Omni-Rewriter: Skill for Cursor

.cursor/skills/omni-rewriter-model-contribution/SKILL.md

omni-rewriter-model-contribution is a skill for Cursor from WayneJin0918/Omni-Rewriter. It costs 54 tokens per session (746 once invoked), scanned A, original, Apache-2.0.

A guide for adding support for video, image, or combined models to Omni-Rewriter, a system that rewrites prompts or requests for media-generation models. It covers the path from a public model contract to validated output and tests.

In plain words
What is it for?
Adding model profiles, task routes, validators, renderers, generation adapters, fixtures, and compatibility claims to Omni-Rewriter. It is also for reviewing model-support pull requests.
Why use it?
It reduces the risk of adding model support based on guesses or incompatible assumptions. It gives contributors a defined order for checking evidence, routing requests, validating data, rendering output, and testing edge cases.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is WayneJin0918/Omni-Rewriter's own configuration. It tells Cursor how to work on Omni-Rewriter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Omni-Rewriter configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/check_model_contribution.py.

Reuse

Borrowing it

Nothing to install: this file belongs to WayneJin0918/Omni-Rewriter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/WayneJin0918/Omni-Rewriter/main/.cursor/skills/omni-rewriter-model-contribution/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/WayneJin0918/Omni-Rewriter

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for omni-rewriter-model-contribution

README.md
[![agentmods](https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution/github.svg)](https://agentmods.dev/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution)
Your own site
<a href="https://agentmods.dev/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution"><img src="https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omni-rewriter-model-contribution

Your own site · 80×15
<a href="https://agentmods.dev/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution"><img src="https://agentmods.dev/badge/skills/waynejin0918/omni-rewriter/omni-rewriter-model-contribution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 746 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00746
Opus 5 $0.00027 $0.00373
Sonnet 5 $0.00011 $0.00149
Haiku 4.5 $0.00005 $0.00075

Measured 11d ago against content hash d8e15e38f9b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

omni-rewriter-model-contribution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/omni-rewriter-model-contribution/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Omni-Rewriter model contribution

Start here

  1. Read docs/architecture.md, docs/dialects/community-models.md, and the relevant profile guide.
  2. Classify the contribution as exactly one of video, image, or unified.
  3. Copy the structure in CONTRIBUTION_TEMPLATE.md.
  4. Keep prompt expansion and media generation as separate deliverables.

Required implementation order

  1. Evidence — link the public upstream prompt/API/runtime contract. Do not infer private behavior or equate stock vLLM, custom vLLM forks, and vLLM-Omni.
  2. Routing — map public user intent to an existing task, or justify a new transport-neutral task without breaking current RewriteRequest users.
  3. Schema — add or reuse a strict typed output. Unknown fields must remain rejected.
  4. Validation — encode deterministic constraints before adding repair instructions.
  5. Renderer — serialize the validated output into the target public dialect.
  6. Repair — pass only the invalid candidate, errors, and required invariants; keep retries bounded.
  7. Fixtures and tests — cover valid, invalid, boundary, and RAW-vs-expanded cases.
  8. Adapter, optional — add generation only when a public contract exists. Pin the tested runtime and label every untested path unverified.
  9. Docs — update the supported matrix only to the exact demonstrated level: PE, adapter, or live runtime.

Category checklist

Video

  • Require duration_seconds.
  • Define timeline, camera, motion, cut, continuity, dialogue, and audio behavior where applicable.
  • Test timestamp bounds and task/media-role combinations.
  • Optional dialect selector: metadata.video_pe_profile (h3 default, seedance for Seedance PE, ltx for LTX-2.5 PE). Seedance is PE-only. LTX has an optional official-CLI runner; live runtime is unverified until a local generate is recorded.

Image

  • Omit duration_seconds.
  • Define ratio/resolution, visible-text quoting, reference retention, and edit locality.
  • Test T2I, I2I, and edit routes only when the model contract supports them.

Read the full file on GitHub · 82 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 82 lines · 54 tokens per session scan A d8e15e38f9b7

Subscribe to this mod's changes

omni-rewriter-model-contribution is a skill published in the GitHub repository WayneJin0918/Omni-Rewriter (85 stars, last pushed 21d ago), licensed Apache-2.0. It adds 54 tokens to every session and 746 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

1370998960-del/https-github.com-Emily2040-seedance-2.0 · 68 tokens

seedance-2-5-prompt-director

A skill for writing and improving prompts for Seedance 2.5, a video-generation system. It covers text-to-video, image-to-video, editing, video extension, references, camera movement, green-screen work, sound, and lip sync.

zhouwei713/seedance-2-5-prompt-director · 159 tokens

model-aware-image-prompt-engineer

Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…

Emily2040/nano-banana-image-skill · 210 tokens

nano-banana-image-skill

Model-aware image prompting for Nano Banana Pro and Nano Banana 2. Covers generation, editing, continuity, text-in-image, style routing, and structured JSON output.

Emily2040/nano-banana-image-skill · 40 tokens

awesome-gpt-image-2

A structured library of reusable prompts for GPT-Image2, an image-generation model. It breaks prompts into parts such as subject, lighting, materials, composition, and visual details, with more than 20 templates.

AvalonLee/AstraCraft-Program · 0 tokens

mj-prompt

A prompt writer for Midjourney and niji, image-generation tools, using an East Asian visual style framework.

khanhhuyenngo985-sys/character-scene-design-skills · 53 tokens