New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gemini Omni

by calesthio in calesthio/OpenMontage

Generate and conversationally edit short videos with Google Gemini Omni Flash (gemini-omni-flash-preview).

AGPL-3.0Auto-check: notesMedia & Creative

Install Gemini Omni

skills CLI
$ npx skills add calesthio/OpenMontage --skill gemini-omni -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install calesthio/OpenMontage gemini-omni --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/calesthio/OpenMontage.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/gemini-omni .claude/skills/gemini-omni && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gemini-omni
GitHub stars
66k
Token cost
~2.1k tokens
SKILL.md length
947 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate and conversationally edit short videos with Google Gemini Omni Flash (gemini-omni-flash-preview).

  • Works in 4 steps: Generate the base clip (subject + scene… → Pass it back as previous_interaction_id… → Append "Keep everything else the same."… → …
  • Iterating on a clip with natural-language edits instead of regenerating (make the phone invisible
  • SKILL.md covers When to pick it (and when not), Generation prompting, Reference images ( / tags) and Conversational editing (the…, plus 2 more sections
  • Needs GOOGLE_API_KEY and GEMINI_API_KEY

What it does

Gemini Omni is an agent skill from calesthio/OpenMontage. Generate and conversationally edit short videos with Google Gemini Omni Flash (gemini-omni-flash-preview). Use when: (1) iterating on a clip with natural-language edits instead of regenerating ("make the phone invisible, keep everything else the same"), (2) generating 3-10s 720p clips with synthesized audio, rendered on-screen text, or timecoded beats, (3) binding reference images to roles with <FIRSTFRAME/<IMAGEREFN prompt tags, (4) editing an existing uploaded video. Accessed via the geminiomnivideo tool using…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Text to speech and voice, LLM API integration and AI video generation. It works with Google Gemini. The repository describes itself as: World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant… The licence is AGPL-3.0.

When your agent uses it

  • Iterating on a clip with natural-language edits instead of regenerating (make the phone invisible
  • Keep everything else the same)
  • Generating 3-10s 720p clips with synthesized audio
  • Rendered on-screen text

Example prompts

  • “make the phone invisible, keep everything else the same”
  • “/gemini-omni”

Requirements

  • A credential in GEMINI_API_KEY
  • A credential in GOOGLE_API_KEY
  • Pre-approved tools (allowed-tools): Bash, Read, Write

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Generate the base clip (subject + scene + motion). The tool returns interaction_id in its result data.
  2. Pass it back as previous_interaction_id with operation="edit_video" and describe only the delta.
  3. Append "Keep everything else the same." to pin unmentioned elements.
  4. Refine in layers — one turn for lighting, one for camera, one for action, one for audio.

What it can do on your machine

Read from SKILL.md and the folder at commit 9327439. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • ai.google.dev
    • blog.google

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GOOGLE_API_KEY
    • GEMINI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gemini Omni loads about 2.1k tokens when it runs. Until then it costs about 156 tokens; SKILL.md has 947 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~156
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from calesthio/OpenMontage at commit 9327439, republished under its AGPL-3.0 licence (© calesthio). 947 words, ~2,099 tokens.

Download SKILL.mdSave it as .claude/skills/gemini-omni/SKILL.md (or your agent's skills folder).
name
gemini-omni
description
Generate and conversationally edit short videos with Google Gemini Omni Flash (`gemini-omni-flash-preview`). Use when: (1) iterating on a clip with natural-language edits instead of regenerating ("make the phone invisible, keep everything else the same"), (2) generating 3-10s 720p clips with synthesized audio, rendered on-screen text, or timecoded beats, (3) binding reference images to roles with <FIRST_FRAME>/<IMAGE_REF_N> prompt tags, (4) editing an existing uploaded video. Accessed via the `gemini_omni_video` tool using the project's GEMINI_API_KEY/GOOGLE_API_KEY — the same key as Imagen and Google TTS.
allowed-tools
Bash, Read, Write

Gemini Omni Flash (Google DeepMind)

Gemini Omni is Google DeepMind's video generation and editing model family, announced at I/O 2026. The first model, Gemini Omni Flash (gemini-omni-flash-preview, developer access since June 30, 2026), generates 3-10 second clips at 720p/24fps with synthesized audio via the Gemini Interactions API. Its differentiator in the OpenMontage fleet is stateful conversational editing: each generation returns an interaction_id, and a follow-up call with previous_interaction_id edits that video in place — no other wrapped provider can refine a clip without regenerating it.

