0xsline/OpenChatCut / src/agent/skills/video-gen
video-gen
VerifiedAI video generation via Fal.ai, Seedance 2.0, Kling, MiniMax Hailuo, xAI Grok Imagine, Google Gemini Omni, OFox, and Agnes Video. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation, multi-shot, or generatively editing / extending an existing clip.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.8 KB |
| references/agnes-video.md | markdown | 980 B |
| references/fal.md | markdown | 955 B |
| references/gemini-omni.md | markdown | 2.1 KB |
| references/grok-imagine-video.md | markdown | 1.6 KB |
| references/hailuo.md | markdown | 7.4 KB |
| references/kling.md | markdown | 13.0 KB |
| references/ofox.md | markdown | 2.6 KB |
| references/seedance2.md | markdown | 13.0 KB |
references/gemini-omni.md
View on GitHub# Google Gemini Omni Flash (`gemini-omni`)
Video generation via Google’s Gemini Omni Flash Interactions API.
Auth: `GEMINI_API_KEY` (same key as Nano Banana image). Optional
`GEMINI_BASE_URL` (default `https://generativelanguage.googleapis.com`).
Configured model id comes from Settings (`GEMINI_OMNI_VIDEO_MODEL`),
default `gemini-omni-1.2-flash`.
## Wired capabilities
- **Text-to-video**, **image-to-video** (`firstFrame`), **first+last frame**
interpolation, and up to **6 `refImages`** (mutually exclusive with frame
anchors).
- **Not wired yet:** conversational multi-turn edit/extend
(`previous_interaction_id`), uploaded `refVideos` / `refAudios`, Kling
multi-shot / Seedance-only controls.
- **Aspect ratio** (`ratio`): `16:9` (default), `9:16` only.
- **Resolution** (`resolution`): `360p`, `720p` (default), `1080p`, `4k`.
- **Duration** (`durationSeconds`): optional whole seconds, 3–15, sent as the
API's native `duration`. First+last frame interpolation allows 3–10. When
omitted, Omni makes a 10-second video. A set duration overrides any length
written in the prompt.
- Generated videos typically include audio; there is no separate audio toggle
in this integration.
- The job is asynchronous from the agent’s point of view: `submit_video`
returns a `jobId`; wait with `track_progress` like other vendors. The
provider makes one Interactions request, then waits for Google to finish
processing the result file before downloading it.
## Prompt guidance
Be concrete: subject, motion, environment, lighting, camera. For a single
continuous shot, say so explicitly (“single unbroken continuous shot, no cuts”).
Put negatives in the prompt (“no dialogue”, “no text overlays”).
## Errors
- Missing `GEMINI_API_KEY`: configure it under Settings → AI Generation → Video
→ Google · Gemini Omni Flash (or Image → Nano Banana).
- `gemini-omni does not support ratio …`: only `16:9` / `9:16`.
- Frame + `refImages` together: pick one mode; do not combine.
- `first+last frame interpolation supports durationSeconds 3 to 10`: shorten
the clip or drop one of the frames.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |