Find the moments of a CapForge video that stand on their own as Shorts, Reels or TikToks: rank the candidates, time each one to the transcript, write the Shorts caption and a post for every short-form channel, and hand the user the cut list. CapForge cuts nothing; the user trims the clip in their editor. Use when the user asks for clip ideas, Shorts candidates, the best moments, a highlight reel list, a TikTok or Reel from a video, or a Shorts caption.
CapForge is a Claude Code agent skill that find the moments of a CapForge video that stand on their own as Shorts, Reels or TikToks: rank the candidates, time each one to the transcript, write the Shorts caption and a post for every short-form channel, and hand the user the cut list. CapForge cuts nothing; the user trims the clip in their editor. Use when the user asks for clip ideas, Shorts candidates, the best moments, a highlight reel list, a TikTok or Reel from a video, or a Shorts caption.
npx skills add https://github.com/FRSname/CapForge/tree/main/mcp_server/skills/capforge-clipsFind the moments of a CapForge video that stand on their own as Shorts, Reels or TikToks: rank the candidates, time each one to the transcript, write the Shorts caption and a post for every short-form channel, and hand the user the cut list. CapForge cuts nothing; the user trims the clip in their editor. Use when the user asks for clip ideas, Shorts candidates, the best moments, a highlight reel list, a TikTok or Reel from a video, or a Shorts caption.
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.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Use when you have a spec or requirements for a multi-step task, before touching code