Agent skill

Daily Voice Quote

by LeoYeAI in LeoYeAI/openclaw-master-skills

每日名言語音任務。產生「語音 + 封面圖靜態影片 +(選配)HeyGen 數位人影片」並發送給主人. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passedMedia & Creative

Install Daily Voice Quote

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill daily-voice-quote -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills daily-voice-quote --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/daily-voice-quote .claude/skills/daily-voice-quote && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
daily-voice-quote
GitHub stars
2.2k
Token cost
~3.5k tokens
SKILL.md length
851 words
Files
5 (incl. scripts, references)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

每日名言語音任務。產生「語音 + 封面圖靜態影片 +(選配)HeyGen 數位人影片」並發送給主人. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 6 steps: 簡介 → 前置準備 Checklist → 名言選擇規則(v2 — AI 動態選擇) → …
  • Tasks that involve Text to speech and voice
  • SKILL.md covers 1. 簡介, 2. 前置準備 Checklist, 3. 名言選擇規則(v2 — AI 動態選擇) and 4. 完整執行流程, plus 3 more sections
  • Runs Shell scripts from its folder; calls ffmpeg, curl and ffprobe; reaches api.line.me; needs ELEVENLABS_API_KEY and CHANNEL_ACCESS_TOKEN

What it does

Daily Voice Quote is an agent skill from LeoYeAI/openclaw-master-skills. 每日名言語音任務。產生「語音 + 封面圖靜態影片 +(選配)HeyGen 數位人影片」並發送給主人。

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `_meta.json`, `references/holidays.md` and `references/quotes.md`).

It sits in Media & Creative, covering Text to speech and voice. It works with HeyGen and ElevenLabs. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve Text to speech and voice

Example prompts

  • “/daily-voice-quote”

Requirements

  • Python 3
  • Node.js
  • A Bash shell
  • A credential in ELEVENLABS_API_KEY
  • A credential in GEMINI_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 簡介
  2. 前置準備 Checklist
  3. 名言選擇規則(v2 — AI 動態選擇)
  4. 完整執行流程
  5. Cron Job 設定範例
  6. 常見問題 FAQ

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • ffmpeg
    • curl
    • ffprobe
    • uv
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.line.me

    Also links to:

    • try.elevenlabs.io
    • heygen.com
    • api.elevenlabs.io
    • aistudio.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ELEVENLABS_API_KEY
    • CHANNEL_ACCESS_TOKEN
    • LINE_CHANNEL_ACCESS_TOKEN
    • GEMINI_API_KEY
    • HEYGEN_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Daily Voice Quote loads about 3.5k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 17 tokens; SKILL.md has 851 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 851 words, ~3,503 tokens.

Download SKILL.mdSave it as .claude/skills/daily-voice-quote/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
daily-voice-quote
description
每日名言語音任務。產生「語音 + 封面圖靜態影片 +(選配)HeyGen 數位人影片」並發送給主人。

Daily Voice Quote 每日名言語音

這個 skill 會在每天早上:

