Best media and creative skills, page 64

A skill your agent uses when editing photos for Xiaohongshu, creating image-based posts, designing cover images, retouching product photos, or adding text overlays to images

vivy-yi/xiaohongshu-skills

Discover, search, and manage Spotify music, podcasts, and playlists, including deleting shows or episodes you created with Save to Spotify.

win4r/MuseAI-Skills

手绘卡通风信息图生成。用户描述内容后，Gemini 生成手绘涂鸦风格的信息图并保存到本地。手动触发. An agent skill from doccker/cc-use-exp.

doccker/cc-use-exp

Execute automatic activation for all google vertex ai multimodal operations operations.

jeremylongshore/tons-of-skills-marketplace

Dung khi can TAO RA anh hoac prompt anh bang AI — anh thuong hieu ca nhan, logo, key visual campaign, anh dang hang ngay, editorial, infographic, mockup web, quote graphic.

minhnv0807/ai-business-skills

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/ECC

Remotion 最佳实践 - 在 React 中创建视频。29 条领域特定规则，涵盖 3D、动画、音频、字幕、图表、过渡等。

affaan-m/ECC

Ingest a voice note with exact-phrasing preservation (never paraphrased).

inbrainfun/inbrain

ARK 套餐管理(Agent Plan / Coding Plan,个人版 + 企业版):查询持有 / 购买 / 续费 / 模型清单 / 轮换 APIKey,以及企业版席位的全部管理操作:列出席位(plans team seat-list)、给员工分配席位(plans team seat-assign)、查谁绑了哪个 seat、轮换席位 APIKey(plans team…

volcengine/ark-cli

抖音视频解析技能。当用户发送抖音链接（douyin.com / v.douyin.com）、 抖音分享口令（"复制打开抖音"）、或提到解析抖音、下载抖音视频、 提取视频文案、视频转文字、语音转文本、抖音内容总结时，使用此技能。

infometa/workbuddyskills

Interactively guide MulmoClaude setup following README instructions.

receptron/mulmoclaude

Build animated motion design (explainer, transition reel, product intro).

bluzir/claude-code-design

Design GPU-accelerated animations with Web Animations API (WAAPI), Scroll-Driven Animations (ScrollTimeline/ViewTimeline), FLIP technique, easing systems, and accessibility (prefers-reduced-motion).

EliasOulkadi/shokunin

使用图片/视频生成工具时必读。包含工具参数、非阻塞工作流、任务路由。

ZS520L/HanakoPro

Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured…

artokun/comfyui-mcp

Text-to-speech on Linux -- make the device speak text aloud.

mikeyobrien/rho

多平台账号主页视频提取器 — 输入平台名称和账号id/链接，自动拉取抖音/快手/B站/YouTube 四大平台主页作品，解析下载链接，支持批量下载。适用场景：竞品账号内容拆解与逐帧学习、收藏喜欢的创作者全部作品避免被删、批量搬运素材二次剪辑创作、保存自己账号作品做本地备份防丢失、课程/教程类视频离线囤货反复看、达人合作前快速拉取对方作品做背调分析。触发词：主页视频下载、批量下载视频、账号视频提取…

redfox-data/redfox-community

抖音账号视频批量下载器 — 输入抖音号，自动拉取账号全部作品并解析无水印下载链接，支持批量一键下载到本地。适用场景：竞品账号内容拆解与逐帧学习、收藏喜欢的创作者全部作品避免被删、批量搬运素材二次剪辑创作、保存自己账号作品做本地备份防丢失、课程/教程类视频离线囤货反复看、甲方要求提供无水印源文件、达人合作前快速拉取对方作品做背调分析。触发词：抖音主页下载、抖音视频下载、抖音批量下载、抖音无水印下载…

redfox-data/redfox-community

Instagram视频下载 — 粘贴 Instagram 视频链接，一键解析返回无水印视频下载链接。当用户需要下载 Instagram 视频、保存 IG 视频、获取 Instagram 视频直链时使用。触发词：Instagram视频下载、IG视频下载、Ins视频下载、Instagram视频解析、下载Instagram视频、reel下载。

redfox-data/redfox-community

基于 Seedance 2.0 模型的 AI 视频生成器，输入关键词/描述文案即可生成 MP4 视频。支持文生视频、分辨率/比例/时长控制、预置虚拟人像引用。使用 Seedance 视频生成、AI 视频、text-to-video 时调用此 Skill。

redfox-data/redfox-community

X(Twitter)视频下载 — 粘贴 X(Twitter) 视频链接，一键解析返回无水印视频下载链接。当用户需要下载 X(Twitter) 视频、保存推特视频、获取 X 视频直链时使用。触发词：X视频下载、Twitter视频下载、推特视频下载、X视频解析、Twitter视频解析、下载推特视频。

redfox-data/redfox-community

Lock a picture edit to a music edit: scene boundaries on downbeats and drops, plus irregular camera-punch hits from bass re-entries and vocal hooks (<stemhits.json, schema music-hits/1) with a…

BlackBeltTechnology/pi-agent-dashboard

Bake redaction into screen-recording or camera footage from a JSON spec: fixed crops, time-windowed logo removal, and blurs that switch on only while a detected UI element is on screen, then verify…

BlackBeltTechnology/pi-agent-dashboard

Name anonymous diarized SRT speakers from a persistent local voiceprint library and repair speaker drift; local, CPU-only, no API key.

