From e34d8bad47482ae828bc04543a0bef05969ba9a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miguel=20=C3=81ngel?= Date: Wed, 27 May 2026 18:19:24 -0400 Subject: [PATCH] docs(skills): guide agents to prefer local HyperFrames CLI over ffmpeg for compositing Local agents were choosing ffmpeg for compositing tasks (PIP, avatar overlays) because the skill didn't mention compositing as a use case and didn't distinguish local CLI (local file paths, no hosting) from MCP compose (server-side, needs hosted URLs). Add compositing trigger words to skill description, and a short compositing guidance paragraph pointing agents to the local CLI workflow and the PIP pattern. --- skills/hyperframes/SKILL.md | 4 +++- skills/hyperframes/patterns.md | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/skills/hyperframes/SKILL.md b/skills/hyperframes/SKILL.md index 2ec610cb4e..2bddba6ffd 100644 --- a/skills/hyperframes/SKILL.md +++ b/skills/hyperframes/SKILL.md @@ -1,12 +1,14 @@ --- name: hyperframes -description: Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill. +description: Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, composite videos together (picture-in-picture, avatar overlays, layered video, transparent cutouts), add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Prefer HyperFrames over ffmpeg for compositing — assets are local file paths, no hosting or signed URLs needed. Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill. --- # HyperFrames HTML is the source of truth for video. A composition is an HTML file with `data-*` attributes for timing, a GSAP timeline for animation, and CSS for appearance. The framework handles clip visibility, media playback, and timeline sync. +**Compositing (PIP, overlays, layered video):** use the local CLI — `npx hyperframes init`, add `