Media & Creative

Convert robot trajectory datasets between formats — currently agibot v1 → LeRobot v2.1 (parquet + HEVC/PNG-encoded MP4).

AgibotTech/genie_sim

Drive geniesimworld to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the geniesimworld create CLI (Click subcommand), pairs SHARP + DA360 to fuse…

AgibotTech/genie_sim

Wibi Style 官方视觉风格。把用户上传的人物照片转换成象牙白纸面的粗蜡笔时尚编辑插画：笨拙大色块形体、符号化小脸、一处高饱和跳色和三个粗钝手写英文单词。适用于用户要求暖纸蜡笔街拍、蜡笔时装插画、把照片画成独立小刊街拍，或明确调用 $warm-paper-crayon-street 时。

Vieeeeeee/wibi-style

Generate speech or transcribe audio locally with Voicebox. An agent skill from first-fluke/oh-my-agent.

first-fluke/oh-my-agent

A skill your agent uses when the user asks to "script this short video", "write a TikTok / Reels / Shorts script", "给这条抖音或视频号视频写脚本", or "fix the hook — viewers drop off in the first seconds"…

aaron-he-zhu/aaron-marketing-skills

Traces the full life of a music generation request (UI form → Node job queue → engine LM → synth → SQLite song row) and every place params can silently drop, especially the LM echo sideband gotcha.

scragnog/HOT-Step-CPP

Make songs, themes and game scores for a Homie studio with ElevenLabs Music, through the creator's OWN ElevenLabs account — a composition plan for anything sung, a transcription check that every…

hashgraph-online/awesome-codex-plugins

Generate elegant cover images for articles. An agent skill from sugarforever/01coder-agent-skills.

sugarforever/01coder-agent-skills

Autonomous design critique mode using the Agentation annotation toolbar.

theexperiencecompany/gaia

turn a GitHub pull request (a PR URL like github.com/<owner/<repo/pull/<N, an <owner/<repo<N ref, or 'this PR' in a checked-out repo) into a code-change explainer video, up to ~3 min (sweet spot…

chmonitor/chmonitor

对比图/一图流：生成 A vs B 参数对比图、优劣势对比表、产品参数一图流. An agent skill from ZJU-REAL/Easel.

ZJU-REAL/Easel

通用图像处理加工：改尺寸/缩放、裁剪、补边适配平台尺寸、格式转换（png/jpg/webp）、 压缩到目标大小、加文字或图片水印、圆角、多图拼接、生成缩略图、读图片信息。

ZJU-REAL/Easel

生成视频脚本，覆盖短视频（7-60秒）到中长视频（1-30分钟）全时长. An agent skill from ZJU-REAL/Easel.

ZJU-REAL/Easel

视频制作策略与工具选型：AI 视频生成模型对比、视频脚本结构设计、制作流程规划，覆盖产品演示/解说/社媒短视频场景. An agent skill from ZJU-REAL/Easel.

ZJU-REAL/Easel

Best practices and comprehensive guide for Remotion - programmatic video creation in React with animations, compositions, and media handling

davila7/claude-code-templates

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps.

sickn33/agentic-awesome-skills

Auto-speak every Hermes response via AgentVibes TTS on a remote machine over SSH.

paulpreibisch/AgentVibes

A skill your agent uses when the user has one or more video clips and wants to add post-production on top — AI-generated cover as first frame, HTML/CSS captions synced to SRT, kinetic illustration…

jianshuo/claude-skills

A skill your agent uses when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

fossasia/eventyay-interpretation

A skill your agent uses to find files, understand module ownership, and locate code in VoxBento.

fossasia/eventyay-interpretation

A skill your agent uses for tasks involving transcription providers, caption streaming, or the audio pipeline.

fossasia/eventyay-interpretation

Write or revise the active iPolloWork video's native STORYBOARD.md, with source coverage, content-led sequence and provisional timing; use for script-only work.