OpenMontage wraps it as gemini_omni_video (native Gemini API, no gateway). It shares GOOGLE_API_KEY/GEMINI_API_KEY with google_imagen and google_tts — one key, three capabilities. Paid tier only: ~$0.10 per second of output video (billed as 5,792 output tokens/sec at $17.50/1M).

Other documented routes are available when the direct Google key is not the chosen provider:

RouteOpenMontage callImportant limitation
fal.aigemini_omni_falT2V, I2V, reference video, and edit endpoints; no Google interaction ID is returned
Runwayrunway_video, model: "gemini_omni_flash"T2V/I2V/V2V; video edits accept up to five image references
ComfyUI Partner Nodecomfyui_video, model_family: "gemini_omni_flash"Hosted paid node; requires network, Comfy login, and credits

Use the direct gemini_omni_video route for stateful conversational editing. Gateway routes return ordinary provider tasks and cannot preserve Google's previous_interaction_id workflow. The fal edit endpoint can still be iterated by feeding each output video URL into the next edit call.

When to pick it (and when not)

Use it forPrefer another provider for
Iterative refinement — generate, review, then edit the same clip in layersOne-shot cinematic hero clips (→ Seedance 2.0, see seedance-2-0)
Editing an existing/uploaded clip (restyle, add/remove objects, change text)Clips longer than 10s or above 720p
On-screen rendered text and word-by-word text beatsSeed-reproducible generations (no seed support)
Reference-image-bound subjects/styles via prompt tagsFirst/last-frame interpolation (→ veo_video)
Timecode-scheduled multi-beat clips from one promptNon-English narration (English only fully supported)

Route through video_selector for generation operations. Editing (edit_video) is a direct-tool operation — call gemini_omni_video from the registry, because the multi-turn interaction state lives outside the selector's model.

Generation prompting

Describe scene + camera + lighting + motion + audio. Official example:

Continuous, unbroken handheld shot of a fluffy tabby cat sitting on a sunny windowsill, looking out into a leafy garden. The cat's tail twitches slowly, and its ears rotate slightly toward ambient noises. Sunbeams illuminate dust motes in the air.

  • Force a single shot explicitly: "In a single continuous shot," / "No scene cuts." Otherwise the model may cut between scenes.
  • Negatives go in prose — there is no negative_prompt parameter: "No dialogue," "No extra sound effects."
  • No sampler controls: system instructions, temperature, top_p, and seeds are all unsupported. The prompt is the only lever.
  • Meta-prompt for quality: "Consider micro-detail, expression and timing to create a very rich, detailed but entirely natural scene."
Timecode syntax

Schedule beats with bracketed ranges or natural language — this maps directly onto OpenMontage scene-plan timings:

[0-3s] A person is walking [3-6s] They stop and turn around

"After 3 seconds, a woman enters the scene." / "At 5s the chorus starts in the background audio."

Audio and on-screen text

Audio is synthesized automatically; direct it in the prompt: "Include calm background music," "The audio is a low tinny radio broadcast in the background." Rendered text works and can be timed:

One word on the screen at a time: 'did, you, know, that, Omni, can, do, awesome, text?' Each word appears for 1s.

Show full SKILL.md (403 more words)Show less

Reference images (<FIRST_FRAME> / <IMAGE_REF_N> tags)

Pass local images via reference_image_paths (they are sent in order), then bind them to roles inside the prompt with tags. <IMAGE_REF_N> indexes from 0 in the order supplied:

in the style of <IMAGE_REF_0> a woman <IMAGE_REF_1> is walking
[0-3s] A studio fashion sequence. Starting with woman <IMAGE_REF_0>, she is
holding <IMAGE_REF_1> [3-6s] Then we see the man <IMAGE_REF_2> holding <IMAGE_REF_3>
  • <FIRST_FRAME> makes an image the opening frame: <FIRST_FRAME> a woman is walking.
  • Use high-resolution images; describe the intended motion specifically rather than "make it move."
  • Say what each image is (product / character / style / background reference) — the model decides usage from context.

