Qwen Edit
digitalsamba/claude-code-video-toolkit
AI image editing prompting patterns for Qwen-Image-Edit. An agent skill from digitalsamba/claude-code-video-toolkit.
Final Cut Pro X (FCPX) assistant — auto video production, TTS voiceover, media management, batch export | AI 自动成片、TTS 配音、素材管理、批量导出.
Install Fcpx Assistant
$ npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fcpx-assistant --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fcpx-assistant .claude/skills/fcpx-assistant && rm -rf skills-srcUse ~/.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/
Install the "fcpx-assistant" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistant into .claude/skills/fcpx-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fcpx-assistant", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistantType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fcpx-assistant --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/fcpx-assistant .agents/skills/fcpx-assistant && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fcpx-assistant" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistant into .agents/skills/fcpx-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fcpx-assistant", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fcpx-assistant --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/fcpx-assistant .cursor/skills/fcpx-assistant && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fcpx-assistant" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistant into .cursor/skills/fcpx-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fcpx-assistant", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/fcpx-assistant--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fcpx-assistant --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/fcpx-assistant .gemini/skills/fcpx-assistant && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fcpx-assistant" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistant into .gemini/skills/fcpx-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fcpx-assistant", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills fcpx-assistantInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/fcpx-assistant .github/skills/fcpx-assistant && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fcpx-assistant" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistant into .github/skills/fcpx-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fcpx-assistant", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fcpx-assistant --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/fcpx-assistant .opencode/skills/fcpx-assistant && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fcpx-assistant" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fcpx-assistant into .opencode/skills/fcpx-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fcpx-assistant", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
fcpx-assistant- GitHub stars
- 2.2k
- Token cost
- ~3.3k tokens
- SKILL.md length
- 746 words
- Files
- 20 (incl. scripts)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
Final Cut Pro X (FCPX) assistant — auto video production, TTS voiceover, media management, batch export | AI 自动成片、TTS 配音、素材管理、批量导出.
- Works in 5 steps: 克隆项目 → 安装依赖 → 下载模型 → …
- Tasks that involve Text to speech and voice
- SKILL.md covers 🔥 Core Feature: One-Click…, 📂 FCP Project Management, ✂️ Editing Assistance and 🔊 Audio Processing, plus 5 more sections
- Runs Shell scripts from its folder; calls bash, osascript and brew; reaches github.com; needs PEXELS_API_KEY
What it does
Fcpx Assistant is an agent skill from LeoYeAI/openclaw-master-skills. Final Cut Pro X (FCPX) assistant — auto video production, TTS voiceover, media management, batch export | AI 自动成片、TTS 配音、素材管理、批量导出. Triggers: FCPX, FCP, Final Cut, make video, auto video, voiceover, import media, export
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including scripts (for example `AUTO_PUBLISH_README.md`, `GUIDE.md` and `README.md`).
It sits in Media & Creative, covering Text to speech and voice and Video production. It works with Qwen. 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
- Tasks that involve Video production
Example prompts
- “/fcpx-assistant”
Requirements
- Python 3
- A Bash shell
- A credential in PEXELS_API_KEY
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 克隆项目
- 安装依赖
- 下载模型
- 启动服务
- 验证服务
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 14 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
bashosascriptbrewpip3python3gitcurl
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:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
PEXELS_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Fcpx Assistant loads about 3.3k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 746 words of instructions outside code blocks.
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). 746 words, ~3,289 tokens.
Download SKILL.mdSave it as
.claude/skills/fcpx-assistant/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.- name
- fcpx-assistant
- description
- Final Cut Pro X (FCPX) assistant — auto video production, TTS voiceover, media management, batch export | AI 自动成片、TTS 配音、素材管理、批量导出. Triggers: FCPX, FCP, Final Cut, make video, auto video, voiceover, import media, export
- author
- Steve & Steven
- version
- 2.0.0
Final Cut Pro Assistant
A fully automated video production pipeline — from topic to published video. Also your everyday FCP editing assistant.
🔥 Core Feature: One-Click Video Production
From topic to published video — fully automated.