BlackBeltTechnology/pi-agent-dashboard

Transcribe video and audio files to SRT subtitles with speaker diarization using the Soniox (default) or AssemblyAI API.

BlackBeltTechnology/pi-agent-dashboard

Download YouTube subtitles (SRT + timestamped TXT) for a channel, playlist or video via yt-dlp, no media download; optionally mine them into a categorized catalog (e.g.

BlackBeltTechnology/pi-agent-dashboard

Opt-in, paid brand board for a new site with no existing brand: confirm count, backend and cost, generate one 3x3 board (logo concept, palette, type, image direction) with pi-nano-banana plus a…

BlackBeltTechnology/pi-agent-dashboard

Wibi Style 官方视觉风格。把照片做成儿童纯大头卡贴，只保留头部、干净悬浮在纯色底上。进门先读图分两条路：儿童老照片走「钻牙萌娃」，重建成明亮可爱的现代儿童棚拍并在露齿时做满钻牙；当代自拍走「童年酷照」，把本人反推成 5–8 岁并加潮童装饰。当用户要求童年大头、萌娃大头贴、钻牙大头、把自拍变成小时候的样子，或明确调用 $kid-head-card 时使用。

Vieeeeeee/wibi-style

A skill your agent uses when the user wants a product demo video / screen recording with zooms and cursor / dashboard walkthrough clip for any product (e.g.

ucsandman/marketing-studio

Creates visual concepts for album artwork and generates AI art prompts.

bitwize-music-studio/claude-ai-music-skills

Transcribes audio or video to speaker-labeled, timestamped text, locally with MLX on Apple Silicon or remotely.

daymade/claude-code-skills

Corrects ASR/STT transcription errors — homophones, garbled terms, person-name errors, mixed Chinese/English — with dictionary rules plus Claude's built-in AI, no external API key required.

daymade/claude-code-skills

Create mathematical, geometric and scientific videos with Manim Community in Python.

WrongStack/WrongStack

A skill your agent uses when the user wants a 3D model, mesh or GLB out of Higgsfield — image-to-3D, multi-view-to-3D, text-to-3D, rigging or animating a mesh, remesh / retopology, retexture, or 3D…

OSideMedia/higgsfield-ai-prompt-skill

A skill your agent uses when コレクションの YouTube サムネイル（thumbnail.jpg）を CTR 最適化し、実効 textrender.mode に従い、既定 aiburnin で文字入り候補を生成・承認してから textless 背景を作るとき、または deterministic で textless main.png/jpg…

daiki-beppu/youtube-automation

화면 녹화 도구 없이 웹사이트/웹앱의 짧은 제품 데모·소개 영상(SNS용 1:1, 9:16, 16:9)을 만들 때 사용.

bam-bam-2/solo-skills

Design high-speed cinematic wuxia blade fights with strict physical continuity, one-armed or asymmetric body mechanics, fixed weapon geometry, cumulative injury, weapon-driven causality, 15-second…

karuvanan/MiniMax-H3-Director-Cut-Studio

Process videos by removing segments and concatenating remaining parts.

benchflow-ai/skillsbench

Run the AI博主爬取 project workflow that downloads the latest Bilibili videos for Feishu Base creators marked 是否持续跟踪=true, writes successful downloads to the Feishu 视频 table, and writes a 爬取任务日志 record.

dragon-hh/ai-boshu-crawler

Searches YouTube and fetches video transcripts via the cli-web-youtube command-line tool — video search, video details (views, duration, description, keywords), trending by category, channel info…

ItamarZand88/CLI-Anything-WEB

Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type.

nexu-io/motion-anything

Generate self-contained HTML pages that visually explain technical material — systems, code changes, plans, data.

NikiforovAll/claude-code-rules

Generate images, videos, speech audio, and music using the PonyFlash Python SDK.

aiskillstore/marketplace

Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.

NVIDIA/skills

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning.

NVIDIA/skills

Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM.

NVIDIA/skills

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning…

NVIDIA/skills

Action recognition from video sequences. An agent skill from NVIDIA/skills.

NVIDIA/skills