diff --git a/skills/audio-reactive/SKILL.md b/skills/audio-reactive/SKILL.md index 26d36c00fe..c01517b9e4 100644 --- a/skills/audio-reactive/SKILL.md +++ b/skills/audio-reactive/SKILL.md @@ -1,7 +1,7 @@ --- name: audio-reactive -description: Drive any visual element in a HyperFrames composition from audio data — captions, backgrounds, shapes, overlays, anything GSAP can animate. Use when a composition should respond to music, voice, or sound. -trigger: Use when a composition involves music, beat-synced animation, audio visualization, or any visual element that should react to sound. +description: Audio-reactive animation — drive visuals from music, voice, or sound in HyperFrames. Maps frequency bands and amplitude to any GSAP-animatable property. +trigger: Use when a composition involves music, beat-synced animation, audio visualization, or any visual reacting to sound. --- # Audio-Reactive Animation diff --git a/skills/gsap-effects/SKILL.md b/skills/gsap-effects/SKILL.md index 5369015c0e..17b112eae1 100644 --- a/skills/gsap-effects/SKILL.md +++ b/skills/gsap-effects/SKILL.md @@ -1,6 +1,6 @@ --- name: gsap-effects -description: Ready-made animation effects for HyperFrames compositions. Use when adding typewriter text, text reveals, character-by-character animation, audio visualizations, spectrum bars, waveform displays, or any reactive audio-driven animation to a composition. Also use when audio has been analyzed or transcribed in the current session and music is detected — the audio visualizer can enhance the composition with reactive visuals. Reference files contain patterns and data contracts. +description: Typewriter text, audio visualizer, and drop-in animation effects for HyperFrames compositions. Use for character-by-character reveals, spectrum bars, waveforms, or audio-reactive visuals. --- # GSAP Effects diff --git a/skills/hyperframes-captions/SKILL.md b/skills/hyperframes-captions/SKILL.md index dd241a21fb..cc2480f0f1 100644 --- a/skills/hyperframes-captions/SKILL.md +++ b/skills/hyperframes-captions/SKILL.md @@ -1,7 +1,7 @@ --- name: hyperframes-captions -description: Build tone-adaptive captions from whisper transcripts. Detects script energy (hype, corporate, tutorial, storytelling, social) and applies matching typography, color, and animation. Supports per-word styling for brand names, ALL CAPS, numbers, and CTAs. Use when adding captions, subtitles, or lyrics to a HyperFrames composition. Lyric videos ARE captions — any text synced to audio uses this skill. -trigger: Use this skill whenever a task involves syncing text to audio timing. This includes captions, subtitles, lyrics, karaoke, transcription overlays, and any word-level or phrase-level text timed to speech or music. +description: Captions, subtitles, lyrics, and karaoke synced to audio in HyperFrames. Tone-adaptive — detects script energy and applies matching typography, color, and animation with per-word styling. +trigger: Syncing text to audio timing — captions, subtitles, lyrics, karaoke, transcription overlays, word-level or phrase-level text timed to speech or music. --- # Captions @@ -11,6 +11,7 @@ trigger: Use this skill whenever a task involves syncing text to audio timing. T **Never use `.en` models unless the user explicitly states the audio is English.** `.en` models (small.en, medium.en) TRANSLATE non-English audio into English instead of transcribing it. This silently destroys the original language. When transcribing: + 1. If the user says the language → use `--model small --language ` (no `.en` suffix) 2. If the user says it's English → use `--model small.en` 3. If the language is unknown → use `--model small` (no `.en`, no `--language`) — whisper auto-detects diff --git a/skills/hyperframes-cli/SKILL.md b/skills/hyperframes-cli/SKILL.md index 34613fdc7c..d68ed903c4 100644 --- a/skills/hyperframes-cli/SKILL.md +++ b/skills/hyperframes-cli/SKILL.md @@ -1,6 +1,6 @@ --- name: hyperframes-cli -description: Use when the user mentions "hyperframes", wants to preview a composition in the studio, render to MP4/WebM, scaffold a new video project, lint or validate a composition, or troubleshoot rendering. Also use after finishing a composition with compose-video — lint and preview are the natural next steps. +description: Preview, render, lint, validate, scaffold, or troubleshoot HyperFrames compositions. Also use after finishing a composition — lint and preview are the natural next steps. --- # HyperFrames CLI diff --git a/skills/hyperframes-compose/SKILL.md b/skills/hyperframes-compose/SKILL.md index 054463825d..6d873116c4 100644 --- a/skills/hyperframes-compose/SKILL.md +++ b/skills/hyperframes-compose/SKILL.md @@ -1,6 +1,6 @@ --- name: hyperframes-compose -description: Create HyperFrames HTML video compositions. Use when asked to create a video, build an animation, make a composition, add a title card, or generate any HTML-based video content for HyperFrames. +description: Create video compositions, animations, title cards, or overlays in HyperFrames HTML. Use when asked to build any HTML-based video content. --- # Compose Video