Best media and creative skills, page 25

Prepare, cut, publish, or repair SubMiner stable and prerelease releases.

ksyasuda/SubMiner

Fetch a YouTube transcript and generate an executive summary, key points, and timestamped topic list as a polished HTML report.

kar2phi/video-lens

Build, sign, validate, notarize, and publish Say It macOS DMG releases using the repository release script.

callebtc/sayit

Create or adapt Bible Strong illustrations in the house style of flat colors, monochromatic characters, and fine detail lines.

smontlouis/bible-strong

Turns a game design document into an art direction document covering visual identity, HUD and feedback, sound direction and the key in-game moments.

zenstory-ai/novel-to-game

AI-powered image generation for Salesforce visuals via Nano Banana Pro.

Jaganpro/sf-skills

Keeps a recurring AI-video character's identity, wardrobe and expressions stable across shots with a stable tag, an identity anchor and one explicit action per character.

Emily2040/seedance-2.0

Record a clean product demo video of a web app on a disposable cloud VM — provision a GCE instance, install Xvfb + Chrome + ffmpeg + real fonts, deploy the app, drive the UI deterministically with…

oratis/LISA

Extracts pixel, video-frame, speech, music and visual-semantic features from image, video and audio files for research datasets, using local tools or the Gemini API.

TyrealQ/q-skills

A skill your agent uses when asked to record a demo proving scaffold-stark actually works end to end — a terminal take of a real Sepolia deploy gate (Take 1), and/or a browser take of a real Braavos…

Scaffold-Stark/scaffold-stark-2

为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames…

bozhouDev/video-skills-toolkit

Add and animate a consistent text layer on an existing NodeTool timeline.

nodetool-ai/nodetool

Make a looping animated chart for LinkedIn or a newsletter in code with Claude Code.

charlie947/motion-graphics-skills

把中文短剧剧本和视觉设定写成有戏剧职责、连续性边界与冻结关键帧提示词的分镜 Markdown。用户提出“拆分镜/设计镜头/做镜头表”“场次视觉计划/调度故事板”“比较导演方案”“写首帧/关键帧提示词”或检查轴线、站位、视线、持物连续性时使用；不生成媒体。

zenstory-ai/drama-skills

This skill helps users automatically extract structured image data from Google Images via BrowserAct API.

browser-act/skills

Verify a Txtify change end-to-end. An agent skill from lkmeta/txtify.

lkmeta/txtify

A skill your agent uses to record or convert ApkAnalyzer app flows into screenshots or GIFs for the README or product docs.

MartinStyk/apk-analyzer

A skill your agent uses when modifying communication between the extension's background, content, popup, or canvas-iframe processes — adding or renaming a ChromeMessageType, changing the manifest's…

nopol10/nekocap

Build a cut from a library — scene, selects, roughcut, custom task, or an edit from a written script.

barefootford/buttercut

A HyperFrames video block in which a canopy of leaves sweeps across the frame and parts to reveal two headlines, rendered at 1920×1080 for 12 seconds.

heygen-com/hyperframes

A HyperFrames video block in which a grid of square tiles flips cell by cell under a sweeping depth field to reveal a rear headline, rendered at 1920×1080 for 8 seconds.

heygen-com/hyperframes

HyperFrames video block where bevelled 3D cuboids carrying card content fly in as a group, rotate in a staggered wave, hold on a hero card and exit.

heygen-com/hyperframes

HyperFrames block that builds a headline of up to 40 characters from Voronoi-cut glass shards flying in through fog, then sends them past the camera.

heygen-com/hyperframes

HyperFrames block with one feature card that circles a dot sphere, driven by camera and card motion exported from an approved Blender rig.

heygen-com/hyperframes

HyperFrames title block with extruded wireframe letters that appear through a portal burst, then swap into a second phrase with a staggered settle glitch.

heygen-com/hyperframes

Generates animation configurations for Remotion including spring configs, interpolations, easing functions, and timing logic.