Full Workflow
Topic 💡 → AI Script 📝 → Fetch Media 🔍 → TTS Voiceover 🎤 → Auto Assemble 🎞️ → Auto Publish 🚀🚀 Quick Start: One Command
# Generate and publish to Bilibili
bash scripts/auto-video-from-topic.sh \
--topic "如何制作一杯完美的咖啡" \
--publish bilibili \
--title "咖啡教程" \
--tags "咖啡，教程"📝 Step 1: AI Script Generation
Auto-generate video script from topic using AI.
bash scripts/ai-script-generator.sh \
--topic "如何制作一杯完美的咖啡" \
--style 教程 \
--duration 90 \
--keywordsFeatures:
- AI-powered script generation
- Platform-specific optimization (TikTok, YouTube, Bilibili)
- Style presets: vlog, 科普，教程，带货，故事
- Auto-generate material search keywords
- Output includes storyboard + TTS-ready text
🔍 Step 2: Fetch Video Assets
Auto-search and download free stock footage from Pexels by keywords.
bash scripts/media-collector.sh \
--keywords "nature ocean sunset" \
--count 5 --output ./my-project- Multi-keyword search (searches each word separately, then merges)
- Orientation (landscape/portrait/square), quality (SD/HD/4K), duration filtering
- Saves metadata and license info automatically
- Set
PEXELS_API_KEYfor expanded search
🎵 Step 3: Add Background Music
Drop your BGM files (mp3/wav/m4a) into the project's music/ folder. The assembler auto-detects them.
my-project/
├── videos/ ← Stock footage (auto-filled by Step 2)
├── music/ ← Your BGM goes here
└── meta/ ← Metadata (auto-generated)🎤 Step 4: TTS Voiceover
Generate per-paragraph voiceover using Qwen TTS.
bash scripts/tts-voiceover.sh \
--script "First paragraph
Second paragraph
Third paragraph" \
--output ./my-project/voiceover- Per-paragraph generation with automatic silence trimming
- Customizable voice via
--instruct(e.g., "warm female voice, moderate pace") - Also reads from file:
--script-file ./script.txt - Requires Qwen TTS WebUI running at
localhost:7860
🎞️ Step 5: Auto Assemble
Combines footage, voiceover, subtitles, and BGM into a finished video.
bash scripts/auto-video-maker.sh \
--project ./my-project \
--script-file ./script.txt \
--voiceover ./my-project/voiceover \
--style vlog \
--output final.mp4Smart Features:
- 📝 Script split by paragraph, each mapped to a video clip
- 🎤 Clip duration auto-syncs to voiceover timing when available
- 📝 Burn-in subtitles with PingFang SC font (position/size adjustable)
- 🎵 Smart audio mixing — voiceover + BGM (BGM auto-ducked to 15%)
- 🎬 Fade transitions between clips
- 📐 Uniform resolution (default 1920x1080, supports portrait 1080x1920)
Style Presets:
| Style | Pacing | Font Size | Transition | Best For |
|---|---|---|---|---|
default | Medium | 42 | 0.5s | General |
vlog | Upbeat | 38 | 0.3s | Daily vlogs |
cinematic | Slow | 48 | 1.0s | Scenic/story |
fast | Rapid | 36 | 0.2s | Shorts/TikTok |
More Options:
--resolution 1080x1920 # Portrait mode
--no-subtitle # No subtitles
--subtitle-pos center # Center subtitles (default: bottom)
--font-size 50 # Custom font size
--music ./specific.mp3 # Specify BGM file
--transition none # No transitions🚀 Step 6: Auto Publish
Upload finished video to platforms (Bilibili, YouTube, TikTok, Xiaohongshu).
bash scripts/auto-publish.sh \
--video final.mp4 \
--platform bilibili \
--title "我的视频" \
--tags "vlog，日常" \
--description "视频描述"Supported Platforms:
bilibili- B 站 (requiresbiliupor web upload)youtube- YouTube (requires Google API setup)tiktok- 抖音 (requires cookie auth)xiaohongshu- 小红书 (requires cookie auth)
Configure Accounts:
bash scripts/auto-publish.sh --configCreates config files in ~/.fcpx-assistant/publish/
📂 FCP Project Management
Automate everyday Final Cut Pro tasks.