Conversational editing (the differentiator)

Editing prompts are the opposite of generation prompts: short and surgical. Overly descriptive edit prompts cause unintended changes.

  1. Generate the base clip (subject + scene + motion). The tool returns interaction_id in its result data.
  2. Pass it back as previous_interaction_id with operation="edit_video" and describe only the delta.
  3. Append "Keep everything else the same." to pin unmentioned elements.
  4. Refine in layers — one turn for lighting, one for camera, one for action, one for audio.

Official good/bad pairs:

AvoidInstead
"In the video of the man sitting on the sofa, please add a small black cat...""Add a cat that jumps onto his lap, he begins to pet it. Keep everything else the same."
"Please remove the cell phone... and fill in the background so it looks like...""Make the phone invisible. Keep everything else the same."

Other working edit prompts: "Make this video anime" / "Put a fashionable hat on this person" / "Change the lighting to be more dramatic" / "Change the text on the sign to say 'Omni Flash'".

Gotcha — store: editing via previous_interaction_id only works if the prior call kept the interaction server-side (store defaults to true in gemini_omni_video). Set store=false only for one-shot generations you will never edit.

Editing uploaded videos: pass input_video_path instead of previous_interaction_id; the tool uploads it via the Files API. Unavailable in the EEA, Switzerland, and the UK (editing generated videos works everywhere).

Hard limitations (preview)

  • Output: 3-10s, 720p, 24fps, MP4 with audio; aspect ratio 16:9 or 9:16. All output carries an invisible SynthID watermark.
  • No seed, negative prompt, temperature, top_p, or system instructions.
  • No video extension or first/last-frame interpolation; no voice editing.
  • Audio reference inputs unsupported. Video references ≤3s are accepted by the schema but not processed correctly — don't rely on them.
  • Multi-video prompting unsupported; may degrade output.
  • English fully supported; other languages untested.
  • Images of minors (EEA/CH/UK) and certain recognizable people are blocked for upload/editing.

Sources

© calesthio, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/gemini-omni of calesthio/OpenMontage.

Open the folder on GitHubat commit 9327439

Compare with similar skills

Gemini Omni next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gemini Omni compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gemini Omni this skillcalesthio/OpenMontage66k—~2.1kAutomated safety check: NotesAGPL-3.0
Google Gemini Mediasundial-org/awesome-openclaw-skills6631 repos~4.5kAutomated safety check: PassMIT
Gemini Interactions APIAyuilos/Miffan225—~4.6kAutomated safety check: PassAGPL-3.0
Fal AImikeOnBreeze/cc-crossbeam293—~1.9kAutomated safety check: NotesMIT
Collage B-Roll Video Makerimraywang/rayskills159—~2.6kAutomated safety check: PassCustom licence
Fal AI Mediaaffaan-m/ECC277k4 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Google Gemini Media

    sundial-org/awesome-openclaw-skills

    Use the Gemini API (Nano Banana image generation, Veo video, Gemini TTS speech and audio understanding) to deliver end-to-end multimodal media workflows and code templates for "generation +…

    663 GitHub starsUsed in 1 repo~4.5k tokens
    Media & CreativeAuto-check passed

  • Gemini Interactions API

    Ayuilos/Miffan

    A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses…

    225 GitHub stars~4.6k tokensUpdated today
    Media & CreativeAuto-check passed

  • Fal AI

    mikeOnBreeze/cc-crossbeam

    This skill enables AI video generation from images AND text-to-speech voiceover generation using Fal.ai's API.

    293 GitHub stars~1.9k tokensUpdated 7 mo ago
    Media & CreativeAuto-check: notes

  • Collage B-Roll Video Maker

    imraywang/rayskills

    Turns a spoken line or a full topic into editorial-collage videos of halftone cut-outs assembled piece by piece, as 5-second B-roll or a narrated explainer.

