# Resolve Tighten Recording

Tightening one long single-take recording, talking-head, screencast, tutorial, podcast...

- Repository: https://github.com/samuelgursky/davinci-resolve-mcp (3887 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-tighten-recording -g -a claude-code -y`
Codex: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-tighten-recording -g -a codex -y`
Cursor: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-tighten-recording -g -a cursor -y`
Gemini CLI: `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-tighten-recording -g -a gemini-cli -y`

## Description

Tightening one long single-take recording, talking-head, screencast, tutorial, podcast video, by removing dead air in the DaVinci Resolve MCP. Apply when asked to tighten a recording, remove silences or dead air, cut the pauses out of a long take, or turn a raw one-take recording into a first cut. The subtractive counterpart to resolve-rough-cut, which selects shots from many clips; this skill removes time from one clip.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Resolve Tighten Recording
Turns one long raw take into a tightened variant timeline. **The variant is the
deliverable; the original timeline is never touched.**

Everything below was measured live against Resolve Studio 21.0.1.11 / MCP
v2.80.1 on 2026-08-06, on a real 28.5-minute 30fps screen recording, unless a
different date is given.

## The deliverable contract

Deliver a tightened **variant** timeline, plan → review → confirm. Do not
grade, caption, or add anything; a tighten is pure subtraction. The variant
runs generous on purpose, recovering over-cut material is slow and invisible,
trimming further is fast and visible.

Two things always go back to the editor with the variant:

- **The largest lifts.** A lift is only *silence to the microphone*. Measured
  on real material (2026-07-31): a 29s lift was 70% silent on-screen
  demonstration, real content, cut because nobody spoke over it. Anything
  over ~15s deserves a human look before the variant is trusted.
- **What silence-driven tightening cannot hear**, see the last section.

## Workflow

1. **Lift the analysis caps for long media**, `media_analysis set_caps_preset {preset: "unlimited"}`. The standard preset
   carries a 90-second wall clock; multi-hour material dies on it. Restore
   `standard` when done (step 7).
2. **Transcribe**, `media_analysis start_batch_job` with
   `{clip_id, vision: false, transcription: {enabled: true, ...}}`, then
   `run_batch_job_slice {job_id}`. Two traps in one call pair:
   - **Batch jobs do not advance themselves.** `start_batch_job` returns a
     durable job in `queued` and nothing runs until a slice call drives it.
   - `run_batch_job_slice` **blocks until the slice completes**, budget
     roughly 4-7x realtime for local whisper (measured: 28.5min of Chinese
     speech in 5m14s via mlx_whisper) and run it from a background process,
     not the main conversation.

The rest: https://github.com/samuelgursky/davinci-resolve-mcp/blob/HEAD/.agents/skills/resolve-tighten-recording/SKILL.md