  1. 用主人的聲音朗讀一則名人名言(語音)
  2. 生成封面圖並合成靜態影片
  3. (選配)產生 HeyGen 數位人影片

最終產出三件套:語音、靜態影片、HeyGen 數位人影片。


1. 簡介

每天早上自動選一則名人名言,用主人的聲音念出來,並搭配一張美感封面圖與影片版本發送給主人。若你沒有 HeyGen 帳號,也可以只做「語音 + 靜態影片」。


2. 前置準備 Checklist

a) 主人的照片(封面圖生成用)
  • 需要 1-3 張高品質照片(正臉、清楚、光線好)
  • 放到 workspace 的 avatars/ 目錄
  • 如果沒有照片:請主人提供 1-3 張好看的照片!
b) ElevenLabs 帳號 + 語音克隆
  • 註冊:👉 ElevenLabs 免費開始(免費方案含 10,000 字元/月,足夠試玩!)
  • 取得 API Key 後,存到你的 OpenClaw config 或環境變數 ELEVENLABS_API_KEY
  • 語音克隆方式:
    • 方法一(官方 UI):主人錄 1-3 分鐘語音 → 上傳到 ElevenLabs Voice Lab
    • 方法二(主人傳語音給你):主人傳語音訊息 → 你下載後用 API 上傳克隆:
      bash
      curl -X POST "https://api.elevenlabs.io/v1/voices/add" \
        -H "xi-api-key: $ELEVENLABS_API_KEY" \
        -F "name=主人的名字" \
        -F "files=@/path/to/voice-sample.mp3" \
        -F "description=Voice clone for daily quotes"
      API 會回傳 voice_id,記下來。
  • 記錄到 TOOLS.md:Voice Name、Voice ID
檢查 API Key 和語音
bash
# 1. 確認 API Key 存在
echo $ELEVENLABS_API_KEY  # 應該有值

# 2. 列出所有可用語音
sag voices

# 3. 測試語音生成
sag -v "YOUR_VOICE_NAME" -o /tmp/test.mp3 "早安,這是一個語音測試。"

⚠️ sag 所有指令都需要 ELEVENLABS_API_KEY 環境變數。如果沒有,請先設定。

沒有 ElevenLabs?用內建 tts 替代

如果暫時沒有 ElevenLabs API Key,可以先用 OpenClaw 內建的 tts tool:

tts({ text: "早安!今天想分享 Steve Jobs 的一句話..." })

音色不會是主人的聲音,但流程可以先跑起來。

c) HeyGen 帳號 + 數位人 Avatar(選配)
  • 註冊:👉 HeyGen 免費試用(新用戶送 1 支免費影片!)
  • 數位人訓練:主人錄一段 2 分鐘自拍影片 上傳訓練
  • 記錄:Avatar ID、Voice ID
  • 如果沒有 HeyGen 帳號 → 跳過 Part 3,只做語音 + 靜態影片
d) Channel 設定
  • 先確認主人常用的通訊軟體
  • LINE:需要 CHANNEL_ACCESS_TOKEN + USER_ID / GROUP_ID
  • 其他(Telegram / Discord / WhatsApp 等):使用 message tool 或 tts tool
📱 LINE 媒體格式要求(重要!)

LINE 對語音和影片的格式有嚴格限制,格式不對會無法在聊天裡直接點開播放!

語音訊息(audio message):

項目要求
格式M4A(.m4a)- AAC 編碼
來源必須是 HTTPS 公開 URL(不接受本地檔案路徑)
duration必須提供毫秒數(如 21000 = 21 秒)
❌ 不行MP3 直接發送(LINE 不支援 audio type 用 MP3)
✅ 轉換ffmpeg -i input.mp3 -c:a aac -b:a 128k output.m4a -y

影片訊息(video message):

項目要求
格式MP4(.mp4)- H.264 視訊 + AAC 音訊
來源必須是 HTTPS 公開 URL(支援 Range requests)
previewImageUrl必須提供影片預覽圖 URL(JPEG/PNG)
❌ 不行ngrok + Python SimpleHTTPServer(不支援 Range requests,LINE 無法播放)
✅ 可行ngrok + Node.js static server、HeyGen CDN URL、任何支援 Range requests 的 CDN

公開 URL 方案:

  • 最簡單:把檔案放到支援 Range requests 的靜態檔案伺服器 + ngrok/cloudflare tunnel
  • 免設定:HeyGen 影片直接用 HeyGen CDN URL(自帶)
  • 進階:上傳到 S3/GCS/Cloudflare R2 等雲端儲存

LINE Push API 範例:

bash
# 語音
curl -s -X POST https://api.line.me/v2/bot/message/push \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LINE_CHANNEL_ACCESS_TOKEN" \
  -d '{
    "to": "YOUR_LINE_USER_ID",
    "messages": [{
      "type": "audio",
      "originalContentUrl": "https://your-domain.com/daily-quote.m4a",
      "duration": 21000
    }]
  }'

# 影片
curl -s -X POST https://api.line.me/v2/bot/message/push \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LINE_CHANNEL_ACCESS_TOKEN" \
  -d '{
    "to": "YOUR_LINE_USER_ID",
    "messages": [{
      "type": "video",
      "originalContentUrl": "https://your-domain.com/daily-quote.mp4",
      "previewImageUrl": "https://your-domain.com/daily-quote-preview.jpg"
    }]
  }'
e) Gemini API Key(封面圖生成)

