Media AI Skills

Claude Code skill: Turn text threads into Instagram carousel slides styled as tweet/X post screenshots

by

Control a remote macOS machine from Linux/VPS via SSH — screenshots, commands, app control, file transfer

by

Use when given an engineering or mathematics homework PDF and asked to solve some or all problems, produce a submission-ready answer document, or generate a verified solution PDF.

by

Tianphoto — 智能图文生成工作室 | Claude Code Skill for WeChat-style article image generation

by

通过 869 客户端发送微信消息（私聊/群聊）：纯文本、图片、视频、语音（音乐=语音）、链接、文件（附件）。语音支持 amr/wav/mp3；其中 wav/mp3 会在本地按 allbot 兼容方式转为 silk，单条最长 59 秒，超长自动分片顺序发送。默认从当前用户目录下的 ~/.openclaw/credentials 读取 869 服务地址与 key，也可用 --config 覆盖。

by

Obsidian-oriented PDF paper reading with single-paper focus, detailed-reading guidance, local memory, and a single Markdown deliverable. Use when Codex needs to turn one or more uploaded PDF papers into an Obsidian-friendly reading workflow with classification, reading.md, reading status, question memory, and later comparison support.

by

Generate and publish branded AI avatar lip-sync video shorts to Instagram Reels and YouTube Shorts. Part of Citedy SEO agent skills.

by

Voice interface for OpenClaw with speaker recognition, voice-gated security, real-time barge-in, and multi-provider streaming TTS

by

A comprehensive PDF document translation tool that enables multilingual translation of PDF documents while preserving the original document layout.

by

OpenClaw TTS Provider for Xiaomi MiMo (mimo-v2-tts)

by

AI Agent skill for narrator-ai-cli — CLI client for Narrator AI video narration API

by

An autonomous AI agent that executes your final wishes and preserves your voice, because nothing should be left unsaid, undone, or unloved.

by

Convert YouTube and Bilibili videos into AI-powered Markdown notes using local Whisper transcription + OpenRouter API. Cost-effective, privacy-focused, and supports multiple languages.

by

🎬 AI Video Creator – Open-source video automation toolkit. Tell Claude Code what you want, get an MP4 back. No accounts, no API keys, fully local. Multilingual helper.

by

Claude Code skill: researches topics across 5-8 real sources and writes data-backed LinkedIn posts in your voice — not AI writing

by

codex里直接生图的skill。

by

`pdf-to-md-zh` is a Codex skill for turning a research PDF into a source Markdown package with Mistral OCR, then translating and correcting it into final Chinese Markdown.

by

>

by

Claude Code skill that organizes hundreds of Apple Voice Memos into a searchable archive with transcriptions, summaries, and key quotes. No API keys needed.

by

AI新闻短视频全自动生成SKILL

by

🎵 B站视频音频下载神器！支持单个视频和批量UP主下载，集成 Claude Code Skill 一键调用。自动选择最高音质、断点续传、防封禁设计。

by

Gemini + Sora-2-all automated short video generation skill for Claude Code

by

Local-first /notes skill for agent-made study notes from YouTube, transcripts, audio, and video

by

Public script-to-video skill for HyperFrames workflows with sanitized paths and secret-free examples.

by

>

by

Use when remaking an existing PPT or slide deck from a source PPTX and matching script or notes into a new deck of consistent AI-generated slide images, especially when one new slide should semantically merge one or more source slides while preserving important screenshots, text, and case-study evidence.

by

Write like yourself — at scale. A Claude Code skill that learns your writing style and creates content in your voice.

by

AI video production skill — premise → screenplay → storyboard → render → review → final mp4, with consistent characters / sets / props. Cross-platform (Claude Code, Qwen Code, …).

by

Zernio CLI - Schedule and manage social media posts across 13 platforms from the terminal

by

Tool-driven video question answering with frame extraction, sub-agent analysis, and audio transcription

by

MCP server for RustChain blockchain and BoTTube video platform — AI agent tools for earning RTC tokens. Built on createkr's RustChain SDK.

by

Fast local PDF parsing with PyMuPDF (fitz) for Markdown/JSON outputs and optional images/tables. Use when speed matters more than robustness, or as a fallback while heavier parsers are unavailable. Default to single-PDF parsing with per-document output folders.

by

AI image, video, and music generation skill for Claude Code. Flux, Veo 3.1, Suno V5.

by

>

by

Local image generation with FLUX or Stable Diffusion. Generate images from text prompts on your GPU.

by

create demo videos for WSO2 integrator

by

Collect mathematical content from LaTeX, websites, PDFs, images, or existing notes into Obsidian markdown, while maintaining block maps and following strict math-note formatting rules.

by

"Load this skill whenever operating as CivicLens AI — the civic waste-management assistant. Triggers: any query about waste reporting, garbage detection, image analysis for waste, segregation guidance, cleanup campaigns, municipal authority workflows, heatmap interpretation, facility discovery, escalation logic, platform features, or CivicLens product operations. This skill gives Claude the complete domain context, behavioral rules, image analysis protocol, role model, workflow logic, escalation rules, response templates, and production technical reference to operate correctly as CivicLens AI in every session."

by

Agentic Video Execution Platform - AI-powered transcript capture, event extraction, and agent execution for YouTube content

by

The Claude skill generates Game Boy music and sound effects using only text instructions.

by

🚀 An OpenClaw-native health management agent. It tracks diet, hydration & exercise via LLM, and automates the generation of SaaS-grade, highly-visualized PDF reports with multi-channel push delivery. | 专为 OpenClaw 设计的 AI 智能健康管家，支持自然语言追踪饮食/运动数据，全自动渲染并推送数据可视化的 SaaS 级 PDF 报告。

by

Codex skill for SSH command execution with Windows Terminal screenshot evidence capture.

by

Text-to-speech workflow for turning user-provided text or markdown into pleasant `.opus` audio with `chunktts`. Use when text contains symbols, URLs, formulas, markdown, or technical notation that should be rewritten for natural speech before TTS.

by

第三方Nano-banana 图像生成与编辑 Skill for OpenClaw - 支持文生图和图生图

by

AI Claude Code Skill: GPT-Image-2, Foundry, Gemini Game Development Pixel Art, Sprite & Tilemap Image Generation

by

Claude Code skill that transforms transcripts into ready-to-publish Jike posts with rigorous fact-checking

by

Claude Code skill: Transcribe audio/video/YouTube to Markdown with speaker diarization (MLX Whisper + SpeechBrain)

by

Verify whether citations in an English academic document (Word/PDF) are real or AI-hallucinated, and — when a citation is fake — find a vetted real replacement through an atomized verify→find-alternative→re-verify loop. Use this skill whenever the user asks to check citations, references, or bibliographies, whenever they mention that an AI wrote citations they want to audit, whenever they upload a .docx or .pdf and ask about references, or whenever they say things like "did ChatGPT/Claude make these up", "核查引用", "查参考文献", "check if these papers are real". Even if the user only says "this paper has fake sources" or "audit my refs", use this skill. The skill runs verification against Crossref + OpenAlex + Semantic Scholar APIs AND uses `codex exec` for atomic LLM-driven verification, candidate search, and context-fit scoring. Every Codex call is one-shot and ephemeral — never use `codex resume`.

by

AI Agent's document beautifier — one command to turn Markdown into beautiful web pages, Word, PDF & slideshows

by

Turn docs, posts, and codebases into interactive walkthroughs — narrated animation, quizzes, and hands-on widgets.

by