Menu
Integrates OpenClaw with the FunClip AI video editor to enable AI-powered video recognition and clipping via command line.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Seamless bidirectional bridge between nanobot (Ollama Mistral orchestrator) and overstory (Claude Code agent swarm). Routes tasks through the OverClaw gateway (port 18800) to overstory for subagent coordination, syncs memory.
IMPORTANT: OpenRouter is required. Routes tasks to the right model and always delegates work through sessions_spawn. Rejects prompt-injection patterns in task strings (v1.7.6+).
Automatically create clips and videos from media files in a specified folder. Uses Agent Swarm for intelligent task delegation and supports cron-based scheduling.
Analyzes journal entries and chat history to identify high-value topics and automatically generate blog posts.
Extracts and analyzes Cursor IDE chat history to identify key discoveries, obstacles, and solutions, saving findings to the journal.
A virtual canvas for OpenClaw to output content and visualize its thinking during development.
| name | funclip-commander |
| displayName | Funclip Commander |
| description | Integrates OpenClaw with the FunClip AI video editor to enable AI-powered video recognition and clipping via command line. |
| version | 0.1.0 |
Integrates OpenClaw with the FunClip AI video editor to enable AI-powered video recognition and clipping via command line.
This skill allows OpenClaw agents to leverage the powerful features of the open-source FunClip AI video editor. By utilizing FunClip's command-line interface, agents can:
This skill will expose functions to:
funclip.recognize_video(file_path_or_url: str, output_dir: str): Handles video download (if YouTube URL), extracts audio, and performs speech-to-text transcription. Depending on config.json settings, it uses Buzz (offline), OpenAI Whisper (cloud), or ClawClip's native ASR. Returns (video_filepath: str, audio_filepath: str, srt_filepath: str, srt_content: str).funclip.clip_video(file_path_or_url: str, output_dir: str, srt_file_path: str, dest_text: str = None, start_ost: int=0, end_ost: int=0, output_file: str = None): Clips video based on a provided SRT, recognized text, or timestamps using ClawClip's Stage 2.This section would list the commands exposed by the OpenClaw skill to interact with FunClip.
The Funclip Commander skill acts as a bridge between OpenClaw's agentic capabilities and FunClip's sophisticated video processing. It enables automated, AI-driven video content creation and analysis workflows directly from your OpenClaw environment.
https://github.com/modelscope/FunClip) must be cloned to your OpenClaw workspace within a directory named FunClip. All its Python dependencies must be installed in a virtual environment (FunClip/.venv).ffmpeg and ffprobe: These must be available in the system's PATH.imagemagick: (Optional, for embedded subtitles) Must be installed and configured as per FunClip's README.md.yt-dlp: Required for downloading YouTube videos. Must be available in the system’s PATH.config.json)workspace/ClawClip).workspace/ClawClip/.venv).true to use Buzz for ASR (default if key/path provided). Requires buzz_python./Users/ghost/.openclaw/workspace/ClawClip/buzz_venv/bin/python3). Buzz 1.4.x requires Python 3.12 or older.true to use OpenAI Whisper API for ASR. Conflicts with use_buzz_for_recognition.whisper-1). Requires OPENAI_API_KEY to be configured in Gateway.Recognition Backends (selected via config, buzz has priority over whisper):
buzz_python and set use_buzz_for_recognition: true.OPENAI_API_KEY to be configured in the OpenClaw Gateway. Best for accuracy and convenience if API access is available. Set use_whisper_for_recognition: true.