Devin-AXIS/iPolloWork

Design/audit qualitative and mixed-methods sampling, reflexivity, integration and claim limits.

huang-sir1/radiology-skills

Select, customize, or extend the project's reusable motion-graphics card library and style templates.

nateherkai/hyperframes-student-kit

Explain how to run and use this repository's local Web UI, with detailed guidance for every Settings section and its visible controls.

autonomous-ai/Physical-AI-Operating-System

图片理解智能体，负责识别图片内容、反推提示词、分析图片风格、对比图片差异以及文字识别（OCR）. An agent skill from jeffstric/ZJT.

jeffstric/ZJT

品牌视觉资产生产质量 Owner — 当任务涉及品牌标志、图标、主题变体、微尺寸光学校正、单色母版、主资产谱系或视觉验收证据时使用；要求把几何一致性、变体关系和人工视觉结论绑定到可重放证据，避免只凭文件存在或单次截图宣告完成。

devcodex-labs/devcodex

Write meaningful alternative text for images, charts, diagrams, and visual content.

Owl-Listener/inclusive-design-skills

Hyperframes-based video template for retro pixel deck motion design.

nexu-io/open-design

Luxury dark-editorial HyperFrames template for three-page cinematic storyboards, inspired by haute couture title cards and magazine chapter spreads.

nexu-io/open-design

Close out Audiobook Organizer issues with verification, status comments, and PR-aware hygiene.

jeeftor/audiobook-organizer

Generate images using OpenAI's Codex backend API with gpt-image-2 tool.

OpenMinis/MinisSkills

Neta API 创作技能——生成图片、视频、歌曲、MV，并从现有作品中拆解创作思路。当用户需要生成或修改图片/视频/歌曲/MV，或基于角色设定与现有作品进行创作时使用本技能；不处理推荐流与标签/分类调研（这些由 neta-community 与 neta-suggest 负责）。

netaart/neta-skills

Transcribe and summarize a meeting recording — speaker-attributed transcript, corrected mis-hearings, then a brief with decisions and action items.

amd/gaia

Unified team skill for motion design. An agent skill from catlog22/Claude-Code-Workflow.

catlog22/Claude-Code-Workflow

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image).

LigphiDonk/Oh-my--paper

arkcli 推理接入点管理与显式 raw CRUD 创建能力。正向触发：用户明确要求脚本化 / CI / 无护栏 / 原始 raw CRUD 创建 Endpoint 时，必须使用本 skill 的 arkcli infer endpoint create 路径，不能切到 arkcli-deploy；模型缺失或只有品牌/家族名时仍留在本 skill，先执行实时有界候选与 0/1/N…

volcengine/ark-cli

Turn a text prompt or script into a finished, multi-shot video with Pexo.

pexoai/pexo-skills

Remotion Shot 组件实现。将 storyboard 转化为 React 组件。包含关键的帧计算规则（Math.round 强制）、interpolate 安全规则（最小 1 帧）、1080p 视觉标准、动画编排模式、音视频同步架构、组件复用模式。这是技术密度最高的 skill。

bilibili/carocut

Generate unified, on-brand Instagram Reel covers for Yuval (YUV.AI Neon Phoenix system) — the signature look is a giant Hebrew headline BEHIND the subject cutout + a punch line IN FRONT (depth…

hoodini/ai-agents-skills

Extract brand identity from a website URL — voice, colors, typography, imagery, values, and target audience — into a structured brand-profile.json.

thatrebeccarae/claude-marketing

HyperFrames CLI dev loop — npx hyperframes for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade).

boraoztunc/skills

Record scripted browser sessions into video clips with the capture studio tools.

OtoDock/oto-dock

Turn a one-line AI video idea into a shot list and per-shot, model-ready prompts via a film crew (director, DP, gaffer, editor, script supervisor).

sickn33/agentic-awesome-skills

Generate and edit images/video with Google's Gemini media models (Nano Banana 2/Pro, Gemini Omni Flash), with cost-approval gates, reference-image support, and a prompt/output log per call.

sickn33/agentic-awesome-skills

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with…

mukul975/Anthropic-Cybersecurity-Skills

End-to-end Chinese video washing pipeline. An agent skill from Pluviobyte/rnskill.

Pluviobyte/rnskill

Create dark cinematic SaaS/product motion videos in the Presenton-like "magic UI" style: black starfield stage, bottom purple glow, large kinetic type, cyan-to-magenta CTA buttons, prompt cards…

Pluviobyte/rnskill