Agent skills

Media & Video skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 28,838codex 6,583cursor 4,244copilot 1,341windsurf 73cline 44
CategoryAI & Agents 4,188Data & Analytics 3,152Code Review & Quality 1,857Backend & API 1,737Security 1,624Workflow & Productivity 1,614Documentation 1,361Design & Presentation 1,327Content & Marketing 1,213Testing & QA 1,074DevOps & Cloud 783Databases 735Frontend 623Business & Finance 447Media & Video 349Other 7,916
509 found
4996 · page 2 / 11
wjs-reframing-videoUse when the user wants to convert a video between horizontal and vertical orientations while preserving the inverted aspect…jianshuoscriptsyoutube-transcribeYouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown。 支持中英文,英文内容自动翻译成中文,输出中英对照。chubbyguanscriptsbio-clip-seq-ago-clip-mirna-targetsIdentify direct miRNA-target interactions from AGO HITS-CLIP, AGO-CLEAR-CLIP (chimeric reads), HEAP (Halo-Ago2 mouse), chimeric…BioTender-maxscriptsASRImplement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user…jjyaoaoscriptsbio-clip-seq-clip-alignmentAlign preprocessed CLIP-seq reads (eCLIP, iCLIP, iCLIP2, PAR-CLIP) to genome with STAR or bowtie2 using crosslink-preserving…BioTender-maxscriptsbio-clip-seq-clip-motif-analysisDiscover RBP binding motifs from CLIP-seq peaks or single-nucleotide crosslink sites using HOMER, MEME/STREME, kpLogo, mCross…BioTender-maxscriptsbio-workflows-clip-pipelineEnd-to-end CLIP-seq pipeline from FASTQ to ENCODE-compliant binding sites, single-nucleotide crosslink maps, annotation, motifs…BioTender-maxscriptsbio-clip-seq-clip-preprocessingPreprocess CLIP-seq reads (eCLIP, iCLIP, iCLIP2, iCLIP3, irCLIP, PAR-CLIP, FLASH) with protocol-specific UMI extraction, adapter…BioTender-maxscriptspodcast-generator用火山引擎 Podcast AI 模型生成中文双人对话播客。当用户要把文章、报告、话题文本转成播客音频、生成对话式音频内容时使用,需要环境具备火山引擎 APP_ID 和 ACCESS_KEY。支持…staruhubscriptslibtv-videoSeedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer…nexu-ioscriptsbio-clip-seq-m6a-clipMap N6-methyladenosine (m6A) RNA modifications at single-nucleotide resolution using miCLIP (Linder 2015), miCLIP2 + m6Aboost…BioTender-maxscriptsmeeting-audio-groundingConvert a meeting audio file into a transcript bundle, then use meeting-grounding to produce structured meeting grounding outputs.gaotiexinquscriptsmeeting-video-groundingConvert a meeting video into an audio-first transcript bundle, then use meeting-grounding to produce structured meeting grounding…gaotiexinquscriptsmix-masterCanonical short-form-ad audio mix in one FFmpeg pass. VO loudnorm + 3.0× per-clip + 2.0× mix, music 0.13 base + apad+afade…gooseworks-aiscriptsopenrouter-image2videoAnimate a still image into a short video via OpenRouter. Default model google/veo-3.1-fast.QinghongLinscriptsopenstoryline-useUse this skill when OpenStoryline is already installed and the user wants to start the local MCP/Web services, create or continue…FireRedTeamscriptsbio-clip-seq-stamp-antibody-freeProfiles RNA-binding protein targets without antibody or UV crosslinking using STAMP (APOBEC1-RBP fusion, C-to-U editing)…BioTender-maxscriptstiktok-transcribeTikTok 视频 → 下载 → 转录 → 存为 Markdown。 支持 TikTok 链接,无需登录。chubbyguanscriptsweibo-transcribe微博视频 → 下载 → 转录 → 存为 Markdown。 支持微博视频链接,无需登录。chubbyguanscriptswjs-dubbing-videoUse when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a…jianshuoscriptsx-tweet-search-by-querySearches X (Twitter) for tweets by free-form advanced query and returns a normalized tweet list with text, author profile…browser-actscriptsxiaohongshu-search-fullSearch Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs…browser-actscriptszhihu-transcribe知乎视频 → 下载 → 转录 → 存为 Markdown。 支持知乎视频链接,无需登录。chubbyguanscriptsmuapi-cinema-directorDirect high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3…SamurAIGPTscriptsebay-search-listingExtracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle…browser-actscriptsevent-signalsExtract leads from conferences, meetups, hackathons, and podcasts by analyzing speaker lists, sponsor lists, hackathon entries…gooseworks-aiwritesscriptsingest-youtubePull a YouTube video transcript into a queryable markdown vault with yt-dlp subtitle discovery, VTT cleanup, metadata…sickn33scriptsmanim-videoBuild reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the…mturacscriptsmuapi-seedance-2Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers.…SamurAIGPTscriptssrt-from-scriptBuild an SRT subtitle file from a 3-shot short-drama script (ai-video-script OUTPUT FORMAT). Reads each SHOT_N block's DURATION_S…opensquillascriptssubtitle-burnerBurn an SRT subtitle file into an MP4 via ffmpeg's subtitles filter (libass). Single-pass re-encode of video; audio copied as-is.…opensquillascriptstitle-card-imageRender a static title / ending card PNG with Pillow. Centered headline + optional subtitle on a solid-colour background.…opensquillascriptsvideo-framesExtract frames or short clips from videos using ffmpeg.Health-Yangscriptsvideo-framesExtract frames or short clips from videos using ffmpeg.SafeAI-Lab-Xscriptswjs-burning-subtitlesUse when the user has a video + an SRT and wants the subtitles either burned into the pixels (libass, always-visible) or…jianshuoscriptswjs-mining-articlesUse when the user has a video's SRT subtitle file — a 王建硕 monologue / 讲解, OR a 对谈 / 访谈 where 王建硕 is one of the speakers — and…jianshuoscriptspi-agentBuild with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring…K-Dense-AIbaocutDrive BaoCut from the CLI: transcribe local media or media URLs, polish transcripts through Agent workers, translate/correct…JimLiutao-finetune-clipCLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT…NVIDIAwritesvideo-template-frame-kinetic-typeUse this plugin when the user wants a "Kinetic Type" HyperFrames motion video — Bold kinetic typography promonexu-iovideo-template-frame-creative-voltageUse this plugin when the user wants a "Creative Voltage Frame" HyperFrames motion video — Electric split with hand-drawn script —…nexu-iovideo-template-frame-product-promoUse this plugin when the user wants a "Product Promo" HyperFrames motion video — Multi-scene product showcase with SVG assetsnexu-iogame-engineExpert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create…githubtao-train-action-recognitionAction recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying…NVIDIAwritesvideo-template-frame-bold-posterUse this plugin when the user wants a "Bold Poster Frame" HyperFrames motion video — A 1970s European editorial poster in motion…nexu-ioctf-miscProvides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Use for encoding…ljagiellowritesvideo-template-frame-warm-grainUse this plugin when the user wants a "Warm Grain" HyperFrames motion video — Cream aesthetic with grain texturenexu-iovideo-template-frame-play-modeUse this plugin when the user wants a "Play Mode" HyperFrames motion video — Playful elastic animationsnexu-io
← Prev2 / 11Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going