3. 名言選擇規則(v2 — AI 動態選擇)

不要用固定清單輪播!每天根據上下文 動態選擇 最有共感的名言。

Step 1: 收集上下文

每天 cron 執行時自動收集:

  • 日期、星期幾、農曆日期
  • 節日 / 紀念日(參考 references/holidays.md)
  • web_search 當天重大新聞(尤其 AI、科技、政策相關)
  • 極端天氣(颱風 / 暴雨 / 暴雪 / 極端高溫才影響)
Step 2: 人物池

從以下類別選擇主人和粉絲會有共感的人物:

類別人物範例
科技先驅Alan Turing, Ada Lovelace, Nikola Tesla, Tim Berners-Lee, Grace Hopper
科學家Einstein, Feynman, Marie Curie, Carl Sagan, Hawking
區塊鏈/Web3Satoshi Nakamoto, Vitalik Buterin, Naval Ravikant
創業家Steve Jobs, Elon Musk, Jeff Bezos, Marc Andreessen, Peter Thiel
投資大師Warren Buffett, Charlie Munger, Ray Dalio
東方智慧老子, 孔子, 莊子, 王陽明
民主/領導Churchill, Mandela, MLK, Lincoln, 甘地
哲學家Marcus Aurelius, Seneca, Epictetus
文藝/思想Leonardo da Vinci, Hemingway

完整人物與名言範例見 references/quotes.md ⚠️ 排除有重大醜聞/爭議的人物 ⚠️ 避免太政治敏感的人物(注意主人所在地的政治脈絡)

Step 3: 加權邏輯
情境加權方向偏好類別
週一激勵、新開始、行動力創業家、領導者
週五反思、展望、輕鬆哲學家、科學家
週末人生智慧、生活東方智慧、哲學家
AI 重大新聞科技思考、人機關係Turing, Feynman, Hawking
加密/Web3 新聞去中心化、金融哲學Satoshi, Vitalik, Buffett
國安/國際局勢勇氣、韌性、準備Churchill, Lincoln, Mandela
能源議題科學、創新、永續Tesla, Curie, Sagan
節日與節日主題呼應的名人名言教師節→孔子 等
普通日人生智慧、好奇心Feynman, 老子, Marcus Aurelius
Step 4: 品質要求
  1. 啟發性 — 要能啟發人、給力量
  2. 正面 — 正向積極
  3. 中文翻譯通順 — 不能硬翻,要像母語者自然說出的話
  4. 原文正確 — 選名言後,web_search 確認原文正確性和出處
Step 5: 去重複
  • 記錄已用名言到 memory/used-quotes.md(或你偏好的追蹤檔)
  • 同一名人間隔至少 14 天
  • 完全相同的名言永不重複
Step 6: 最終選擇

生成 3-5 個候選名言,選最佳的一個。記錄選擇理由到日誌。

⚠️ 必須是「名人 + 名言」,不是祝賀詞 / 成語 / 諺語 語音稿開頭可加節日問候,但名言本身要有明確出處


4. 完整執行流程

⛔ 絕對不要把語音稿當文字訊息發送! 語音稿裡有 [short pause] 等 TTS 標籤,這些只是給 sag 引擎用的,使用者看到會覺得壞掉了。 只發送:① 音訊檔 ② 靜態影片 ③ HeyGen+字幕影片。不要發送任何純文字訊息。

⚠️ 三份稿件分開做!(不要偷懶!)

