/ 目錄 / 演練場 / skills
● 社群 aahl ⚡ 即開即用

skills

作者 aahl · aahl/skills

AAHL skill pack — Home Assistant control, TTS (Edge / GLM), DuckDuckGo search, weather, crypto, Lark/Feishu, movie search, price compare.

AAHL Skills is a Chinese-developer-focused skill pack: smart-home control via Home Assistant, TTS through Microsoft Edge and Zhipu GLM-TTS, DuckDuckGo web search, DeepWiki doc retrieval, crypto market data, weather, Lark/Feishu workflows, movie/show search, and shopping price comparison. Practical for daily-life automation and Chinese SaaS stacks.

為什麼要用

核心特性

即時演示

實際使用效果

skills-skill-3.replay ▶ 就緒
0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "skills-skill-3": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/aahl/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "skills-skill-3": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/aahl/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "skills-skill-3": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/aahl/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示,然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "skills-skill-3": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/aahl/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "skills-skill-3",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/aahl/skills",
        "~/.claude/skills/skills"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列,而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "skills-skill-3": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/aahl/skills",
          "~/.claude/skills/skills"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add skills-skill-3 -- git clone https://github.com/aahl/skills ~/.claude/skills/skills

一行命令搞定。用 claude mcp list 驗證,claude mcp remove 移除。

使用場景

實戰用法: skills

How to automate a smart-home routine via Home Assistant

👤 Home Assistant users wanting voice-free automation via Claude ⏱ ~20 min intermediate

何時使用: You want to chain actions (lights + AC + music) with conditional logic.

前置條件
  • Skill installed — git clone https://github.com/aahl/skills ~/.claude/skills/aahl-skills
  • Home Assistant URL + long-lived token — HA user profile → create token; export HA_URL, HA_TOKEN
步驟
  1. List entities
    列出所有与 'living_room' 相关的 Home Assistant entities。✓ 已複製
    → Entity list with current states
  2. Define routine
    我晚上 7 点到家。灯调至 60%、空调打开到 26°C、播放轻音乐。✓ 已複製
    → Sequenced service calls with expected outcome
  3. Execute
    执行这个 routine,按步骤 echo 服务调用后再执行。✓ 已複製
    → Per-step confirmation + resulting state

結果: A working chained automation without hand-writing HA YAML.

注意事項
  • Wrong entity selected (similar names) — Require the skill to confirm entity_id before executing service call

Generate voice notes from markdown

👤 Content creators producing audio versions ⏱ ~10 min beginner

何時使用: You have a blog post and want a quick audio version for WeChat or podcast RSS.

步驟
  1. Pick voice
    用 Edge TTS 的 zh-CN-XiaoxiaoNeural 把 post.md 合成 mp3。✓ 已複製
    → Audio file produced
  2. Upgrade for emotion
    改用 GLM-TTS,声音要更自然有起伏。✓ 已複製
    → Alternate audio with different voice

結果: An audio version of your post ready to publish.

Post a daily digest to Lark/Feishu

👤 Team leads running Lark-based teams ⏱ ~25 min intermediate

何時使用: Each morning you want an automated team digest.

前置條件
  • Lark app with message-send permission — feishu.cn open platform → app → bot → add to group
步驟
  1. Compose
    今天的要闻:天气、加密货币BTC/ETH价格、团队昨日 GitHub PR 摘要。✓ 已複製
    → Composed message
  2. Send
    发送到 '开发组' 群。✓ 已複製
    → Success ack from Lark API

結果: A daily digest landing in Lark without manual copy-paste.

Compare prices before buying

👤 Shoppers on Chinese e-commerce platforms ⏱ ~5 min beginner

何時使用: Before clicking buy on a product across 淘宝/京东/拼多多.

步驟
  1. Query
    比价 'iPhone 15 Pro 256GB' 在主要平台,附链接。✓ 已複製
    → Platform-by-platform price + URL

結果: A price comparison with direct links.

注意事項
  • Cached / stale prices — Skill should fetch live; verify with a click-through

組合

與其他 MCP 搭配,撬動十倍槓桿

skills-skill-3 + github

Pull GitHub PR data then use AAHL skills to post a digest to Lark/Feishu

Use GitHub MCP to list this week's merged PRs in our org, then use AAHL's Lark skill to post a summary to the dev group.✓ 已複製
skills-skill-3 + filesystem

Read a local markdown file and convert it to audio with AAHL's TTS skill

Read ~/blog/latest-post.md, then use AAHL's Edge TTS to generate a Chinese audio version.✓ 已複製

工具

此 MCP 暴露的能力

工具輸入參數何時呼叫成本
Home Assistant control - Smart-home actions HA API (local)
TTS (Edge / GLM) text, voice Voice content Edge free / GLM paid
DuckDuckGo search query Web lookups 0
DeepWiki docs query Reference lookups 0
Crypto + weather symbol or location Daily digests 0
Lark/Feishu messaging group, text Team ops Lark API free
Movie + price search query Daily life 0

成本與限制

運行它的成本

API 配額
Free for most; GLM-TTS and some search APIs bring-your-own-key
每次呼叫 Token 數
Low per tool call
費用
Mostly free
提示
Use Edge TTS (free) unless you need GLM's emotion.

安全

權限、密鑰、影響範圍

憑證儲存: Various: HA_TOKEN, GLM API key, Lark app credentials — all in env
資料出站: Home Assistant (local LAN), Edge TTS (Microsoft), GLM (Zhipu), Lark (Feishu), DuckDuckGo

故障排查

常見錯誤與修復

Home Assistant 401

Token expired or URL wrong (check http vs https, port 8123)

驗證: curl -H "Authorization: Bearer $HA_TOKEN" $HA_URL/api/
Lark send fails

Bot not added to target group, or tenant_access_token expired. Re-issue.

Edge TTS silent on Linux

Install ffmpeg; Edge TTS depends on it for mp3 output

驗證: ffmpeg -version

替代方案

skills 對比其他方案

替代方案何時用它替代權衡
Home Assistant MCPYou want MCP semantics rather than skill promptsDifferent integration shape

更多

資源

📖 閱讀 GitHub 上的官方 README

🐙 查看未解決的 issue

🔍 瀏覽全部 400+ MCP 伺服器和 Skills