Resolve Media Analysis
Media intelligence layer for the DaVinci Resolve MCP.
Install
npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-media-analysis -g -a claude-code -y- Repository
- samuelgursky/davinci-resolve-mcp3.9k
- Category
- AI and agents
- Updated
- 3d ago
- License
- MIT
- Context cost
- Lightabout 1,026 tokens
- Runs scripts
- No, instructions only
What it does
Media intelligence layer for the DaVinci Resolve MCP. Uses FFprobe, FFmpeg, and optionally Whisper to READ and ANALYZE source media, never modify, transcode, convert, or create derivatives. Provides the MCP with full context of what footage actually is so it can take informed actions within Resolve.
Resolve Media Analysis
This skill wraps the project's canonical media analysis guide with Claude Code-specific integration.
Read docs/guides/media-analysis-guide.md for the complete guide. Everything below is Claude Code-specific context.
The First Rule
Never touch the source. Your relationship to source media is READ-ONLY. See docs/guides/media-analysis-guide.md section "The First Rule: Never Touch the Source" for the full rationale from every post-production department.
What this build cannot do (check before you offer it)
The scripting API changes per patch release, so "Resolve 21" is not a usable
label. Read resolve_control get_version → build.unavailable_on_this_build
before offering a gated surface; check_version_support asks about one named
symbol. Gated in this domain, note all of it is Resolve's own analysis,
not this repo's:
| Surface | Needs | If absent |
|---|---|---|
MediaPoolItem / Folder.AnalyzeForIntellisearch | 21.0 | No IntelliSearch index |
Project.ResetIntellisearchAnalysis | 21.0 | The index cannot be cleared from a script |
MediaPoolItem / Folder.AnalyzeForSlate | 21.0 | No automatic slate detection |
MediaPoolItem / Folder.PerformAudioClassification / ClearAudioClassification | 21.0 | No Resolve-side audio classification |
MediaPoolItem / Folder.RemoveMotionBlur | 21.0 | Unavailable |
Project.GenerateSpeech | 21.0 | No AI speech generation |
This repo's own analysis stack does not depend on any of them. analyze_media
reads frames and audio off disk and runs its own vision/transcription/embedding
tiers, so an older Resolve loses Resolve's AI features, not this pipeline. Say
which one the user is actually missing.
