davinci-resolve-mcp: Skill for Claude Code

.agents/skills/resolve-mcp/SKILL.md

resolve-mcp is a skill for Claude Code, Codex from samuelgursky/davinci-resolve-mcp. It costs 125 tokens per session (1,472 once invoked), scanned A, original, MIT.

An index for using DaVinci Resolve, a video-editing and color-grading program, through MCP connections. It maps tasks such as editing, grading, media analysis, delivery, and project-file work to the right guidance.

In plain words
What is it for?
Use it to find instructions for color grading, timeline editing, conforming footage, rendering deliverables, media analysis, and handling .drp, .drt, and .drx project files.
Why use it?
It helps you choose the correct workflow and know whether a task needs a running Resolve application or can be prepared offline.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is samuelgursky/davinci-resolve-mcp's own configuration. It tells Claude Code and Codex how to work on davinci-resolve-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything davinci-resolve-mcp configures →

About the project

davinci-resolve-mcp is an MCP server that lets AI assistants control DaVinci Resolve Studio through its scripting API, including editing, media organization, rendering, grading, and other project tasks. It is for users who want agents to operate Resolve and inspect media through a local control panel. The catalogue entries support agent workflows for this Resolve integration.

samuelgursky/davinci-resolve-mcp · 2,622 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to samuelgursky/davinci-resolve-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/samuelgursky/davinci-resolve-mcp/main/.agents/skills/resolve-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for resolve-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-mcp/github.svg)](https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/resolve-mcp)
Your own site
<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/resolve-mcp"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for resolve-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/resolve-mcp"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/resolve-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.01472
Opus 5 $0.00063 $0.00736
Sonnet 5 $0.00025 $0.00294
Haiku 4.5 $0.00013 $0.00147

Measured 11d ago against content hash 4b26dcb21157, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

resolve-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/resolve-mcp/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DaVinci Resolve MCP — Index

Orientation for any Resolve MCP task. This is the map, not the depth — each domain skill below carries its own routing and triggers on its own description. Open the one that matches, or use this when a task spans several domains. This skill does not auto-load the others; it points at them.

Two servers — compute offline, apply live

  • Livedavinci-resolve (Python): drives a running Resolve via the scripting API.
  • Advanced / offlinedavinci-resolve-advanced (Node): authors .drp/.drt/.drx files and patches the project DB with no Resolve open.

Rule of thumb: compute grades, QC, and conform math offline; apply the result live. Node never drives Resolve.

Domains

Task Skill Kernel Any-MCP-client prompt
Grading, looks, shot match, LUT/CDL/DRX resolve-color color-grade-kernel.md /color_grade_workflow
Cutting, trimming, ranges, variants, changelist resolve-edit timeline-edit-kernel.md /timeline_edit_workflow
Conform, relink, finishing QC, grade tracing resolve-conform timeline-conform-interchange-kernel.md /conform_workflow
Render, deliverable QC, media/provenance resolve-delivery render-deliver-kernel.md /delivery_workflow
Fusion comps (titles, MG, VFX) resolve-fusion fusion-composition-kernel.md /fusion_workflow
Audio / Fairlight (tracks, buses, loudness) resolve-audio audio-fairlight-kernel.md /audio_workflow
Media pool ingest / organize / multicam resolve-media-pool media-pool-ingest-kernel.md /media_pool_workflow
Reading/analyzing source media resolve-media-analysis media-analysis-guide.md /analyze_media

Less-common domains (no dedicated skill — go straight to the kernel/tool)

These have real coverage but low enough traffic that they route through this index rather than their own skill:

  • Project lifecycle — create/export/import/archive/restore projects, databases, settings, presets: project_manager compound tool → docs/kernels/project-lifecycle-kernel.md. Offline DB read/patch: advanced project_read / project_db (project CLOSED + quit/relaunch).
  • Review / annotations — timeline markers, review reports, annotation copy/move/scope: timeline_markersdocs/kernels/review-annotation-kernel.md. Offline audit/lineage: advanced provenance.
  • Extension authoring — install/remove Fuse/DCTL/Lua-Python plugins: script_plugindocs/kernels/extension-authoring-kernel.md, docs/authoring/.
  • Pipeline (DB-as-truth) — YAML-authored canonical project DB, staged runs with gates + provenance + drift: advanced pipeline tool → resolve-advanced/README.md.

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 103 lines · 125 tokens per session scan A 4b26dcb21157

Subscribe to this mod's changes

resolve-mcp is a skill published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,622 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 1,472 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cyxj-video-cover

A generator for making 16:9 video-cover background scenes without text, letters, numbers, logos, or watermarks.

chenyuxiaojin/xiaochen-skills · 131 tokens

skill

Skill "skill" from Mun1to/vidorq, covering vidorq skill — edición por ia (v1), flujo, uso, 1) transcribir (word-level, local) and 3) renderizar.

Mun1to/vidorq · 0 tokens

davinci-resolve

Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize DaVinci Resolve Studio 19, Python Scripting API, Fusion VFX nodes, ACES/DWG color management, and Deliver batch rendering.

alivirgo/Major-AI-Skills · 53 tokens

davinci-resolve-cli

Use this skill when the user wants to script DaVinci Resolve from the command line — list/open/save projects, batch-import media, queue or wait on render jobs, list timelines/clips, or add/delete timeline markers. Trigger on mentions of DaVinci Resolve, "render this timeline", "import this footage", "tag clips", or…

Poechant/davinci-resolve-cli · 100 tokens

video-agent-jianying-editor

A video-editing workflow that combines audio, visual files, and subtitles into a draft project for Jianying, the Chinese version of CapCut. It creates a multi-track timeline that can be opened and finished in Jianying.

chenyuxiaojin/video-agent-skills · 128 tokens

video-agent-voice

A voice-production workflow that turns a video script into spoken audio and subtitle files. It can also create guidance for someone recording the narration themselves and use storyboard notes about emotion.

chenyuxiaojin/video-agent-skills · 150 tokens