qcut

End-to-end QCut CLI workflow for cleaning talking-head and vlog footage, applying restrained portrait filters and skin smoothing, optionally cutting out the speaker and replacing the background, regenerating time-aligned SRT captions after the cuts, and exporting both an editable MP4 plus SRT and a hard-captioned MP4. Use for vlog editing, talking-head cleanup, portrait enhancement, background replacement, 口播剪辑, 剪口播, 去口头词, 去停顿, 人像滤镜, 美颜, 抠像换背景, 自动字幕, 中文字幕, or exporting a captioned social video.

Unified QCut media toolkit — organize project files, process media with FFmpeg, generate AI content, control the QCut editor with native CLI commands, generate video prompts, and test MCP preview. Use when the user asks about any media workflow, file organization, video processing, AI generation, editor control, video prompts, or content pipeline task.

Unified QCut media toolkit — organize project files, process media with FFmpeg, generate AI content, control the QCut editor with native CLI commands, generate video prompts, and test MCP preview. Use when the user asks about any media workflow, file organization, video processing, AI generation, editor control, video prompts, or content pipeline task.

Run QCut's native TypeScript pipeline CLI for AI content generation, video analysis, transcription, YAML pipelines, ViMax agentic video production, and project management. Also use for editor HTTP automation tasks (state snapshots, events, transactions, and notification bridge control) when user needs deterministic state-aware control.

agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如"画只猫"、"做个海报"、"把纸船换成爱心"、"这个视频帮我改一下"、"帮我复刻这段视频"、"用这首歌做个MV"、"一句话生成短剧"），都必须触发此技能。

Export, preprocess, and fix GitHub PR review comments. Use when user wants to export PR comments, evaluate code reviews, or fix review feedback from CodeRabbit/Gemini/Devin bots.

Generate AI content (images, videos, audio, avatars) and analyze videos with AICP in QCut. Primary mode uses QCut's bundled AICP binary with secure API key injection.

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.

Run QCut's native TypeScript pipeline CLI for AI content generation, video analysis, transcription, YAML pipelines, ViMax agentic video production, and project management. Also use for editor HTTP automation tasks (state snapshots, events, transactions, and notification bridge control) when user needs deterministic state-aware control.

Decision matrix for delegating tasks between Claude Code and Codex CLI. Guides when to handle tasks directly vs. delegate to Codex.

Orchestrate parallel AI agents for Qcut development. Use when spawning agents on issues, checking session status, handling CI failures, managing PRs, or batch-processing multiple tasks. Covers all qagent CLI commands configured for Qcut.

Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion.

AI image generation with OpenAI, Google, DashScope, Replicate and fal.ai APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, and infographics. Use when user asks for "markdown to html", "convert md to html", "md转html", or needs styled HTML output from markdown.

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".

Use when user asks to convert, compress, trim, resize, extract audio, add subtitles, create GIFs, or process video/audio files

Build, deploy, and remotely control QCut on a real iPad or simulator. Use when the user asks to install on iPad, test on iPad, take iPad screenshots, run E2E tests on device, or send CLI commands to the iPad app.

Switch QCut's center Preview Panel between normal video preview and MCP app mode, validate iframe rendering, and debug MCP HTML delivery through IPC and HTTP endpoints. Use when asked to test, demo, or troubleshoot MCP app preview behavior, the "MCP Media App" toggle, `mcp:app-html` events, `/api/claude/mcp/app`, or to craft prompts for Claude that modify the MCP media app UI safely.

CLI-first shot planning skill for QCut. Analyzes a script, article, or idea; builds a deterministic shot list; writes per-shot image prompts; and can render shot frames through its own local fal-backed renderer. Use when the user wants scene shots, storyboard frames, or a shot plan from the terminal.

CLI-first slide deck generator for QCut. Analyzes markdown or text content, creates a slide outline, generates per-slide image prompts, renders slide images through its own local fal-backed renderer, and merges the results into PPTX or PDF. Ships with its own local slide references. Use when the user wants a real command-line slide workflow rather than an interactive slash-skill flow.

Generate Seedance 2.0 video prompts from story outlines. Supports single shots (15s) and long videos (1-2 min). Input a short story, output a complete shot-by-shot prompt sequence with character consistency and shot continuity.

从故事大纲生成 Seedance 2.0 长视频分镜提示词。支持单镜头（15秒）和长视频（1-2分钟）。输入一个短故事，输出完整的分镜 prompt 序列，确保角色一致性和镜头衔接。

Use this skill when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "AI video", "短剧", "广告视频", "视频延长", "video prompt", "video generation", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows. Supports both English and Chinese interactions.

Self-evolving skills. Record user feedback, update methodology and rules. Triggers: update rules, record feedback, improve skill, 更新规则, 记录反馈, 改进skill

Environment setup. Install dependencies, configure API keys, verify environment. Triggers: install, setup, initialize, 安装, 环境准备, 初始化

Subtitle generation and burn-in. Volcengine transcription → dictionary correction → review → burn-in. Triggers: add subtitles, generate subtitles, 加字幕, 生成字幕, 字幕

Talking-head video transcription and speech error detection. Generates review page and deletion task list. Triggers: edit talking head, process video, detect speech errors, 剪口播, 处理视频, 识别口误

Generate AI content (images, videos, audio, avatars) and analyze videos with AICP in QCut. Primary mode uses QCut's bundled AICP binary with secure API key injection.

Export, preprocess, and fix GitHub PR review comments. Use when user wants to export PR comments, evaluate code reviews, or fix review feedback from CodeRabbit/Gemini/Devin bots.

Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.

Orchestrate parallel AI agents for Qcut development. Use when spawning agents on issues, checking session status, handling CI failures, managing PRs, or batch-processing multiple tasks. Covers all qagent CLI commands configured for Qcut.

Decision matrix for delegating tasks between Claude Code and Codex CLI. Guides when to handle tasks directly vs. delegate to Codex.