媒体创作
1,959 个结果
- Source GraderStepenkoAnatoliGrades every evidence row in a Fetchproof project as P (primary - the page that owns the fact), S (secondary - context) or L (lead only - forums, video, blogs), and records contradictions between sources with both sides and which one is trusted and why, never averaging them.
- Tech Podcast Interview PrepsamberPrepares a guest for someone else's technical podcast, YouTube interview, livestream or panel - show reconnaissance, the angle, an ABT message spine backed by evidence and stories, a self-contained opening answer, clip-safe sound bites, depth calibration, recording-day mechanics, and the post-publication promotion loop.
- Video Content AnalysisgasseraneConvert FGD/webinar/SBCC video files into a structured artefact pack (transcript, frames, manifest, Tier 1 BLUF summary) the existing MEL specialists can consume. Use when Ane asks to "analyse a video", "transcribe a focus group", "process a webinar recording", "summarise a meeting recording", or runs `/analyze-video <path>`.
- Vids DirectorShugar86Create, edit and review Google Vids videos through the vids-claude MCP: direction, scenes, references, speech, sound and export. Use for docs.google.com/videos or explicit Vids work. Создавать, монтировать и проверять ролики именно в Google Vids через vids-claude.
- Adobe PhotoshopalivirgoAutomate Photoshop image-processing tasks with UXP or ExtendScript, Actions, batch jobs, and Smart Objects.
- Ai Tasksimagekit-developerApply AI-powered analysis to images for business-specific tagging, metadata extraction, and quality checks using controlled vocabularies. Use when user wants to analyze images and apply structured metadata in ImageKit.
- Attaching Pr ScreenshotsbostonaholicUploads local images through GitHub's attachment pipeline and writes one verified Screenshots section into a PR body. Use when the user explicitly asks to add or attach screenshots to a PR. Never infer from local images. Not for capturing screenshots; use capturing-screenshots.
- Capturing ScreenshotsbostonaholicCaptures deterministic, visually verified screenshots of a running web or native app (named screens, states, viewports, dark mode) with a manifest. Use when asked for screenshots of an app or its screens. Not for attaching images to a PR; use attaching-pr-screenshots.
- Connector SpotifycaffeinelabsMANDATORY recipe for every Caffeine build that reads Spotify catalog data or drives a user's Spotify account from a canister. The supported path is the `spotify-client` mops package (Spotify Web API) over outbound HTTPS with an OAuth 2.0 bearer token minted off-chain.
- Create Miniature Worlddenggui-aiUse when the user requests 微缩摄影、微缩造景、日常物件变场景、田中达也风格、mitate miniature photography, or tiny-world product imagery from an object name or reference photo, including concept-only requests and follow-up edits. Exclude ordinary product photography, miniature shopping, and tilt-shift blur alone.
- Dialogue Editing And RestorationgothicpixieCutting and cleaning narration, interview and handheld-recorder recordings for documentary and podcast mixes: sentence-exact cuts with measured air and fades, breaths and laughs kept, room-tone fills and floors, spectral repair of coughs, throat-clears and thumps (opendubstage specrepair), de-rumble and the dialogue chain order, sentence-level levelling, and what neural restoration…
- Douyin Video Summaryliu-wei-aiSummarize Douyin (TikTok China) videos by extracting audio, transcribing with whisper.cpp, and generating structured summaries. Use when a user shares a Douyin link and wants a text summary of the video content. Supports optional sync to Feishu (Lark) docs. Triggers on Douyin URLs (v.douyin.com, douyin.com/video/).
- EartrumpetalivirgoInspect and route per-application audio with EarTrumpet, WASAPI, and pycaw; troubleshoot audio sessions and output devices.
- Extension Object StoragecaffeinelabsGeneral file/object storage, such as for images, videos, files, documents and other bulk data. Perfect fit for image galleries, video galleries, and other file or object management. Supports large files beyond IC limit, with browser-cached HTTP URL access.
- FfmpegalivirgoTranscode and compress video with FFmpeg, inspect streams with ffprobe, build filtergraphs and HLS outputs, and diagnose codec or hardware-encoder failures.
- FluxcdalivirgoConfigure Flux CD GitRepository, Kustomization, and HelmRelease resources; troubleshoot reconciliation and image-update automation.
- FtkalivirgoAutomate authorized FTK evidence workflows with FTK Imager, distributed processing, and known-file hash filtering.
- Keyframe CoachGuilherme-M-MateusAnimate game characters and props in Blender using the 12 principles of animation adapted for games (responsiveness, loops, blending, root motion, export). Use when the user wants to animate, block, polish, review or export a character/creature/weapon animation in Blender for a game engine (Unity, Unreal, Godot, Roblox), or asks why an animation looks stiff, floaty, slidey or pops in-engine.
- 11jthingelstadSinging the [A-B-C song backwards](http://www.ralphsworld.com/realaudio/abc.ram). (Wait for the 3rd verse...) Try it. It's harder than you would think. This skill courtesy [Ralph's World](http://www.ralphsworld.com/).
- Logic ProalivirgoAutomate Logic Pro MIDI with Scripter JavaScript, configure Audio Units, and troubleshoot CoreAudio or spatial-audio workflows.
- Lyzbcylyzbcy用于润色 AI 视频 / 漫剧分镜的"逐镜头生成提示词"。核心信念是做减法：角色的长相、服装、配饰一律以角色形象图(art)为准，场景材质以场景图为准，提示词绝不重复描述这些，否则会污染视频模型对形象的还原。只要用户让你"润色/改/优化"分镜提示词、镜头提示词、视频生成提示词，或贴出带"镜头1/镜头2/景别/构图/情绪"的 <提示词> 块让你改，或遇到人物站位/占位错乱、光线跳变，或提到漫剧、AI 漫剧、即梦/可灵/Vidu/Runway 等视频模型的分镜提示词，就应优先使用这份 skill。也支持单功能使用：用户只要"调站位/修占位错乱/跳轴"、"统一音色/VoiceID"、"删污染词"、"统一光线"、"核时长语速"、"核对台词"、"抽帧验证"或"整理分镜目录/按规范摆放"这类局部需求时，同样触发本 skill，只走对应模式、不做多余修改。
- Motion PackANVEAIMake finished, platform-ready videos with an AI agent from motion-pack, an open-source kit of deterministic, seek-safe parts rendered with HyperFrames - transitions, kinetic type and captions, synthesised sound and music, overlays and film looks, camera moves, three.js objects, Blender plates and genre templates - steered by a playbook of graded rules learned from studied films.
- Music Under NarrationgothicpixieSpotting, placing and mixing music under and around spoken word in documentaries, radio features and podcasts: where music enters and exits (downbeats, phrase ends, posts and buttons), ducking depth and timing, the 1–4 kHz carve (opendubstage carve), the music budget (how much of the narration may have music under it), song-relative levels, instrumentals instead of sung vocals under speech…
- Nextjs PerformancejovermierNext.js performance optimizations including next/image, next/font, dynamic imports, caching strategies, and bundle optimization. Use when optimizing Next.js apps for speed or Core Web Vitals.