osascript scripts/check-fcp.scpt # Check FCP status
osascript scripts/list-projects.scpt # List all projects
osascript scripts/open-project.scpt "Name" # Open a project
osascript scripts/import-temp-media.scpt # Import temp media
osascript scripts/project-time-tracking.scpt # Time tracking✂️ Editing Assistance
bash scripts/scene-detect.sh video.mp4 # Scene detection
bash scripts/auto-rough-cut.sh video.mp4 # Auto rough cut (silence removal)
bash scripts/smart-tagger.sh ./media/ # AI smart tagging
bash scripts/auto-chapter-marker.sh video.mp4 # Auto chapter markers🔊 Audio Processing
bash scripts/audio-normalizer.sh video.mp4 # Normalize to -23 LUFS
bash scripts/auto-voiceover.sh "text" out.wav # Single-file voiceover🌍 Subtitles
bash scripts/multi-lang-subtitles.sh video.mp4 en # Multi-language (en/ja/ko/fr/de/es)🖼️ Other Tools
bash scripts/auto-thumbnail.sh video.mp4 ./thumbs # Keyframe thumbnails + contact sheet
osascript scripts/create-script.scpt "Title" "Content" # Create script in Notes
osascript scripts/list-scripts.scpt # List scriptsRequirements
必需依赖
| 工具 | 用途 | 安装方式 |
|---|---|---|
ffmpeg | 视频剪辑、转场、字幕烧入 | brew install homebrew-ffmpeg/ffmpeg/ffmpeg |
osascript | FCPX AppleScript 控制 | macOS 自带 |
curl | API 调用 | macOS 自带 |
jq | JSON 处理 | brew install jq |
bash | 脚本运行 | macOS 自带 |
可选依赖
| 工具 | 用途 | 安装方式 |
|---|---|---|
biliup | B 站视频上传 | pip3 install --break-system-packages biliup |
trash | 安全删除文件 | brew install trash |
外部服务
| 服务 | 用途 | 配置方式 |
|---|---|---|
| Qwen TTS WebUI | 文字转语音配音 | 本地部署，运行在 localhost:7860 |
| Pexels API | 免费视频素材搜索 | 无需 API key（可选设置 PEXELS_API_KEY 提高限额） |
| B 站账号 | 视频上传发布 | 运行 biliup login 扫码登录 |
🔧 Qwen TTS WebUI 部署指南
本技能的 TTS 配音功能依赖 Qwen TTS WebUI，这是一个本地部署的语音合成服务。
部署步骤
- 克隆项目
git clone https://github.com/your-org/qwen-tts-webui.git
cd qwen-tts-webui- 安装依赖
pip3 install -r requirements.txt- 下载模型
# 下载 Qwen3-TTS 模型
python3 scripts/download_model.py --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice- 启动服务
python3 app.py --port 7860- 验证服务
curl http://localhost:7860/gradio_api/info配置说明
在 tts-voiceover.sh 中修改以下参数（如果需要）：
TTS_HOST="http://127.0.0.1:7860" # TTS 服务地址
INSTRUCT="活泼开朗的年轻男声，语调轻快有活力" # 默认声音特征
MODEL="Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice" # 模型名称资源需求
- 内存: 至少 8GB（推荐 16GB+）
- GPU: 可选（有 GPU 时生成速度更快）
- 磁盘: 约 5GB（模型文件）
Show full SKILL.md (310 more words)Show less
替代方案
如果不想部署 Qwen TTS，可以：
- 使用其他 TTS 服务（修改
tts-voiceover.sh中的 API 调用） - 使用本地录音文件代替 TTS 配音
- 跳过配音步骤，仅生成字幕视频
From script to screen — let AI make your videos! 🎬
中文版
Final Cut Pro 助手
从主题到发布的全自动视频生产线，同时也是你的 FCP 剪辑助手。
🔥 核心能力：一键视频生产
从主题到发布，全自动完成。
完整工作流
主题 💡 → AI 文案 📝 → 搜素材 🔍 → TTS 配音 🎤 → 自动成片 🎞️ → 自动发布 🚀🚀 快速开始：一条命令
# 生成并发布到 B 站
bash scripts/auto-video-from-topic.sh \
--topic "如何制作一杯完美的咖啡" \
--publish bilibili \
--title "咖啡教程" \