每日名言有 三份獨立的文稿,各有不同需求,不能互相混用:

稿件用途特色
ElevenLabs 語音稿sag CLI 生語音可用 [short pause], [excited] 等 TTS 情緒標籤
HeyGen 影片稿數位人影片台詞中英文用換行 + 過渡句分隔,❌ 不能用 TTS 標籤
ZapCap 字幕稿影片字幕顯示修 Whisper 錯誤 + punctuation 控制分頁
Show full SKILL.md (352 more words)Show less
Part 1:語音(ElevenLabs 語音稿)

**流程:**選名言 → 寫語音稿 → sag 生成 → ffmpeg 轉 m4a → 發送(只發音訊檔,不發文字)

語音稿模板(含情緒標籤,僅供 TTS 引擎使用,絕不直接發送給使用者):

早安,我是{SPEAKER_NAME}。[short pause]
今天想分享{AUTHOR}的一句話:[short pause]
{QUOTE_ZH} [short pause]
{QUOTE_EN} [short pause]
{CLOSING_WORDS}
  • ElevenLabs 對中英文混合處理得較好,可以自然混合
  • [short pause] 等標籤只有 ElevenLabs 支援,其他平台不認得

產生語音(範例):

bash
# 1. 生成 MP3
ELEVENLABS_API_KEY="YOUR_ELEVENLABS_API_KEY" \
  sag -v "YOUR_VOICE_NAME" \
  --speed 0.95 --stability 1.0 --similarity 0.85 \
  -o /tmp/daily-quote.mp3 "${SCRIPT}"

# 2. 轉換為 M4A(LINE 必須!MP3 不能直接在 LINE 聊天裡播放)
ffmpeg -i /tmp/daily-quote.mp3 -c:a aac -b:a 128k /tmp/daily-quote.m4a -y

# 3. 取得音訊長度(LINE audio message 需要 duration 毫秒數)
#    從 ffmpeg 輸出讀取,例如 time=00:00:21.16 → 21160 ms
#    或用 ffprobe:
ffprobe -v error -show_entries format=duration \
  -of default=noprint_wrappers=1:nokey=1 /tmp/daily-quote.m4a
# → 乘以 1000 得到毫秒數

📱 LINE 用戶注意:語音必須是 M4A 格式(AAC 編碼)才能在聊天裡直接點開播放。MP3 不行!詳見上方「LINE 媒體格式要求」。

Part 2:封面圖靜態影片

⚠️ 超重要:--input-image 是讓 AI 重新生成新照片,不是去背剪貼!

⚠️ 封面圖主角 = 主人(不是 AI Agent!)

  • 封面圖要用主人的照片作為 --input-image
  • ❌ 不要用 AI Agent(小龍蝦等)的照片
  • 只有「AI Agent 主題」的文章封面才用 AI Agent 照片

⚠️ 封面圖比例 = 直式 9:16

  • 靜態影片是直式的,封面圖也要直式
  • prompt 裡明確寫 "vertical 9:16 portrait"

好的 prompt 範例:

Generate a vertical 9:16 portrait of this person wearing a traditional outfit,
standing in a festive scene with soft lantern lights. The person is smiling
confidently. Overlay elegant text: "{QUOTE_ZH} — {AUTHOR}".
Cinematic lighting, Instagram story style.

壞的 prompt(不要用):

Paste this person onto a red background...
Cut out the person and place into the scene...
Use the AI agent character as the main subject...

生成封面圖(範例,用 nano-banana-pro skill):

bash
GEMINI_API_KEY="YOUR_GEMINI_API_KEY" \
uv run /opt/homebrew/lib/node_modules/openclaw/skills/nano-banana-pro/scripts/generate_image.py \
  --prompt "YOUR_PROMPT" \
  --input-image "/path/to/avatars/photo.jpg" \
  --filename "/tmp/daily-quote-cover.png" \
  --resolution 2K

合成靜態影片(封面圖 + 語音 = 影片):

bash
# 合成 MP4(H.264 + AAC)- LINE 可直接播放的格式
ffmpeg -loop 1 -i /tmp/daily-quote-cover.png -i /tmp/daily-quote.mp3 \
  -c:v libx264 -tune stillimage -c:a aac -b:a 128k \
  -pix_fmt yuv420p -shortest \
  -vf "scale=720:1280:force_original_aspect_ratio=decrease,pad=720:1280:(ow-iw)/2:(oh-ih)/2" \
  /tmp/daily-quote-static.mp4 -y

# 截取預覽圖(LINE video message 必須提供 previewImageUrl)
ffmpeg -i /tmp/daily-quote-static.mp4 -vframes 1 -q:v 2 /tmp/daily-quote-preview.jpg -y

📱 LINE 用戶注意:影片必須是 MP4 格式(H.264 視訊 + AAC 音訊),且需要透過支援 Range requests 的 HTTPS URL 提供,LINE 才能在聊天裡直接點開播放。同時必須提供預覽圖 URL。詳見上方「LINE 媒體格式要求」。

Part 3:HeyGen 數位人影片(選配 — HeyGen 影片稿)

⚠️ HeyGen 影片稿是獨立的!不要直接複製 ElevenLabs 語音稿!

