Video and Media
Video and media skills support audio, video, image, and presentation workflows used in content production. Expect tools for generating, editing, packaging, or automating media assets that sit outside the typical code-and-infrastructure toolchain.
166 skills
Skills in this category
ocr-super-surya
by aktsmm/agent-skills
Source details, install context, and public review data are available on the full page.
video-transcript-downloader
by steipete/agent-scripts
Source details, install context, and public review data are available on the full page.
pixi-js
by mindrally/skills
Source details, install context, and public review data are available on the full page.
xhs-publisher
by byheaven/byheaven-skills
Source details, install context, and public review data are available on the full page.
mgrep-code-search
by intellectronica/agent-skills
mgrep is a semantic search tool that enables natural language queries across code, text, PDFs, and images. It is particularly effective for exploring larger or complex codebases where traditional pattern matching falls short.
reading-invoice
by kazukinagata/shinkoku
Source details, install context, and public review data are available on the full page.
r3f-loaders
by enzed/r3f-skills
The recommended way to load GLTF/GLB models.
ralph-plan
by mastra-ai/mastra
Source details, install context, and public review data are available on the full page.
reading-deduction-cert
by kazukinagata/shinkoku
控除証明書（生命保険料控除証明書、地震保険料控除証明書、社会保険料控除証明書等）の画像を読み取り、構造化データとして返すスキル。
reading-receipt
by kazukinagata/shinkoku
レシート・領収書・ふるさと納税受領証明書の画像を読み取り、構造化データとして返すスキル。
reading-payment-statement
by kazukinagata/shinkoku
支払調書（報酬、料金、契約金及び賞金の支払調書）の画像を読み取り、構造化データとして返すスキル。
framer-motion
by mindrally/skills
Source details, install context, and public review data are available on the full page.
openai-whisper-api
by steipete/clawdis
Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.
pw-redbook-image
by plugins-world/pw-skills
Source details, install context, and public review data are available on the full page.
seedance-prompter
by pexoai/pexo-skills
This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.
openai-image-gen
by steipete/clawdis
Generate a handful of “random but structured” prompts and render them via the OpenAI Images API.
source-management
by anthropics/knowledge-work-plugins
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md .
reading-withholding
by kazukinagata/shinkoku
Source details, install context, and public review data are available on the full page.
gpt-image-1-5
by intellectronica/agent-skills
Generate new images or edit existing ones using OpenAI's GPT Image 1.5 model.
generating-sounds-with-ai
by raphaelsalaja/userinterface-wiki
Review Web Audio API code for sound synthesis best practices.
seedance
by songguoxs/seedance-prompt-skill
你是一个专业的 AI 视频提示词工程师，专门为字节跳动即梦平台的 Seedance 2.0 视频生成模型编写高质量的中文提示词。
discord
by steipete/clawdis
Use the message tool. No provider-specific discord tool exposed to the agent.
nanobanana-ppt-skills
by sickn33/antigravity-awesome-skills
AI-powered PPT generation with document analysis and styled images
sag
by steipete/clawdis
Use sag for ElevenLabs TTS with local playback.