--tags "咖啡，教程"📝 Step 1: AI 文案生成
根据主题自动生成视频脚本。
bash scripts/ai-script-generator.sh \
--topic "如何制作一杯完美的咖啡" \
--style 教程 \
--duration 90 \
--keywords功能:
- AI 自动生成文案
- 平台优化（抖音、YouTube、B 站）
- 风格预设：vlog, 科普，教程，带货，故事
- 自动生成素材搜索关键词
- 输出包含分镜脚本 + TTS 配音文本
🔍 Step 2: 搜集视频素材
从 Pexels 免费素材库自动搜索下载，按关键词匹配。
bash scripts/media-collector.sh \
--keywords "nature ocean sunset" \
--count 5 --output ./my-project- 多关键词自动逐词搜索
- 支持方向（横屏/竖屏）、质量（SD/HD/4K）、时长范围筛选
- 自动保存素材元数据和版权信息
- 设置
PEXELS_API_KEY解锁更多搜索能力
🎵 Step 3: 准备背景音乐
把你找的 BGM 放到项目的 music/ 目录即可，成片时自动检测。
my-project/
├── videos/ ← 素材（Step 2 自动填充）
├── music/ ← 你的 BGM 放这里（mp3/wav/m4a）
└── meta/ ← 元数据（自动生成）🎤 Step 4: TTS 配音
用 Qwen TTS 为每段文案生成配音。
bash scripts/tts-voiceover.sh \
--script "第一段文案
第二段文案
第三段文案" \
--output ./my-project/voiceover- 逐段生成，自动修剪首尾静音
- 声音特征可自定义（
--instruct） - 也支持从文件读取：
--script-file ./script.txt - 需要 Qwen TTS WebUI 运行在
localhost:7860
🎞️ Step 5: 自动成片
把素材、配音、字幕、BGM 全部组装成完整视频。
bash scripts/auto-video-maker.sh \
--project ./my-project \
--script-file ./script.txt \
--voiceover ./my-project/voiceover \
--style vlog \
--output final.mp4智能特性：
- 📝 文案按段落拆分，每段对应一个视频片段
- 🎤 有配音时，片段时长自动匹配配音节奏
- 📝 PingFang SC 简体中文字幕烧入（位置/大小可调）
- 🎵 配音 + BGM 智能混合（BGM 自动降低到 15% 音量）
- 🎬 fade 转场效果
- 📐 统一分辨率（默认 1920x1080，支持竖屏 1080x1920）
风格预设：
| 风格 | 节奏 | 字号 | 转场 | 适合 |
|---|---|---|---|---|
default | 中等 | 42 | 0.5s | 通用 |
vlog | 轻快 | 38 | 0.3s | 日常 Vlog |
cinematic | 缓慢 | 48 | 1.0s | 电影感 |
fast | 快速 | 36 | 0.2s | 短视频/抖音 |
🚀 Step 6: 自动发布
将成品视频上传到各大平台（B 站、YouTube、抖音、小红书）。
bash scripts/auto-publish.sh \
--video final.mp4 \
--platform bilibili \
--title "我的视频" \
--tags "vlog，日常" \
--description "视频描述"支持平台:
bilibili- B 站（需要biliup或网页上传）youtube- YouTube（需要 Google API 配置）tiktok- 抖音（需要 cookie 认证）xiaohongshu- 小红书（需要 cookie 认证）
配置账号:
bash scripts/auto-publish.sh --config在 ~/.fcpx-assistant/publish/ 创建配置文件
📂 FCP 项目管理
osascript scripts/check-fcp.scpt # 检查 FCP 状态
osascript scripts/list-projects.scpt # 列出所有项目
osascript scripts/open-project.scpt "名称" # 打开项目
osascript scripts/import-temp-media.scpt # 导入临时素材
osascript scripts/project-time-tracking.scpt # 时间追踪✂️ 剪辑辅助
bash scripts/scene-detect.sh video.mp4 # 场景分析
bash scripts/auto-rough-cut.sh video.mp4 # 自动粗剪
bash scripts/smart-tagger.sh ./media/ # 智能标签
bash scripts/auto-chapter-marker.sh video.mp4 # 自动章节标记🔊 音频处理
bash scripts/audio-normalizer.sh video.mp4 # 音频标准化 (-23 LUFS)
bash scripts/auto-voiceover.sh "文本" out.wav # 单文件配音🌍 字幕
bash scripts/multi-lang-subtitles.sh video.mp4 en # 多语言字幕🖼️ 其他工具
bash scripts/auto-thumbnail.sh video.mp4 ./thumbs # 自动缩略图
osascript scripts/create-script.scpt "标题" "内容" # 创建文案
osascript scripts/list-scripts.scpt # 列出文案依赖
必需依赖
| 工具 | 用途 | 安装方式 |
|---|---|---|
ffmpeg | 视频剪辑、转场、字幕烧入 | brew install homebrew-ffmpeg/ffmpeg/ffmpeg |
osascript | FCPX AppleScript 控制 | macOS 自带 |