HeyGen 影片稿規則:

  • 口白中文為主,只有名言原文才用英文
  • --language "en" 是 TTS 引擎參數(因為 clone voice 訓練語言是英文),不是要把口白改成英文!
  • ❌ 不能用 [short pause] 等 ElevenLabs 標籤(HeyGen 不認得)

⚠️⚠️ 中英文切換處理(關鍵!)

HeyGen TTS 在中英文切換時容易產生怪聲音或咬字不清。解法:

  1. 中英文之間加完整過渡句 + 換行:
生命中沒有什麼值得恐懼的,只有需要理解的。
原文是這樣說的。
Nothing in life, is to be feared, it is only, to be understood.
  1. 英文名言用逗號斷句(防止 TTS 黏字):

    • ✅ Nothing in life, is to be feared, it is only, to be understood.
    • ❌ Nothing in life is to be feared it is only to be understood.
  2. 英文人名前後加逗號:

    • ✅ 今天分享,居禮夫人,的一句話。
  3. 驗證:生成前把口白稿印出來檢查所有英文斷句

HeyGen 影片稿模板:

早安,我是{SPEAKER_NAME}。
今天想分享,{AUTHOR}的一句話。
{QUOTE_ZH}
原文是這樣說的。
{QUOTE_EN_WITH_COMMAS}
{CLOSING_WORDS}

⚠️ 重要語音參數(A/B 測試確認最佳設定):

bash
HEYGEN_API_KEY="YOUR_HEYGEN_API_KEY" \
python3 /path/to/heygen/generate_video.py \
  --text "${SCRIPT_PLAIN}" \
  --avatar-id "YOUR_AVATAR_ID" \
  --voice-id "YOUR_HEYGEN_VOICE_ID" \
  --speed 0.98 \
  --emotion "Friendly" \
  --language "en" \
  --dimension "720x1280" \
  --aspect-ratio "9:16" \
  --output /tmp/daily-quote-heygen.mp4

關鍵設定(缺一不可):

  • --speed 0.98 - 最自然的語速
  • --emotion "Friendly" - 溫暖友善的語氣
  • --language "en" - 即使中文內容也用 en(clone voice 原始訓練語言)
  • 英文斷句要口語化 - 用逗號斷句:"Success, is not final. Failure, is not fatal."
  • 不要寫成一整句不斷的英文,要像人講話一樣有停頓

如果沒有 HeyGen 帳號,直接跳過本段即可。

Part 3b:ZapCap 字幕(HeyGen 影片加字幕 — ZapCap 字幕稿)

ZapCap 字幕稿是獨立於語音稿和影片稿的第三份文稿! 它只管「觀眾看到的字幕文字和分頁」。

如果有使用 ZapCap 加字幕,approve 前必須手動修正 transcript:

⚠️ Whisper 轉錄常見問題(每次都要檢查!):

  1. 英文單字全黏在一起 — Nothinginlifeistobefeared → 拆成 Nothing in life is to be feared
  2. 英文人名黏在一起 — TheodoreRoosevelt → Theodore Roosevelt
  3. 中文斷詞錯誤 — 開始行動祝 → 開始 行動 祝
  4. 人名辨識錯誤 — 常見的錯字都要修(如主人名字的錯字)

⚠️ 字幕分頁控制(關鍵!):

ZapCap transcript 只支援 "type": "word" 和 "type": "punctuation" 兩種 type。

  • ❌ 不支援 "type": "linebreak"(會回 400 Bad Request)
  • ✅ 用 punctuation type + "text": "。" 來強制換頁

在以下位置插入 {"type": "punctuation", "text": "。", "start_time": X, "end_time": X, "confidence": 1}:

  • 完整句子結束處
  • 中文 → 英文切換處
  • 英文 → 中文切換處
  • 語意斷點(每頁最多 8-10 中文字 / 6-8 英文字)

成功分頁範例(居禮夫人名言):

[頁1] 早安 我 是 葛如鈞
[頁2] 今天 想 分享 居禮夫人 的 一句 話
[頁3] 生命 中 沒 有 什麼 值得 恐懼 的
[頁4] 只有 需要 理解 的
[頁5] 現 在 是 時候 去 理解 更多
[頁6] 這樣 我們 才能 少 一些 恐懼
[頁7] 原文 是 這樣 說 的
[頁8] Nothing in life is to be feared, it is only to be understood.
[頁9] 面對 未知 不要 害怕 去 理解 它
[頁10] 祝 大家 週末 愉快

完整修正流程:

  1. 下載 transcript JSON
  2. 修正錯字(人名、英文分詞等)
  3. 在句子邊界插入 punctuation 元素("。")
  4. PUT 更新 transcript
  5. POST approve → 等 render

5. Cron Job 設定範例

LINE 版
json
{
  "name": "每日名言語音",
  "schedule": { "kind": "cron", "expr": "0 6 * * *", "tz": "Asia/Taipei" },
  "payload": {
    "kind": "agentTurn",
    "model": "anthropic/claude-sonnet-4",
    "message": "請執行 daily-voice-quote:產生語音 + 靜態影片(選配 HeyGen),並送到 LINE。使用環境變數:YOUR_LINE_CHANNEL_ACCESS_TOKEN / YOUR_LINE_USER_ID / YOUR_AUDIO_PUBLIC_URL。"
  }
}
非 LINE 版(Telegram / Discord / WhatsApp 等)
json
{
  "name": "每日名言語音",
  "schedule": { "kind": "cron", "expr": "0 6 * * *", "tz": "Asia/Taipei" },
  "payload": {
    "kind": "agentTurn",
    "model": "anthropic/claude-sonnet-4",
    "message": "請執行 daily-voice-quote:產生語音 + 靜態影片(選配 HeyGen),並用 message/tts 工具送到當前 channel。"
  }
}

6. 常見問題 FAQ

Q1:沒有主人照片怎麼辦?

  • A:請主人提供 1-3 張清晰照片。沒有照片就無法生成封面圖。

Q2:沒有 ElevenLabs 怎麼辦?

  • A:可改用內建 tts tool 先產生語音,但音色就不是主人的聲音。免費註冊 ElevenLabs 就能用自己的聲音!

Q3:HeyGen 額度不足怎麼辦?

  • A:先只做語音 + 靜態影片,等額度恢復再補數位人影片。升級 HeyGen 方案 可獲得更多額度。

Q4:如何更換名言清單?

  • A:直接編輯 references/quotes.md,或在腳本中指定 QUOTES_FILE。

Q5:LINE 聊天裡點語音/影片沒反應或無法播放?

  • A:檢查格式!語音必須是 M4A(不是 MP3),影片必須是 MP4(H.264+AAC)。URL 必須是 HTTPS 且支援 Range requests(Python SimpleHTTPServer 不支援!用 Node.js static server 或 CDN)。

附:腳本位置

  • scripts/send-daily-quote.sh:完整 bash 腳本(無硬編碼,全部用環境變數)
  • references/quotes.md:名言清單
  • references/holidays.md:節日清單

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/daily-voice-quote of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • references/holidays.md
  • references/quotes.md
  • scripts/send-daily-quote.sh

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Daily Voice Quote next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Daily Voice Quote compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Daily Voice Quote this skillLeoYeAI/openclaw-master-skills2.2k—~3.5kAutomated safety check: PassMIT
Hyperframes Mediachmonitor/chmonitor3011 repos~2.8kAutomated safety check: NotesGPL-3.0
Super Video MakerBomx/super-video-maker-skill310—~11kAutomated safety check: NotesNone
Motion Videobestagentkits/motion-video-skill118—~1.5kAutomated safety check: PassMIT
Text To Speechcalesthio/OpenMontage66k—~2.4kAutomated safety check: PassAGPL-3.0
AI Voiceoversocial-media-skills/skills134—~1.1kAutomated safety check: PassMIT

