oma-video
Skill223 starsChanged 28 days agoMITView on GitHub
Create short, explainer, or recorded-demo videos through the OMA video CLI. Use for scripts, narration, assets, composition, and video delivery.
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use this skill for a short/reel, README or code explainer, or demo walkthrough.
- Very specific: line 22
Use oma-image for a still image, oma-slide for a deck, oma-voice for audio only, and oma-explanation for an interactive HTML explainer.
- Distinctive: line 53
Ask only when it changes the result: an ambiguous mode/source, a required demo recording, or a cost confirmation.
- Very specific: line 65
Keep output and capture paths inside $PWD unless external output is explicitly allowed.
- Very specific: line 72
Before a paid provider action or rerun, compare the planning estimate with cost.guardrail_usd or --max-usd and reuse existing spend …
- Distinctive: line 80
Keep run directories. Never auto-prune a user’s video artifacts.
- Very specific: line 109
Read video and asset paths from the manifest.
- Distinctive: line 159
Do not run a live render merely to test documentation or a mock-only branch.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Video Router
Scheduling
When to use
Use this skill for a short/reel, README or code explainer, or demo walkthrough.
| Request | Mode | Default aspect | Required source |
| Short, reel, social clip | shorts | 9:16 | Topic or brief |
| README, code, data explanation | explainer | 16:9 | Topic or source path |
| Demo or walkthrough | demo | 16:9 | Human recording via --capture |
When NOT to use
Use oma-image for a still image, oma-slide for a deck, oma-voice for
audio only, and oma-explanation for an interactive HTML explainer. Editing an
existing finished video and live streaming are out of scope.
Structural Flow
Inputs are a brief plus optional mode, aspect, locale, captions, visual, voice,
music, duration, compositor, capture path, and seed. Outputs live in
.agents/results/videos/<timestamp>-<shortid>-<mode>/:
script.json,timing.json, andrender-spec.jsonform the deterministic asset bus.- Captions and acquired audio/visual assets are recorded in
manifest.jsonwith hashes, providers, cost, warnings, and exit code. - A successful real render contains
<mode>-<slug>.mp4, an encoded video stream, and a positive ffprobe duration.
OMA_VIDEO_MOCK=1 is a test harness only. It can create deterministic text
placeholders with an .mp4 name; those files are never a user deliverable. A
missing HyperFrames/MPT toolchain, an un-authored composition, a render error, or
an invalid video fails with diagnostics and leaves the script/render spec for
recovery.
Decide and confirm
Infer mode when clear: short/reel -> shorts; README/code/data/explain ->
explainer; demo/walkthrough/capture -> demo. For a one-line request, state
the inferred mode, aspect, duration, visual strategy, captions, locale, and
voice/music before invoking. Do not make the user complete a questionnaire
when those defaults are clear.
Ask only when it changes the result: an ambiguous mode/source, a required demo recording, or a cost confirmation. Respect an explicit mode, aspect, duration, captions, or voice verbatim.
For a demo, a human records the screen and controls login. --source web --url
provides context only; it never automates login or starts a recorder. Without
--capture, return guided capture instructions and stop.
Logical Operations
Guardrails
- Keep output and capture paths inside
$PWDunless external output is explicitly allowed. Validate capture formats and copy external assets into the run directory. Mask URL query/hash tokens in logs and manifests. - Provider configuration is key-optional: use the configured chain. Paid providers require their environment key and the cost guardrail. Local fallbacks may replace voice, visuals, captions, or music; record coverage in warnings. A compositor failure is never a fallback video.
- Before a paid provider action or rerun, compare the planning estimate with
cost.guardrail_usdor--max-usdand reuse existing spend authorization. In an active OMA video workflow, record the actual paid, limited, fallback, or declined choice before executing it (execution protocol Step 2). Pass--yesorOMA_VIDEO_YES=1only for an already authorized paid action; the event does not grant permission. - Respect
limits.max_duration_sec(180) andlimits.max_scenes(40). Cancel subprocess work on SIGINT/SIGTERM. - Keep run directories. Never auto-prune a user’s video artifacts.
--dry-runwrites only planning artifacts and does no provider render. It does not prove an MP4 exists.
Canonical command path
# Plan or create the asset bus. Supply --script whenever an agent authored it.
oma video generate "Jeju coffee" --mode shorts --aspect 9:16 \
--captions tiktok --script ./script.json --output json
# Deterministic planning only; no real render or provider work.
oma video generate "explain this project" --mode explainer --seed 42 --dry-run
# Human-recorded demo input.
oma video generate "feature walkthrough" --mode demo --capture <absolute-path>.mp4
# Scaffold the per-run HyperFrames project, author index.html as instructed,
# then render and validate the encoded output.
oma video compose <runDir> --output json
oma video render <runDir> --output json
# Diagnose required toolchains without changing a run.
oma video doctor
oma video provider listoma video generate --output json returns
{exitCode, runDir, manifestPath, scriptPath, renderSpecPath, warnings, error}.