curl | API 调用 | macOS 自带 |
jq | JSON 处理 | brew install jq |
bash | 脚本运行 | macOS 自带 |
可选依赖
| 工具 | 用途 | 安装方式 |
|---|---|---|
biliup | B 站视频上传 | pip3 install --break-system-packages biliup |
trash | 安全删除文件 | brew install trash |
外部服务
| 服务 | 用途 | 配置方式 |
|---|---|---|
| Qwen TTS WebUI | 文字转语音配音 | 本地部署，运行在 localhost:7860 |
| Pexels API | 免费视频素材搜索 | 无需 API key（可选设置 PEXELS_API_KEY 提高限额） |
| B 站账号 | 视频上传发布 | 运行 biliup login 扫码登录 |
🔧 Qwen TTS WebUI 部署指南
本技能的 TTS 配音功能依赖 Qwen TTS WebUI，这是一个本地部署的语音合成服务。
部署步骤
- 克隆项目
git clone https://github.com/your-org/qwen-tts-webui.git
cd qwen-tts-webui- 安装依赖
pip3 install -r requirements.txt- 下载模型
# 下载 Qwen3-TTS 模型
python3 scripts/download_model.py --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice- 启动服务
python3 app.py --port 7860- 验证服务
curl http://localhost:7860/gradio_api/info配置说明
在 tts-voiceover.sh 中修改以下参数（如果需要）：
TTS_HOST="http://127.0.0.1:7860" # TTS 服务地址
INSTRUCT="活泼开朗的年轻男声，语调轻快有活力" # 默认声音特征
MODEL="Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice" # 模型名称资源需求
- 内存: 至少 8GB（推荐 16GB+）
- GPU: 可选（有 GPU 时生成速度更快）
- 磁盘: 约 5GB（模型文件）
替代方案
如果不想部署 Qwen TTS，可以：
- 使用其他 TTS 服务（修改
tts-voiceover.sh中的 API 调用） - 使用本地录音文件代替 TTS 配音
- 跳过配音步骤，仅生成字幕视频
从文案到成片，让 AI 帮你做视频！🎬
Made by Steve & Steven 🤝
© 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 19 other files (scripts) in skills/fcpx-assistant of LeoYeAI/openclaw-master-skills.
- SKILL.md
- AUTO_PUBLISH_README.md
- GUIDE.md
- README.md
- _meta.json
- package.json
- scripts/ai-script-generator.sh
- scripts/audio-normalizer.sh
- scripts/auto-chapter-marker.sh
- scripts/auto-publish.sh
- scripts/auto-rough-cut.sh
- scripts/auto-thumbnail.sh
- scripts/auto-video-from-topic.sh
- scripts/auto-video-maker.sh
- scripts/auto-voiceover.sh
- scripts/media-collector.sh
- scripts/multi-lang-subtitles.sh
- scripts/scene-detect.sh
- scripts/smart-tagger.sh
- scripts/tts-voiceover.sh
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Fcpx Assistant 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fcpx Assistant this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Qwen Editdigitalsamba/claude-code-video-toolkit | 2.2k | — | ~711 | Automated safety check: Pass | MIT | |
| Runpoddigitalsamba/claude-code-video-toolkit | 2.2k | — | ~2.1k | Automated safety check: Notes | MIT | |
| DaVinci AutoEdit Agentliuluhaixiu/DaVinci-AutoEdit-Agent | 484 | — | ~2.8k | Automated safety check: Notes | MIT | |
| Ergo Remotion Videoitwanger/toBeBetterJavaer | 18k | — | ~1.1k | Automated safety check: Pass | None | |
| Agent Video PipelineJayceHuang/agent-video-pipeline | 105 | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Runpod
digitalsamba/claude-code-video-toolkit
Cloud GPU processing via RunPod serverless. An agent skill from digitalsamba/claude-code-video-toolkit.
