Perform non-destructive deterministic editorial assistance including silence mapping and jump cuts, optional local transcription, subtitle burn-in, exact clipping, subject-aware reframing, and delivery compression.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add badgids/Story-Film-Skills --skill edit-assist --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Edit Assist?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-edit-assist)More formats (shields.io, HTML) on the badges page.
---
name: edit-assist
description: Perform non-destructive deterministic editorial assistance including silence mapping and jump cuts, optional local transcription, subtitle burn-in, exact clipping, subject-aware reframing, and delivery compression.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Edit Assist
1. Read `../../references/EDIT_ASSIST.md` and the approved edit intent.
2. Preserve the source file and write a new output.
3. Use silence detection as evidence, not automatic permission to delete dramatic pauses.
4. Use reviewed subtitle or transcript text when dialogue accuracy matters.
5. Prefer approved focus metadata for reframing; face estimation is only a fallback aid.
6. Treat delivery presets as project defaults and verify current platform constraints when necessary.
7. Run `scripts/edit_assist.py` for deterministic execution and verify the resulting media.
Done when the requested edit-assist operation produced a new verified output or reported the exact missing runtime.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