Read video and asset paths from the manifest; the JSON envelope has no
outputs field.
Failure and recovery
- Missing HyperFrames composition:
oma video compose <runDir>prepares the project and authoring contract. Author<runDir>/hyperframes/index.htmlusing the generatedAUTHORING.md, then invokeoma video render <runDir>. The command lints, renders, and ffprobes the output. Fix a reported composition or toolchain failure and re-run; return a failure report when it cannot render. - Missing MPT toolchain:
--compositor mptrequires the installed checkout, its virtual environment, and ffmpeg. Useoma video doctor --install-mptwhen setup is authorized and available. MPT setup failures, driver failures, and non-video output fail with the diagnostic; they do not write a placeholder MP4.
Success means all asset schemas and manifest hashes validate and a real MP4 passes video-stream and duration validation. A partial success may use a key-free visual, timing, caption, or music fallback, but it still requires that real video validation.
References
Conditional resources
Load only what the task needs:
resources/execution-protocol.mdfor the full ordered pipeline, failure mapping, and JSON reporting rules.resources/vendor-matrix.mdbefore changing providers, keys, cost, or fallback order.resources/script-schema.mdwhen authoring or validating--scriptinput.resources/prompt-tips.mdwhen turning a brief into scene prompts.resources/hyperframes-authoring/README.mdand the selected mode guide before writingindex.html.resources/checklist.mdbefore handing a real video to a user.
Verification
For CLI/runtime changes, add a regression test for the affected success and failure paths. At minimum run the focused Vitest files, for example:
cd cli
bunx vitest run commands/video/providers/compositor.test.ts \
commands/video/orchestrator.test.ts
bunx biome check commands/video/providers/compositor.ts \
commands/video/providers/compositor.test.tsDo not run a live render merely to test documentation or a mock-only branch.
Other versions3 projects use a version of this.
Word for word · 2
- first-fluke/oh-my-ag★ 1.3k100% same
- first-fluke/oh-my-agent★ 1.3k100% same
Edited · 0
None found.
Wrote their own version · 1
- deathrashed/agents★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository131 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/backend.mdcCursor rule
- .cursor/rules/branching-strategy.mdcCursor rule
- .cursor/rules/build-guide.mdcCursor rule
- .cursor/rules/commit.mdcCursor rule
- .cursor/rules/database.mdcCursor rule
- .cursor/rules/debug.mdcCursor rule
- .cursor/rules/design.mdcCursor rule
- .cursor/rules/design-tokens-guide.mdcCursor rule
- .cursor/rules/dev-workflow.mdcCursor rule
- .cursor/rules/frontend.mdcCursor rule
- .cursor/rules/i18n-arb.mdcCursor rule
- .cursor/rules/i18n-guide.mdcCursor rule
- .cursor/rules/infrastructure.mdcCursor rule
- .cursor/rules/lint-format-guide.mdcCursor rule
- .cursor/rules/market.mdcCursor rule
- .cursor/rules/mobile.mdcCursor rule
- .cursor/rules/preferred-editing-tools.mdcCursor rule
- .cursor/rules/quality.mdcCursor rule
- .cursor/rules/test-guide.mdcCursor rule
- oma-academic-writingSkill
- oma-architectureSkill
- oma-backendSkill
- oma-brainstormSkill
- oma-coordinationSkill
- oma-dbSkill
- oma-debugSkill
- oma-deepsecSkill
- oma-designSkill
- oma-dev-workflowSkill
- oma-docsSkill
- oma-explanationSkill
- oma-frontendSkill
- oma-hwpSkill
- oma-imageSkill
- oma-marketSkill
- oma-mobileSkill
- oma-observabilitySkill
- oma-orchestrationSkill
- oma-pdfSkill
- oma-pmSkill
- oma-qaSkill
- oma-recapSkill
- oma-refactorSkill
- oma-scholarSkill
- oma-scmSkill
- oma-searchSkill
- oma-skill-creationSkill
- oma-slideSkill
- oma-tf-infraSkill
- oma-translationSkill
- oma-voiceSkill
- architectureSkill
- brainstormSkill
- commitSkill
- convertSkill
- coordinate-proSkill
- coordinateSkill
- debugSkill
- deepinitSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