DaVinci AutoEdit Agent
liuluhaixiu/DaVinci-AutoEdit-Agent
Guides an approval-gated video editing pipeline from raw footage to an audited DaVinci Resolve timeline, with scripting, optional TTS and a blueprint at each stage.
Ergo Remotion Video
itwanger/toBeBetterJavaer
把口播稿做成二哥风格的 Remotion 视频，包括整理视频用稿、火山 TTS 配音、音画对齐、逐章动画预览和导出带配音的 MP4。用户说“做视频”“口播稿转视频”“Remotion”“继续做下一章”“出片”“渲染”“改读音”“配音读错了”，或给出 docs/src/ai/video/ 下的稿子要做成视频时使用。共享工具、配置和素材在…
Agent Video Pipeline
JayceHuang/agent-video-pipeline
Orchestrate a configurable, debuggable local pipeline from approved narration packages to timed audio, captions, visual assets, semantic motion, rendered video, optional avatar compositing…
Paper Collage Explainer Generator
tl2012tl/comfyUI-llama-TE
For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics.
More from LeoYeAI/openclaw-master-skills
All 1,235 skills in this repoDevOps 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.
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.
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.
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.
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.
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.
Related
Works with
Categories
Questions about Fcpx Assistant
What does Fcpx Assistant do?
Final Cut Pro X (FCPX) assistant — auto video production, TTS voiceover, media management, batch export | AI 自动成片、TTS 配音、素材管理、批量导出. Fcpx Assistant is an agent skill from LeoYeAI/openclaw-master-skills. Final Cut Pro X (FCPX) assistant — auto video production, TTS voiceover, media management, batch export | AI 自动成片、TTS 配音、素材管理、批量导出.
When should I use Fcpx Assistant?
Fcpx Assistant fits situations like: tasks that involve Text to speech and voice; tasks that involve Video production.
How do I install Fcpx Assistant in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a claude-code`. Or copy the skill folder (skills/fcpx-assistant in LeoYeAI/openclaw-master-skills) into .claude/skills/fcpx-assistant in your project. Claude Code loads it when a task matches its description.
How do I install Fcpx Assistant in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill fcpx-assistant -a codex`. Or copy the skill folder (skills/fcpx-assistant in LeoYeAI/openclaw-master-skills) into .agents/skills/fcpx-assistant in your project. Codex loads it when a task matches its description.
Can I use Fcpx Assistant 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 fcpx-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fcpx-assistant, .gemini/skills/fcpx-assistant, .github/skills/fcpx-assistant and .opencode/skills/fcpx-assistant in your project.
What does Fcpx Assistant need to run?
Going by SKILL.md and its folder, Fcpx Assistant needs a shell for the scripts in its folder, the command-line tools its instructions call (bash, osascript, brew, pip3, python3 and git) and credentials named PEXELS_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in PEXELS_API_KEY.
Does Fcpx Assistant access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Fcpx Assistant 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 Fcpx Assistant use?
Fcpx Assistant 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 Fcpx Assistant use?
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Fcpx Assistant?
Skills that share tags, products or a category with Fcpx Assistant: Qwen Edit (digitalsamba/claude-code-video-toolkit, 2.2k stars), Runpod (digitalsamba/claude-code-video-toolkit, 2.2k stars), DaVinci AutoEdit Agent (liuluhaixiu/DaVinci-AutoEdit-Agent, 484 stars) and Ergo Remotion Video (itwanger/toBeBetterJavaer, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fcpx Assistant?
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.