    159 GitHub stars~2.6k tokensUpdated 18 days ago
    Media & CreativeAuto-check passed

  • Fal AI Media

    affaan-m/ECC

    Unified media generation via fal.ai MCP — image, video, and audio.

    277k GitHub starsUsed in 4 repos~1.9k tokens
    Media & CreativeAuto-check passed

  • Gemini

    Anil-matcha/awesome-muse-connectors

    Google Gemini media generation: Nano Banana images, Imagen 4 images, Veo video, TTS, model listing.

    1.3k GitHub stars~778 tokensUpdated 5 days ago
    Media & CreativeAuto-check passed

More from calesthio/OpenMontage

All 41 skills in this repo

  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 8 days ago
    Auto-check passed

  • Avatar Video

    calesthio/OpenMontage

    Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API.

    66k GitHub stars~1.6k tokensUpdated 8 days ago
    Auto-check passed

  • D3 Viz

    calesthio/OpenMontage

    Creating interactive data visualisations using d3.js. An agent skill from calesthio/OpenMontage.

    66k GitHub starsUsed in 3 repos~5.4k tokens
    Auto-check passed

  • Create Video

    calesthio/OpenMontage

    Create videos from a text prompt using HeyGen's Video Agent.

    66k GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed

  • Threejs World Generation

    calesthio/OpenMontage

    Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs.

    66k GitHub stars~2k tokensUpdated 8 days ago
    Auto-check passed

  • Video Edit

    calesthio/OpenMontage

    Edit videos locally using ffmpeg. An agent skill from calesthio/OpenMontage.

    66k GitHub stars~855 tokensUpdated 8 days ago
    Auto-check: notes

Works with

Categories

Questions about Gemini Omni

What does Gemini Omni do?

Generate and conversationally edit short videos with Google Gemini Omni Flash (gemini-omni-flash-preview). Gemini Omni is an agent skill from calesthio/OpenMontage. Generate and conversationally edit short videos with Google Gemini Omni Flash (gemini-omni-flash-preview).

When should I use Gemini Omni?

Gemini Omni fits situations like: iterating on a clip with natural-language edits instead of regenerating (make the phone invisible; keep everything else the same); generating 3-10s 720p clips with synthesized audio; rendered on-screen text.

How do I install Gemini Omni in Claude Code?

Run `npx skills add calesthio/OpenMontage --skill gemini-omni -a claude-code`. Or copy the skill folder (.agents/skills/gemini-omni in calesthio/OpenMontage) into .claude/skills/gemini-omni in your project. Claude Code loads it when a task matches its description.

How do I install Gemini Omni in Codex?

Run `npx skills add calesthio/OpenMontage --skill gemini-omni -a codex`. Or copy the skill folder (.agents/skills/gemini-omni in calesthio/OpenMontage) into .agents/skills/gemini-omni in your project. Codex loads it when a task matches its description.

Can I use Gemini Omni in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add calesthio/OpenMontage --skill gemini-omni -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gemini-omni, .gemini/skills/gemini-omni, .github/skills/gemini-omni and .opencode/skills/gemini-omni in your project.

What does Gemini Omni need to run?

Going by SKILL.md and its folder, Gemini Omni needs credentials named GOOGLE_API_KEY and GEMINI_API_KEY. Our summary lists: A credential in GEMINI_API_KEY; A credential in GOOGLE_API_KEY. Its frontmatter pre-approves these tools: Bash, Read, Write.

Does Gemini Omni access the network?

SKILL.md names 2 domains. As links in the text: ai.google.dev and blog.google. This is read from the text; nothing was executed.

Is Gemini Omni safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Gemini Omni use?

Gemini Omni is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gemini Omni use?

About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gemini Omni?

Skills that share tags, products or a category with Gemini Omni: Google Gemini Media (sundial-org/awesome-openclaw-skills, 663 stars), Gemini Interactions API (Ayuilos/Miffan, 225 stars), Fal AI (mikeOnBreeze/cc-crossbeam, 293 stars) and Collage B-Roll Video Maker (imraywang/rayskills, 159 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gemini Omni?

calesthio (a GitHub user) maintains it in calesthio/OpenMontage, which has 65,930 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 3, 2026.

Source: calesthio/OpenMontage on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.