Resolve Scripting logo

Resolve Scripting

Community
appariciojunior
resolve-scripting

Practical DaVinci Resolve Studio scripting knowledge for building edits from code - timelines from a template, frame-exact appends, zoom, grades, custom frame sizes, subtitles, renders, and the traps that silently fail or crash Resolve 21. Use when writing or debugging any script that talks to Resolve.

Overview

Publisherappariciojunior
Repositoryvideo-editor-skills
Skill nameresolve-scripting
Stars
360
Forks
50
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by appariciojunior on GitHub. Read the source before you install it.

Installation

Install the Resolve Scripting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/appariciojunior/video-editor-skills/tree/main/skills/resolve-scripting
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/appariciojunior/video-editor-skills.git /tmp/video-editor-skills
mkdir -p .claude/skills
cp -r /tmp/video-editor-skills/skills/resolve-scripting .claude/skills/resolve-scripting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Resolve Scripting in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Resolve Scripting on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Resolve Scripting is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Resolve scripting: what actually works (Resolve Studio 21)

Check the API for the installed version before trusting memory: the scripting docs ship with Resolve, and functions move (some changed between 20 and 21).

Golden rules

  • Only add. New timelines (never overwrite: "name v2"), imports into bins, clips on free tracks. Never touch the creator's template or their timelines/media. Never switch/create/close projects.
  • Verify every write by reading it back. Many setters return True and do nothing.
  • Save the project at the end of each step.

Building the timeline

  • Find bins by name recursively. Import files once (reuse the media pool item if the same path is already imported).
  • Copy the template with DuplicateTimeline(name), move it into the timelines bin, then empty every track (unlock locked tracks temporarily). The copy keeps the track FX chain (voice treatment on A1, music treatment on A2) - that's why we copy instead of creating.
  • Frame rate mismatch footage vs template: stop and ask. If they choose the footage rate: useCustomSettings=1, timelineFrameRate, timelinePlaybackFrameRate.
  • Custom frame (e.g. 4:3 2880x2160): set timelineResolutionWidth/Height and the output resolution, then input mismatch behaviour scaleToCrop ("scale full frame with crop"). The default scaleToFit letterboxes. Read it back.
  • AppendToTimeline: endFrame is exclusive. For audio-only media, start/end frames count in the clip's own frame rate (a WAV reports 23.976), not the timeline's.
  • Audio duration from timecode: at 23.976, a timecode counts 24 frames per second. seconds = ((h*3600+m*60+s)*round(fps) + f) / fps. Using 23.976 per second lost 16 frames on an 11-minute music bed.
  • Check after laying: piece count on V1 and A1, each duration, no gaps.

Picture

  • Zoom: item.SetProperty("ZoomX", z) and "ZoomY" (centre anchored). Works in 21.
  • Grades: Timeline.ApplyGradeFromDRX fails in 21. Use each item's graph: item.GetNodeGraph().ApplyGradeFromDRX(path, 0). It occasionally fails on one piece and works on a retry: try twice, then count graded pieces (node count) and report.
  • Never put a log look on non-log footage. Read the profile from the camera's sidecar XML, not from luma guesses.
  • SetClipColor("Green") on B-roll pieces.

Audio

  • Normalize: Timeline.NormalizeAudioLevel(items, {normalizationMode, targetLevel, targetLoudness, setLevelMode}) with resolve.NORMALIZE_AUDIO_SET_LEVEL_INDEPENDENT. See voice-and-audio for values.
  • Per clip: AudioVolume (dB), SetVoiceIsolationState({"isEnabled": True, "amount": 50}), Dialogue Leveler properties. EQ is not scriptable; Fairlight presets can be applied if the user saved some.
  • Silent track trap: a template's music track had a track-level AI Music Remixer switched on (and a Stereo Width insert). Anything placed on that track rendered as silence while the same file played on another track. The API can't read or toggle it; it's in the Edit page → select the track header → Inspector → Audio. If music is silent, check that first.

Diagnosing audio the reliable way

When "there's no sound", don't guess. Render a few seconds of audio from Resolve and compare it with the source file:

  • Project render: SetCurrentRenderFormatAndCodec("mov", "ProRes422LT"), SetRenderSettings({SelectAllFrames: False, MarkIn, MarkOut, TargetDir, CustomName, ExportVideo: False, ExportAudio: True, AudioCodec: "lpcm"}), AddRenderJob().
  • From an external script, rendering only starts with StartRendering([job], False) (isInteractiveMode False). Other forms return False and the job stays "Ready".
  • Render into a folder without spaces (a path with spaces left the job unstarted).
  • Wait on GetRenderJobStatus(job) until "Complete", not on IsRenderingInProgress() (it can be False before rendering begins).
  • Correlate the rendered audio with the source (mono, 8 kHz, best lag): ~0.9 = present, ~0.0 = missing. Least-squares gain tells how much of an SFX is in the mix.
  • Restore the Deliver settings afterwards (format, whole timeline, video+audio on, output folder): your test changes the creator's export settings.
  • AddRenderJob jumps to the Deliver page; SetTrackEnable only works on the Edit page (on other pages it returns True and does nothing). Go back with OpenPage("edit").
  • Timeline export (Timeline.Export(path, EXPORT_DRT)) is a zip of XML with per-track fields; deeper mixer state is a compressed binary. Useful for diffing a working vs broken track.

Subtitles

  • MediaPool.AppendToTimeline with an imported .srt ignores recordFrame and appends the subtitles after the end of the timeline. Passing start/end frames for it crashed Resolve 21.1.
  • Use File > Import > Subtitle in the UI (the creator clicks it, or computer-use). It places the first cue at the playhead and shifts the rest relative to it, so make the SRT's first cue start at 00:00:00,000, or everything lands early.
  • Subtitle track style can't be set by script; read it from a DRT export if you need to record it.

Overlays and media cache

  • Re-rendered files with the same name can keep playing stale cached frames: give each new render a new name (-v2) and replace the clip.
  • Place overlays on the first free unlocked track from V2 up; never on V1.

Reading the timeline the creator edited

Before music, captions or graphics, map the timeline as it is now: walk V1 items (name, start, left offset) to find where each kept word and each B-roll landed. They trim and delete things; follow their version.

Frequently asked questions

What does the Resolve Scripting AI skill do?

Practical DaVinci Resolve Studio scripting knowledge for building edits from code - timelines from a template, frame-exact appends, zoom, grades, custom frame sizes, subtitles, renders, and the traps that silently fail or crash Resolve 21. Use when writing or debugging any script that talks to Resolve.

Why use Resolve Scripting on TypingMind?

Because you install it once and use it with any model. Resolve Scripting is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Resolve Scripting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/appariciojunior/video-editor-skills/tree/main/skills/resolve-scripting. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Resolve Scripting?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Resolve Scripting?

As many as you like. As long as a model supports skills, you can use Resolve Scripting with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Resolve Scripting AI skill free?

It is published on GitHub by appariciojunior. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