Video Generation
- 378 installs
- 19 repo stars
- Updated July 27, 2026
- postplusai/postplus-skills
Classify short-form and long-form video requests before your agent builds provider-ready plans and hands off to PostPlus runners.
About
Video Generation is a PostPlus routing-contract skill that acts as the controller layer for agent-driven video creation. Solo and indie builders use it when a user asks for a clip, storyboard reel, UGC piece, podcast visual, reference-based video, talking-head, image-to-video, text-to-video, or research-handoff video and the agent must decide what kind of work this is before anyone hits a provider API. The skill reads the natural-language intent, maps it to a task class, and determines whether references or a storyboard must be resolved upstream. It deliberately does not submit jobs; that keeps failures and cost surprises out of casual chat turns. After classification, it routes approved structure to video-request-architect and execution-ready payloads to seedance-submitter or video-batch-runner depending on batch versus single-shot needs. If the user only wants transcription, subtitles, semantic media analysis, or edit decisioning, media-router is the correct entry point instead. If architecture is already signed off, builders should bypass this controller and call a runner directly. The pattern fits content creators and product teams who wire Claude Code or Cursor into generative
- Classifies requests into task classes (simple clip, storyboard, UGC, podcast clip, talking-head, image-to-video, text-to
- Enforces core boundary: classify and route only—never submits generation jobs itself
- Decides when reference assets or storyboard resolution must run before architecture
- Hands approved structure to video-request-architect and submit-ready plans to seedance-submitter or video-batch-runner
- Explicit do-not-use rules: media analysis-only work goes to media-router; already-approved plans skip straight to submit
Video Generation by the numbers
- 378 all-time installs (skills.sh)
- +42 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #451 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/postplusai/postplus-skills --skill video-generationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 378 |
|---|---|
| repo stars | ★ 19 |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | postplusai/postplus-skills ↗ |
What it does
Classify short-form and long-form video requests before your agent builds provider-ready plans and hands off to PostPlus runners.
Files
Video Generation
Use When
- The desired final asset is a generated video or video render plan.
- The request may be a simple clip, storyboard, UGC, podcast clip, reference
video, talking-head, image-to-video, text-to-video, or research handoff.
- The next decision is task class, request architecture, and execution handoff.
Do Not Use When
- The user only needs transcription, subtitles, semantic analysis, or edit
decisioning. Use media-router.
- The request architecture is already approved and provider-ready. Use
seedance-submitter or video-batch-runner.
- The task is image-only or audio-only.
Core Boundary
This is the video generation controller. It does not submit jobs.
It must:
1. classify the video task, 2. choose whether references or storyboard must be resolved, 3. hand approved structure to video-request-architect, 4. hand submit-ready plans to seedance-submitter or video-batch-runner.
Task Classes
| Task class | Use when | Required handoff |
|---|---|---|
simple_clip | one short text/image-to-video clip | video-request-architect |
storyboard | panel sequence or contact sheet drives the clip | storyboard-grid-writer, then video-request-architect |
ugc | creator-style product or app video | ugc-flow unless it is one isolated clip |
podcast | voice-led clip, audiogram, or speaker segment | audio-generation, then video architecture |
reference_video | benchmark video controls rhythm or motion | reference-decode and reference-contract-builder |
research_handoff | research/benchmark becomes a generation request | benchmark-to-brief, then video-request-architect |
Routing Table
| If not video-generation | Send to |
|---|---|
| Understanding or subtitles first | media-router |
| Image asset must be created first | image-generation |
| Voice or dub must be created first | audio-generation |
| Product-to-UGC pipeline | ugc-flow |
| Provider-ready request exists | seedance-submitter or video-batch-runner |
Three-Layer Boundary
- Controller: classify task and produce the handoff. It must not submit.
- Architect:
video-request-architectbuilds provider-agnostic structure. It
must not call providers.
- Runner:
seedance-submitterorvideo-batch-runnervalidates and executes
normalized requests. It must not make creative strategy decisions.
Output Shape
Return:
taskClassrequiredUpstreamSkillsarchitectureHandoffrunnerHandoffreferencePolicymustNotDo
Stop Conditions
- Stop when required user intent, source evidence, or owned input artifacts are
missing and guessing would change the result.
- Do not ask a runner to infer hook, persona, or reference meaning.
- If an owned CLI or script command fails, report the exact error and stop. Do
not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
Public Command Boundary
- Choose the smallest matching command or workflow from the user input and run
it directly.
- If an owned CLI or script command fails, report the exact error and stop. Do
not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
- This public skill is instruction-driven. Produce the controller handoff
artifact directly from the available evidence.
- Do not call private provider/runtime paths or unpublished local tools.
- If the CLI returns a quote-confirmation challenge, run
postplus quote confirm --json --challenge-file <challenge.json>and retry with the returned token.
Related skills
Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k
Ai Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665Ai Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665Ai Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665Remotion RenderRender videos programmatically using React components and Remotion framework441k665
Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665FAQ
Is Video Generation safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.