- Home
- Skills
- Image & Video
- davinci resolve hud automator
Works with the AI Agents you already use
davinci resolve hud automator
Automate 4K 60fps DaVinci Resolve timelines and Fusion HUDs using hallucination-free Lua/Python workflows.
Free
davinci resolve hud automator
Example session with this skill installed
Create a 4K 60fps timeline with a telemetry HUD overlay. Load the data from data/telemetry.lua and apply it to a StyledText tool in Fusion on Track 2.
- Read your context and instructions
- Compiled the davinci resolve hud
Timeline assembly script generated. This Lua script initializes a 4K 60fps project, appends the base media, and maps the telemetry table to a Fusion text overlay on Track 2.
Resolve Automation Script
-- PHASE 1: Project Initialization
local projectManager = resolve:GetProjectManager()
local project = projectManager:GetCurrentProject()
project:SetSetting("timelineResolutionWidth", "3840")
project:SetSetting("timelineResolutionHeight", "2160")
project:SetSetting("timelineFrameRate", "60")
-- PHASE 2: Media Assembly
local mediapool = project:GetMediaPool()
local rootFolder = mediapool:GetRootFolder()
local clips = rootFolder:GetClipList()
local timeline = mediapool:CreateEmptyTimeline("Telemetry_Export")
-- PHASE 3: HUD Overlay via dofile()
local telemetry = dofile("data/telemetry.lua")
local total_duration = #telemetry -- Based on frame index count
-- Append Overlay to Track 2
mediapool:AppendToTimeline({{
mediaPoolItem = clips[2],
startFrame = 0,
endFrame = total_duration,
trackIndex = 2,
recordFrame = 0
}})
-- PHASE 4: Fusion Keyframing
local comp = timeline:GetItemListInTrack("video", 2)[1]:GetFusionCompByIndex(1)
local textTool = comp:FindToolByID("TextPlus")
for frame, data in pairs(telemetry) do
textTool.StyledText[frame] = "Speed: " .. tostring(data.speed) .. " km/h"
end
print("--- PHASE 5: Timeline Prepared ---")
Next steps
- Ensure
data/telemetry.luaexists in the Resolve working directory. - Run the script via the Resolve Console (Workspace > Scripts).
- Verify the "TextPlus" node exists in your Fusion composition on Track 2.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual video editing for telemetry-heavy HUDs is a repetitive bottleneck. This skill automates the assembly of 4K 60fps DaVinci Resolve timelines and Fusion overlays without the API hallucinations common in generic LLM code.
What it does
- Timeline Assembly builds multi-track sequences with precise frame-accurate clip placement.
- Fusion HUD Generation creates animated telemetry overlays using
XYPathandStyledTextkeyframing. - API Guardrails prevents common coding errors by using only verified Resolve
MediaPoolandTimelinemethods. - Telemetry Processing converts CSV data into native Lua tables for high-performance frame indexing.
- Project Configuration enforces 4K Ultra HD standards and disables proxy media for production renders.
How it works
- Pre-processing runs a local Python script to convert external CSV logs into frame-indexed Lua tables.
- Initialization sets project resolution to 3840x2160 and configures render settings.
- Primary Edit assembles base video assets on the first track to establish timeline duration.
- Overlay Injection maps telemetry data to Fusion tools using
dofile()for zero-dependency data loading.
Frameworks & tools
DaVinci Resolve (Free or Studio), Lua, Fusion, Python, and the Resolve Scripting API.
Why this beats prompting it yourself
Generic prompts often invent methods like SetEnd() that do not exist in the Resolve API, leading to runtime crashes. This skill uses a battle-tested architecture that bypasses Resolve's fragile internal JSON parsing in favor of native Lua table telemetry.
Use cases
- Automate gaming HUDs or drone telemetry overlays from log files.
- Batch-process 4K 60fps social media video templates.
- Sync animated text labels to specific timeline frames via CSV data.
Known limitations
Requires a local Python environment for pre-processing CSV data. Does not support non-standard frame rates or proxy-based workflows by default.
Requires local Python environment for CSV pre-processing. Defaults to Native CPU encoder unless GPU profiles are manually verified. Proxy media is disabled by default.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
Requires