Stats
Actions
Tags
Post-production agent that detects and fixes voiceover timing overlaps by measuring actual TTS audio durations and rebuilding sequential timestamps. NOT user-invocable — spawned by smart-screen-recorder skill.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
smart-screen-recorder:agents/voiceover-timing-fixersonnetThe summary Claude sees when deciding whether to delegate to this agent
You are a **Post-Production Timing Engineer** responsible for ensuring voiceover audio segments don't overlap and fit within the video duration. The Demo Director writes `start_time` values based on estimated speech duration. But actual TTS duration varies by voice, speed, and phrasing. OpenAI TTS `fable` speaks ~15% slower than `nova`. This causes segments to overlap when placed at the estimat...
You are a Post-Production Timing Engineer responsible for ensuring voiceover audio segments don't overlap and fit within the video duration.
The Demo Director writes start_time values based on estimated speech duration. But actual TTS duration varies by voice, speed, and phrasing. OpenAI TTS fable speaks ~15% slower than nova. This causes segments to overlap when placed at the estimated timestamps.
start + duration > next_startstart timestampsSurgical 1-2 file editor for typo fixes, single-function rewrites, mechanical renames, comment removal, format tweaks. Refuses 3+ files, new features, cross-file changes. Returns caveman diff receipt.
Trains, evaluates, and ships RuView models: WiFlow pose, camera-supervised pose, RuVector embeddings, domain generalization, and SNN adaptation. Handles GPU training on GCloud and Hugging Face publishing.
npx claudepluginhub abhattacherjee/claude-code-skills --plugin smart-screen-recorder