venice-api SKILL.md skillC

venice-api from jordanurbs/venice-video-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jordanurbs/venice-video-harness/venice-api@git:20260805.9863caf

Pins git:20260805.9863caf in mdr.lock. Pin the fingerprint instead.

Audit grade
C, 14 of 17 checks passed
Kind
SKILL.md skill
Repository
jordanurbs/venice-video-harness
Path
.agents/skills/venice-api/SKILL.md
Versions recorded
1
Latest version
git:20260805.9863caf, committed Aug 5, 2026
Size
11,272 bytes
Repository stars
33
License
MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Venice AI Image & Video Generation Skill

## Description
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 production use.

## Model

- **Model ID**: `nano-banana-pro`
- **Retired models**: `fluently-xl` was the old model ID. It returns 404 "model not found" if used. Other available models include `lustify-sdxl`, `flux-2-max`, `lustify-v7` but we use `nano-banana-pro` for storyboard work.

## Endpoints

### Image Generation
```
POST https://api.venice.ai/api/v1/image/generate
Authorization: Bearer <VENICE_API_KEY>
Content-Type: application/json
```

#### Request Body
```json
{
  "model": "nano-banana-pro",
  "prompt": "scene description...",
  "negative_prompt": "things to avoid...",
  "resolution": "1K",
  "aspect_ratio": "16:9",
  "steps": 30,
  "cfg_scale": 7,
  "seed": 12345,
  "hide_watermark": true,
  "safe_mode": false
}
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jordanurbs/venice-video-harness/venice-api@sha256:6a977b40b9178059

The line at the top of this page pins the label git:20260805.9863caf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_j253udblnvesh5lj.svg)](https://markdownregistry.com/a/art_j253udblnvesh5lj)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 5, 2026.

versioncommittedcommitsizeaudit
git:20260805.9863caf latest2026-08-05 9863caf 11,272 BC view

Audit of the latest version

C  14 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: Frontmatter block present
  • fail: Frontmatter declares a name
  • fail: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11272 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

jordanurbs/venice-video-harness · 33 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_j253udblnvesh5lj
GET https://markdownregistry.com/api/v1/resolve?ref=jordanurbs/venice-video-harness/venice-api
GET https://markdownregistry.com/api/v1/blob/6a977b40b9178059b518bc4a0be7c461ac74564f1bbdf996154739bbada16fb2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jordanurbs/venice-video-harness

burn-in-subtitles SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/burn-in-subtitles/SKILL.md · This skill should be used whenever a video harness pipeline produces a voice-over (VO) track and the agent is about to…
git:20260805.9863caf · audit A · 33 stars
character-consistency SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/character-consistency/SKILL.md
git:20260805.9863caf · audit C · 33 stars
screenplay-parsing SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/screenplay-parsing/SKILL.md
git:20260805.9863caf · audit C · 33 stars
sd25-pe SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/sd25-pe/SKILL.md · Use when a user asks an Agent to optimize text, stories, or optional multimodal references for Seedance 2.5…
git:20261026.ca0fe63 · audit A · 33 stars
shot-composition SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/shot-composition/SKILL.md
git:20260805.9863caf · audit C · 33 stars
venice-agent-guide SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/venice-agent-guide/SKILL.md
git:20261026.3846990 · audit C · 33 stars
venice-ui-production SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/venice-ui-production/SKILL.md
git:20260805.9863caf · audit C · 33 stars
venice-video-model-routing SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/venice-video-model-routing/SKILL.md · This skill should be used when generating images or videos via Venice AI, selecting models, attaching reference images…
git:20261006.26d42a0 · audit A · 33 stars
video-editing SKILL.md skill
jordanurbs/venice-video-harness · .agents/skills/video-editing/SKILL.md · This skill should be used whenever the task is to edit existing video/audio files — re-cutting a generated episode…
git:20260805.9863caf · audit A · 33 stars
shot-asset-safety Cursor rule
jordanurbs/venice-video-harness · .cursor/rules/shot-asset-safety.mdc · Preserve generated shot assets by archiving instead of deleting
git:20260319.a64eedf · audit A · 33 stars
AGENTS.md AGENTS.md file
jordanurbs/venice-video-harness · AGENTS.md
git:20261026.3846990 · audit B · 33 stars

Every file in jordanurbs/venice-video-harness

Browse by kind, by grade C, or by owner.