Menu
SkillsMP a collecté 48 skills depuis Quriosity-agent/qcut. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 48.
Trace a Jianying (剪映) filter from its local resource database to the downloaded package, classify its LUT/shader/segmentation implementation, then reproduce pure color grades in QCut with measured parity. Use for 剪映滤镜, 滤镜对标, 滤镜缓存, 拟合滤镜, 复刻滤镜, adding jy-*…
Langue du texte source : anglais
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…
Langue du texte source : anglais
驱动本机剪映专业版(JianyingPro)做参照采集/导出/草稿实验的操作手册——进程管理、副屏纪律、UI 自动化配方、已知陷阱。凡要操作剪映(打开草稿、导出视频、采平价参照、改片段参数)先读本 skill。
Langue du texte source : chinois
Reverse-engineer how Jianying (剪映专业版) implements an effect — text animations, filters, transitions, stickers — by harvesting its on-disk effect packages (TextAnim.lua, config.json, node-graph lsproj) and capturing stepped reference frames from its UI, then…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Trace how Jianying (剪映专业版) implements 画面特效/人物特效 (the 特效 panel) across its four layers — effects2/face-prop catalog in ressdk_db http_cache, materials.video_effects + dedicated effect tracks in drafts, AmazingFeature packages under Cache/effect, and the…
Langue du texte source : anglais
Trace Jianying (剪映专业版) text animations from catalog cards through Cache/effect packages to the AE-style text-animator runtime in libcccreator. Use for 文字动画对标, studioAnim.lsanim anatomy, Text_BaseSelector keyframe math, sticker/text SwingSegment animation…
Langue du texte source : anglais
Trace Jianying (剪映专业版) transitions from catalog cards through plaintext draft ownership and local effect packages, classify GLSL/Lua/Lumi/ThreeJS/sequence implementations, and produce five-stop QCut parity reports. Use for 剪映转场, 转场对标, transition cache…
Langue du texte source : anglais
Trace Jianying (剪映专业版) decorative text and word-art cards from local ressdk catalog metadata to downloaded artistEffect packages, classify TextStyle versus InfoSticker, inspect gradients, textures, strokes, shadows, and SDF runtime dependencies, and plan…
Langue du texte source : anglais
Use QCut's CLI to generate images, videos, speech, and music; analyze or transcribe media; run AutoClip and other media edits; execute QCut pipelines; and inspect models or project files. Use for QCut media tasks that do not require direct manipulation of a…
Langue du texte source : anglais
Trace which Jianying (剪映专业版) processes, app binaries, and dynamic libraries read, deserialize, encrypt, save, or render local draft and timeline files. Use for 剪映草稿二进制, draft_info.json encryption, crypto_key_store.dat, libvideoeditor, libVECreator,…
Langue du texte source : anglais
Trace Jianying (剪映专业版) sound-effect cards from the local resource database to cached audio, inspect categories and licensing metadata, and prove mappings with content hashes and FFprobe. Use for 剪映音效, 音效库对标, audio cache inspection, Cache/music, downLoadcfg,…
Langue du texte source : anglais
Control a running QCut desktop editor from Codex. Use to open projects, inspect or modify media and timeline state, play or seek, transcribe footage, add stickers, run AI generation, capture screenshots, diagnose errors, and export finished video.
Langue du texte source : anglais
Add or swap feature-showcase blocks (GIF + full-video links) in the repo-root README. Use when the user wants a new feature demo on the README, wants to replace the text-animation/sticker showcase video, or asks to "把视频/动图放到 README 上".
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
End-to-end workflow for turning talking-head or vlog footage into a verified social-ready edit and publishing package. Builds a clean QCut baseline, makes restrained sticker and SFX variants, researches and archives rights-aware B-roll, composes a richer…
Langue du texte source : anglais
Reproduce the look and structure of a reference city/travel promo film with your own or licensed footage — analyze the reference, gather clips, pick segments, write per-act copy, narrate it with emotional TTS, assemble the timeline in QCut, and mix the final…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : chinois
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.
Langue du texte source : anglais
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".
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Decision matrix for delegating tasks between Claude Code and Codex CLI. Guides when to handle tasks directly vs. delegate to Codex.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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",…
Langue du texte source : anglais
Use when user asks to convert, compress, trim, resize, extract audio, add subtitles, create GIFs, or process video/audio files
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
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。
Langue du texte source : chinois
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",…
Langue du texte source : anglais
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
Langue du texte source : anglais