mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-05 02:31:47 +00:00
20859cc408
Pulls the hyperframes skill up to the latest state of heygen-com/hyperframes skill content. Opened 2026-04-17; upstream has shipped CLI, layout, and path changes since. - SKILL.md: promote the visual-style check to a proper HARD-GATE (DESIGN.md > named style > ask 3 questions, with the #333/#3b82f6/Roboto tells); expand Step 6 to cover audio-reactive (mandatory per-frame tl.call() sampling loop — a single long tween does NOT react to audio), caption exit guarantee (hard tl.set kill after group.end), marker highlighting, and scene transitions; add the animation-map script to Verification; link the new features.md. - references/cli.md: add capture and validate (both shipped commands, both referenced from the workflow but missing from the reference). Add --lang to tts with the voice-prefix auto-inference table and espeak-ng dependency note (heygen-com/hyperframes#351, 2026-04-20 — after this PR opened). - references/website-to-video.md: update all paths to the capture/ subfolder layout introduced in heygen-com/hyperframes#345 (capture/screenshots/, capture/assets/, capture/extracted/tokens.json). Old captured/ prefix was broken — agents following the skill were looking for files in wrong locations. - references/features.md (new): distilled coverage for captions (language rule, tone table, word grouping, fitTextFontSize, exit guarantee), TTS (multilingual phonemization, speed tuning), audio-reactive (data format, mapping table, sampling pattern), marker highlighting (highlight/circle/burst/scribble/sketchout), and transitions (energy/ mood tables, presets, shader-compatible CSS rules). Five topics the original PR didn't cover. |
||
|---|---|---|
| .. | ||
| blender-mcp | ||
| concept-diagrams | ||
| hyperframes | ||
| kanban-video-orchestrator | ||
| meme-generation | ||