oma-video
Short-form, explainer, and demo video generation via a key-optional 3-tier router. Composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a vendored Remotion compositor into reproducible run directories. Routes three modes — shorts/reels (9:16), explainer (16:9 README/code/data), and demo/walkthrough (screen capture, incl. supervised headed web-app capture of any URL). Use for video, shorts, reels, short-form, demo, explainer, walkthrough, screencast, web capture, video generation, 영상, 숏폼, 쇼츠, 릴스, 데모, 설명 영상.
npx skills add first-fluke/oh-my-agent --skill oma-video --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates finished .mp4 videos through a key-optional, 3-tier provider router for shorts, explainer, and demo videos. It composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a vendored Remotion compositor into reproducible run directories. It supports three modes: shorts/reels (9:16), explainer (16:9), and demo/walkthrough (screen capture, including supervised headed web-app capture of any URL). Outputs include a run directory with script.json, timing.json, render-spec.json, audio/, visuals/, captions.srt/.vtt, and the final <mode>-<slug>.mp4 plus manifest.json.
How it works
- Entry validates the brief and mode, infers plan if needed, and selects a mode-specific pipeline (shorts, explainer, or demo).
- For demo via file: requires a capture path; for demo via web: opens a headed browser to record a URL with a human driving the flow; if Playwright is unavailable or no interactive TTY, falls back to guided protocol.
- Resolves defaults from config and flags, then executes a pipeline: script -> (voice and/or visuals and captions) -> render-spec -> compositor -> final mp4.
- Writes deterministic assets and manifests: script.json, timing.json, render-spec.json, audio/, visuals/, captions.srt/.vtt, manifest.json, and the rendered <mode>-<slug>.mp4.
- Uses vendored Remotion for compositing and relies on providers like oma-voice, oma-image, oma-slide, with optional Pexels/Pixelle/RunningHub when keys are present.
When to use it
- When you need a short-form video (shorts/reels) from a topic or brief, using --mode shorts and 9:16 aspect.
- When you need an explainer from a README, code, or data, using --mode explainer and 16:9 (or 9:16).
- When you need a demo or walkthrough from a screen capture file or a supervised headed web capture of a URL, using --mode demo with --source file or --source web.
- When you want deterministic re-renders from render-spec.json or to share video-generation infrastructure across skills.
What it can touch
- Tools:
oma video generate,oma video doctor,oma video render. - Providers/adapters: AgentScript, oma-voice, oma-image, oma-slide, Pexels, Pixelle, oma-captions, Cap, Remotion, MPT.
- Vendored Remotion at
resources/remotion/and related config files.
Caveats
- Web capture is headed and human-driven for demo/web captures; login flows are user-performed and not automated.
- Outputs are written to
.agents/results/videos/<timestamp>-<shortid>-<mode>/and are not auto-pruned. - Deterministic outputs depend on a render-spec and fonts; if fonts are unavailable, rendering may fall back to system fonts.
# Video Agent - Short-form, Explainer & Demo Router ## Scheduling ### Goal Generate finished `.mp4` videos through a key-optional, 3-tier (CLI-first / MCP / guided) provider router while preserving deterministic asset buses (script -> timing -> render-spec), reproducible manifests, cost controls, and capture-path safety. ### Intent signature - User asks for a short-form video, shorts/reels clip, TikTok/YouTube Short, explainer, demo, walkthrough, or screencast. - User wants a topic, README, code, or data turned into a narrated, captioned video. - Another skill needs shared video-generation infrastructure (script -> assets -> render). ### When to use - Generating short-form video (shorts / reels) from a topic or brief (`--mode shorts`, 9:16) - Generating an explainer from a README, code, or data set (`--mode explainer`, 16:9 / 9:16) - Producing a demo / walkthrough from a screen capture file (`--mode demo --source file`, 16:9) - Supervised headed web-app capture of any URL (`--mode demo --source web --url <url>`) — a human drives the on-screen flow; the tool only opens a headed browser and records. Example categories are equal and illustrative only: demo, walkthrough, onboarding cli
- Scheduling
- Goal
- Intent signature
- When to use
- When NOT to use
- Expected inputs
- Expected outputs
- Dependencies
- Control-flow features
- Structural Flow
- Entry
- Scenes
- Transitions
- Failure and recovery
oma video doctor oma video generate "<brief>" --mode shorts --aspect auto --captions tiktok --format json oma video generate "explain this project" --mode explainer --aspect 16:9 --seed 42 --out ./out oma video generate "feature walkthrough" --mode demo --capture <absolute-path>.mp4 oma video render .agents/results/videos/20260603-143052-ab12cd-shorts
What does the oma-video skill do?
Short-form, explainer, and demo video generation via a key-optional 3-tier router. Composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a vendored Remotion compositor into reproducible run directories. Routes three modes — shorts/reels (9:16), explainer (16:9 README/code/data), and demo/walkthrough (screen capture, incl. supervised headed web-app capture of any URL). Use for video, shorts, reels, short-form, demo, explainer, walkthrough, screencast, web capture, video generation, 영상, 숏폼, 쇼츠, 릴스, 데모, 설명 영상.
How do I install it?
Run `npx skills add first-fluke/oh-my-agent --skill oma-video --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From first-fluke/oh-my-agent, a repository with 1,204 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.