jordanurbs/venice-video-harness
Command Codex
Run a visual QA analysis on generated storyboard panels for character and setting consistency.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Command Codex
Auto-generate aesthetic comparison samples and let the user pick a visual style.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Command Codex
Generate the complete storyboard for all scenes in the screenplay.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Command Codex
Generate storyboard panel images for an episode.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Command Codex
Generate the storyboard for a single scene. Use this to validate results before batch generating.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Command Codex
Workshop an episode script collaboratively with the user.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
This skill should be used whenever a video harness pipeline produces a voice-over (VO) track and the agent is about to assemble a final video — the agent MUST first ask the user whether to burn in subtitles. When subtitles are wanted, this skill provides the end-to-end captioning process: VO authoring rules that don't…
30 11d ago A 168 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
Maintain visual consistency for characters across all storyboard panels and video clips using a multi-layer approach covering prompt construction, reference generation, multi-edit refinement, and R2V video anchoring.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
Parse screenplays from Fountain (.fountain) and PDF (.pdf) formats into structured scene data.
30 11d ago A 0 tokens
original MIT
sd25-pe
34jordanurbs/venice-video-harness
Skill Claude CodeCodex
Use when a user asks an Agent to optimize text, stories, or optional multimodal references for Seedance 2.5 text-to-video, multi-reference generation, keyframes, storyboards, blockouts, video editing, audio editing, or extension.
30 11d ago A 55 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
Plan cinematic shot lists for screenplay scenes, determining shot types, camera angles, movements, and lens choices for each beat.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
The core rules for driving the venice-video CLI from a coding agent (Hermes, OpenClaw, Cursor, Claude Code, and others). This is the 80/20 subset of AGENTS.md — the rules whose absence loses money or produces unusable output. It mirrors venice-video agent-guide (the same text ships inside the binary) and the full…
30 11d ago A 0 tokens
original MIT
venice-api
37jordanurbs/venice-video-harness
Skill Claude CodeCodex
Generate images and videos via the Venice AI REST API. Image generation uses the Nano Banana Pro model. Video generation uses Veo 3.1 models (image-to-video and text-to-video) via an async queue. This skill covers model names, endpoint behavior, response parsing, resolution limits, and best practices learned from…
30 11d ago B 0 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
Plan and produce mini-drama episodes for manual generation through the Venice AI web UI (venice.ai) instead of the automated CLI pipeline. Outputs a complete shot-by-shot production guide with copy-paste-ready image prompts, video prompts, frame reference instructions, and Venice UI settings.
30 11d ago A 0 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
This skill should be used when generating images or videos via Venice AI, selecting models, attaching reference images, choosing frame sources, or adapting prompts for character consistency. Includes executable Python scripts for image generation, video generation, image editing, and upscaling. Covers R2V-first model…
30 11d ago A 120 tokens
original MIT
jordanurbs/venice-video-harness
Skill Claude CodeCodex
This skill should be used whenever the task is to edit existing video/audio files — re-cutting a generated episode, trimming filler from a VO take, editing raw footage into a delivered cut, or rescuing a truncated TTS render. It codifies the "text + on-demand visuals" philosophy adapted from browser-use/video-use…
30 11d ago A 130 tokens
original MIT
jordanurbs/venice-video-harness
Cursor rule Cursor
Preserve generated shot assets by archiving instead of deleting.
30 11d ago A 144 tokens
original MIT
jordanurbs/venice-video-harness
Instructions file CodexOpenCode
Instructions for jordanurbs/venice-video-harness, covering venice video harness, what this harness does, supported use cases, how to operate and venice api coverage.
30 11d ago A 25,569 tokens
original MIT