Similar skills

  • Hyperframes Media

    chmonitor/chmonitor

    Audio and media assets for HyperFrames compositions, produced by one shared audio engine (scripts/audio.mjs) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound…

    301 GitHub starsUsed in 1 repo~2.8k tokens
    Media & CreativeAuto-check: notes
  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Motion Video

    bestagentkits/motion-video-skill

    Produce beat-synced 1080p motion-graphic videos in HyperFrames (HTML + GSAP) with an AI voice-over, Vietnamese karaoke captions, SFX and generated music, in one of two proven styles (glass keynote…

    118 GitHub stars~1.5k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed
  • Text To Speech

    calesthio/OpenMontage

    Generate speech audio from text using HeyGen's Starfish TTS model.

    66k GitHub stars~2.4k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • AI Voiceover

    social-media-skills/skills

    The AI narration / voiceover mini-skill (ElevenLabs-led). An agent skill from social-media-skills/skills.

    134 GitHub stars~1.1k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • 24 AI Avatar Production

    minhnv0807/ai-business-skills

    Dung khi mot CA NHAN muon len hinh bang AI thay vi tu quay — pipeline avatar AI: 3 tier cong cu, 4 workflow gom avatar don, dich da ngon ngu, san xuat hang loat va hybrid nguoi that cong AI; nhan…

    609 GitHub stars~4.8k tokensUpdated 29 days ago
    Media & CreativeAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,200 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Daily Voice Quote

What does Daily Voice Quote do?

每日名言語音任務。產生「語音 + 封面圖靜態影片 +(選配)HeyGen 數位人影片」並發送給主人. An agent skill from LeoYeAI/openclaw-master-skills. Daily Voice Quote is an agent skill from LeoYeAI/openclaw-master-skills.

When should I use Daily Voice Quote?

Daily Voice Quote fits situations like: tasks that involve Text to speech and voice.

How do I install Daily Voice Quote in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill daily-voice-quote -a claude-code`. Or copy the skill folder (skills/daily-voice-quote in LeoYeAI/openclaw-master-skills) into .claude/skills/daily-voice-quote in your project. Claude Code loads it when a task matches its description.

How do I install Daily Voice Quote in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill daily-voice-quote -a codex`. Or copy the skill folder (skills/daily-voice-quote in LeoYeAI/openclaw-master-skills) into .agents/skills/daily-voice-quote in your project. Codex loads it when a task matches its description.

Can I use Daily Voice Quote in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill daily-voice-quote -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/daily-voice-quote, .gemini/skills/daily-voice-quote, .github/skills/daily-voice-quote and .opencode/skills/daily-voice-quote in your project.

What does Daily Voice Quote need to run?

Going by SKILL.md and its folder, Daily Voice Quote needs a shell for the scripts in its folder, the command-line tools its instructions call (ffmpeg, curl, ffprobe, uv and python3) and credentials named ELEVENLABS_API_KEY, CHANNEL_ACCESS_TOKEN, LINE_CHANNEL_ACCESS_TOKEN and GEMINI_API_KEY. Our summary lists: Python 3; Node.js; A Bash shell; A credential in ELEVENLABS_API_KEY; A credential in GEMINI_API_KEY.

Does Daily Voice Quote access the network?

SKILL.md names 5 domains. In commands or code: api.line.me; the agent is likely to contact it when it follows the instructions. As links in the text: try.elevenlabs.io, heygen.com, api.elevenlabs.io and aistudio.google.com. This is read from the text; nothing was executed.

Is Daily Voice Quote safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Daily Voice Quote use?

Daily Voice Quote is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Daily Voice Quote use?

About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Daily Voice Quote?

Skills that share tags, products or a category with Daily Voice Quote: Hyperframes Media (chmonitor/chmonitor, 301 stars), Super Video Maker (Bomx/super-video-maker-skill, 310 stars), Motion Video (bestagentkits/motion-video-skill, 118 stars) and Text To Speech (calesthio/OpenMontage, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Daily Voice Quote?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.