.meal-name
calories.meal-cal
protein_g, fat_g, carbs_g, fiber_gMacro bar segments + legendFlex ratios = gram values
components[].component rowsName, amount, calories, per-component macros
insights[].insight-row items.positive or .negative indicator bar
dailyTotals.daily-totals sectionCalories, protein, fat, carbs

Workout

API PathTemplate ElementNotes
sessionNameHeader h1
duration, equipment, levelHeader .meta spans
blocks[].block sectionsPhase badge: warmup=green, main=orange, cooldown=blue

Each exercise within a block:

  • imageUrl → <img> src (CDN: cdn.bestyou.ai)
  • name → h3
  • sets, reps, weight, rpe, rest → .rx-pill spans
  • notes → .exercise-notes
  • targetMuscle, exerciseType → .exercise-cues

Conversation Patterns

Morning check-in

User: "What's my day look like?" or "Morning briefing"

  1. get_account_link_status → verify connected
  2. get_daily_briefing → render briefing widget
  3. get_todays_action_plan → render action plan widget
  4. Summarize: readiness score, day type, top priority

Progress check

User: "How am I doing?" or "Show my progress"

  1. get_progress_snapshot → render snapshot widget
  2. Highlight strongest and weakest domains, top recommendation

Meal logging

User: "I just had [food description]"

  1. analyze_meal_text with the description → render meal widget
  2. Note protein hit vs target, suggest next meal bias

Workout request

User: "Give me a workout" or "[duration] [type] workout"

  1. generate_workout with parameters → render workout widget
  2. Brief summary: duration, focus, number of exercises

Weekly review

User: "Weekly summary" or "How was my week?"

  1. get_weekly_summary → render weekly widget
  2. Highlight trends (improving/declining), top achievement, next week focus

Text Summary Style

Keep text summaries alongside widgets brief and actionable:

  • Lead with the key number (readiness score, calories, overall score)
  • One sentence on what's going well
  • One sentence on the top action item
  • No need to repeat everything the widget shows visually

平台分布

OpenClaw

94.98%
按下载量换算1,370

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills