A DIY-friendly Skill for remote Codex tasks, notifications and file delivery through Feishu. Use your phone's Feishu app to remotely connect to a desktop Codex, send tasks, receive notifications, and view/download generated images, PDFs, and Excel files—no need to stay glued to the ChatGPT app waiting for reconnections. Supports iPhone, Android, Huawei HarmonyOS, and is fully customizable.
This skill, named 'feishu-mobile-codex-skill', enables developers and AI agent users to remotely interact with a desktop Codex environment via the Feishu (Lark) messaging platform on their mobile devices. It is particularly useful for situations where you need to dispatch tasks, receive real-time notifications, and retrieve generated files like images, PDFs, and Excel spreadsheets without being physically present at the desktop or constantly monitoring the ChatGPT app for reconnection. The skill supports major mobile platforms including Apple iPhone, Android, and Huawei HarmonyOS, and is designed to be DIY-friendly, allowing users to customize its behavior to fit their workflows. It works by integrating Codex with Feishu's bot and webhook capabilities, enabling seamless command execution and file delivery through a familiar chat interface. This makes it ideal for developers who want to offload tasks to a remote Codex instance while staying mobile, or for teams that need a lightweight, accessible way to collaborate with AI agents from their phones.
npx skills add ChiyuSONG/feishu-mobile-codex-skillFeishu Pocket Codex Skill: Use Feishu on your phone to remotely connect to a desktop Codex, dispatch tasks, receive notifications, and view/download generated images, PDFs, and Excel files—no need to keep the ChatGPT app open waiting for reconnections. Supports Apple iPhone, Android, Huawei HarmonyOS, and is fully DIY-friendly. A DIY-friendly Skill for remote Codex tasks, notifications and file delivery through Feishu.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.