Davinci Resolve Editor

Community

liuluhaixiu

davinci-resolve-editor

Safe DaVinci Resolve Studio editing through davinci-resolve-mcp or the official Resolve Python API. Use when Codex must inspect Resolve state, create or revise projects and timelines, import approved media, place source ranges, apply authorized LUTs or effects, prepare rendering, and verify gaps, tracks, source bounds, frame origin, and actual write success.

Overview

Publisher	liuluhaixiu
Repository	`DaVinci-AutoEdit-Agent`
Skill name	`davinci-resolve-editor`
Stars	493
Forks	61
Bundled files	7
License	MIT
Links	Skill source Repository

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.
7 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by liuluhaixiu on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/liuluhaixiu/DaVinci-AutoEdit-Agent/tree/main/skills/davinci-resolve-editor
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/liuluhaixiu/DaVinci-AutoEdit-Agent/tree/main/skills/davinci-resolve-editor

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/liuluhaixiu/DaVinci-AutoEdit-Agent.git /tmp/DaVinci-AutoEdit-Agent
mkdir -p .claude/skills
cp -r /tmp/DaVinci-AutoEdit-Agent/skills/davinci-resolve-editor .claude/skills/davinci-resolve-editor

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Davinci Resolve Editor 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 Davinci Resolve Editor 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 Davinci Resolve Editor 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.

DaVinci Resolve Editor

Operate only from an approved blueprint. Read references/mcp-operations.md for the tool map and references/verification.md before delivery.

For deeper operations, load only the relevant bundled reference:

references/compound-tool-reference.md
references/prompt-patterns.md
references/page-capabilities.md
references/keyboard-shortcuts.md

Connect

Confirm Resolve Studio is open and external scripting is set to Local.
Call resolve -> get_version.
If the tool is unavailable, distinguish missing registration from a server failure. An MCP config file alone is not proof of connection.
Offer blueprint-only delivery or the official Python API fallback.

Install the upstream MCP server when the user approves configuration:

bash
npx davinci-resolve-mcp setup

Write Contract

Before changing Resolve, state:

project and timeline name
tracks to create or modify
media and derivative paths
color, audio, subtitle, and render operations

Obtain explicit approval. Use a new project or duplicated timeline for substantial revisions. Preserve existing user tracks, audio, grades, and manual work unless the user explicitly authorizes modification.

Build

Import only blueprint media.
Convert seconds to frames using the actual project FPS.
Set source in/out and record frame deliberately.
Keep source ranges within probed bounds.
Use explicit track roles rather than assuming A1/A2/A3 universally.
Add BGM, LUTs, stabilization, retiming, audio processing, and renders only when the current request authorizes them.
Apply LUTs to verified camera/color-space groups and read back the node LUT.

Resolve API Boundaries

Resolve writes are stateful; wait and retry in a fresh project/timeline when a batch partially fails.
Derive frame origin from actual timeline items.
Still-image duration may differ by Resolve version; use approved pre-rendered still video for frame-exact delivery.
Resolve 19 may reject item volume writes and does not expose complete Fairlight sidechain automation. Measurement is not a successful write.
Never report an unsupported or rejected operation as completed.

Verify

Read back and report:

active project and timeline
item counts by track
timeline start frame/origin
gaps, overlaps, and one-frame errors
each source path and source range
source group/camera duration ratios
adjacent repeated source, including section boundaries
missing or offline media
LUT/effect/property readback
render settings and job status, when requested

A failed report or a report for an older timeline is not delivery.

Export or report enough timeline information for the parent pipeline to compare the finished cut with the approved script: clip time ranges, source paths, track roles, markers, captions, and narration/dialogue placement. Do not make pickup-shot recommendations from the blueprint alone when a finished timeline exists.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Davinci Resolve Editor AI skill do?

Why use Davinci Resolve Editor on TypingMind?

Because you install it once and use it with any model. Davinci Resolve Editor 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 Davinci Resolve Editor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/liuluhaixiu/DaVinci-AutoEdit-Agent/tree/main/skills/davinci-resolve-editor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Davinci Resolve Editor?

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 Davinci Resolve Editor?

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

Is the Davinci Resolve Editor AI skill free?

Yes. It is published on GitHub by liuluhaixiu under the MIT license. 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

Pixel Art

NousResearch

OrganizationPopular

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

Inference Sh Cli

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Weights And Biases

W&B: log ML experiments, sweeps, model registry, dashboards.

Nemo Curator

Curate LLM training data: dedupe, filter, PII redaction.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

DaVinci Resolve Editor

Connect

Write Contract

Build

Resolve API Boundaries

Verify

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now