Marve10s/Better-Fullstack

小红书标题公式工具。从 75 个验证过的爆款公式中，帮你挑对的、用对的、理解为什么用这个. An agent skill from Jamailar/Beav.

Jamailar/Beav

HTMLファイルをmelta UIデザインシステムに照らしてレビューし、違反を検出・分類・修正提案する。トリガー: 「デザインレビュー」「DSチェック」「禁止パターンチェック」「design review」「check compliance」「DS準拠確認」。対象ファイルのパスを引数で受け取る。

tsubotax/melta-ui

Orchestrates story, script, screenplay, concept, product promo, and multi-shot idea work into finished video.

Utopai-Research/pai-code

Turns user content into AntV Infographic syntax, choosing a matching template and structuring the data into a single infographic code block.

ThinkInAIXYZ/deepchat

Design, build or improve procedural risograph animations and videos in this repo, including narrative films, abstract shorts, motion effects and visual inspection.

sevenevesai/riso-windowseat

Adds sound to a finished video: generates narration from a script with TTS, finds royalty-free background music, and mixes everything together with ffmpeg.

SpaceZephyr/creator-buddy

操作本地 BeatDesign 项目中的 Canvas、Assets、生成任务、视频时间线和字幕；在用户要求创作、整理、检查或剪辑媒体时使用。

BeatAPI/BeatDesign

Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally.

feiskyer/codex-settings

使用 AI 生成结构化文本分镜，作为视频生成的输入。用于用户需要一个视频的文本描述（分镜）的场景。用户说"帮我生成一个分镜"、"帮我写视频脚本"时触发。

T0UGH/videoclaw

Cuts long-form video into short platform-ready clips: finds strong moments, reframes for vertical, adds subtitles and brand overlays, and writes a clip manifest.

pawbytes/skill-suites

A skill your agent uses when the user asks to review a design, critique a UI or mockup, give design feedback, or check a screen for usability and accessibility issues.

aakashg/pm-claude-skills

Get content from Bilibili videos: official subtitles, danmaku (density/peaks/sample), comments.

Misaka-Mikoto-Tech/agent-skills

Extract frames or short clips from videos using ffmpeg. An agent skill from trpc-group/trpc-agent-go.

trpc-group/trpc-agent-go

制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片，或用户显式调用 $cs-knowledge-film：从概念与画面隐喻设计，到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板；网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。

ChenShuo2004/cs-skills

Author and run VibeFrame YAML pipelines with vibe run, checkpoints, and budget controls.

vericontext/vibeframe

产品宣传片创意简报。输入产品说明或 GitHub 链接，自动抓取产品信息，提炼核心卖点，推荐视觉风格和叙事结构。当用户提到"宣传片""promo""产品视频""做个视频介绍""项目宣传"时触发。

kangarooking/promo-creator-skills

Check and configure motiscope — verify ffmpeg/ffprobe are installed and scaffold the API-key config used for optional (stubbed) asset generation.

KumarSashank/motiscope

Create cinematic movie poster concepts and final poster images from a user's brief, existing video plan, storyboard, character design, or project context.

MagicCube/agentara

把电影、电视剧或短剧素材制作成第三者旁白主导、关键影视原声点睛的中文解说视频，并生成抖音竖版封面、标题候选、50-100 字文案、话题和完整发布包。复用 videohub-story-editor 的证据提取、剧情理解、剪辑、后置翻译、TTS…

cacity/VideoHub

将分集大纲写成结构化场次、动作节拍和逐句台词，核对人物与美术引用、估算时长并交付剧本评审报告。用于写剧本、对白和场次修订；不分镜、不直接执行配音或视频生成。

suihe1/short-drama-production

Create professional infographics using Nano Banana Pro AI with smart iterative refinement.

lamm-mit/scienceclaw

Edit Final Cut Pro timelines with natural language via FCPXML.

DareDev256/fcp-mcp-server