jordanurbs

42 mods across 1 repository, 30 stars between them.

art-director

01

jordanurbs/venice-video-harness

Agent Codex

Make aesthetic decisions for the storyboard: visual style, color palette, lighting language, shot composition, and cinematic tone.

30 11d ago A 0 tokens original MIT

cut-qa

02

jordanurbs/venice-video-harness

Agent Codex

Post-render quality gate for any edited or assembled video. Runs AFTER src/editing/render.ts (editing pipeline) OR after src/mini-drama/assembler.ts (generation pipeline) produces a candidate final.mp4 / final-edit.mp4. Evaluates cut boundaries with scripts/timeline-view.ts, flags regressions, and proposes fixes back…

30 11d ago A 0 tokens original MIT

ffmpeg-overlay

03

jordanurbs/venice-video-harness

Agent Codex

Lightweight sibling of remotion-overlay for overlays that don't need animation or complex typography: static callouts, simple lower thirds, chapter markers without transitions, static chapter title banners. Produces drawtext filter specs that scripts/render-overlay.ts chains into the compositing pass — no separate…

30 11d ago A 0 tokens original MIT

overlay-designer

04

jordanurbs/venice-video-harness

Agent Codex

Top-level planner for branded motion graphics composited onto a delivered cut. Reads the shot script, EDL, and project brief; decides which overlays the episode needs; spawns one sub-agent per overlay in parallel (either remotion-overlay or ffmpeg-overlay); then hands the resulting OverlayManifest to…

30 11d ago A 0 tokens original MIT

prompt-engineer

05

jordanurbs/venice-video-harness

Agent Codex

Before filling any template below, decide what the shot is doing — the turn, the point of view, the power, the subtext — and name one intention. Then derive camera, lens, light, blocking, performance, and sound from that single intention. Do not stack "cinematic / epic / beautiful / masterpiece / 4k" adjectives; they…

30 11d ago A 0 tokens original MIT

remotion-overlay

06

jordanurbs/venice-video-harness

Agent Codex

Worker sub-agent spawned by overlay-designer. Renders a single animated overlay (lower third, chapter marker, title card, logo-bug reveal) as a transparent video file (ProRes 4444 MOV or WebM with alpha) using Remotion.

30 11d ago B 0 tokens original MIT

screenplay-reader

07

jordanurbs/venice-video-harness

Agent Codex

Parse and analyze screenplays in Fountain or PDF format. Extract structured scene data, character information, and narrative metadata.

30 11d ago A 0 tokens original MIT

storyboard-qa

09

jordanurbs/venice-video-harness

Agent Codex

Analyze generated storyboard panels for character consistency and setting continuity. Run after each scene's initial generation to flag issues before video production begins.

30 11d ago A 0 tokens original MIT

trailer-curator

10

jordanurbs/venice-video-harness

Agent Codex

Analyze a full screenplay and curate a shot list for teaser/theatrical trailers. Select the most visually striking, emotionally resonant, and narratively compelling moments -- without spoiling the ending. Build a trailer that makes people want to watch the full film.

30 11d ago A 0 tokens original MIT

edit-footage

14

jordanurbs/venice-video-harness

Command Codex

End-to-end editing pipeline for existing media. Read the video-editing skill before running this command — it defines the EDL format, the ask-confirm-execute-self-eval loop, and the anti-patterns to avoid.

30 11d ago A 0 tokens original MIT

fix-panel

16

jordanurbs/venice-video-harness

Command Codex

Fix character appearance in a storyboard panel using Venice multi-edit with character references.

30 11d ago A 0 tokens original MIT

generate-trailer

18

jordanurbs/venice-video-harness

Command Codex

Analyze the screenplay and generate a curated trailer -- selecting the most compelling moments, generating panel images, and creating video clips.

30 11d ago A 0 tokens original MIT

generate-videos

19

jordanurbs/venice-video-harness

Command Codex

Generate video clips from storyboard panel images using Venice AI's image-to-video models with frame chaining for visual continuity.

30 11d ago A 0 tokens original MIT