agentleFS
Galbaz1Galbaz1/video-research-mcp/skills/video-generation/SKILL.md

video-generation

Skill23 starsChanged 39 days agoMITView on GitHub

Generate AI video clips with an available provider, including image-to-video, reference assets, or extensions. Use for generation requests, not video analysis or FFmpeg editing.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use consulting-analysis, surprise-me and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HK-hubSkill

    consulting-analysis

    Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.

    Also in 4 projects that use this

  • stophobiaSkill

    surprise-me

    Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".

    Also in 3 projects that use this

  • HK-hubSkill

    ppt-generation

    Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

    Also in 3 projects that use this

  • stophobiaSkill

    github-deep-research

    Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

    Also in 3 projects that use this

  • MicrosoftSkill

    podcast-generation

    Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

    Also in 3 projects that use this

  • VercelSkill

    vercel-deploy

    Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.

    Also in 3 projects that use this

  • +1 more from HK-hub

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify capability: Read provider-details.md for the current provider snapshot, then check live model availability, input constraints, …

    line 13
  2. Distinctive:

    Generate one draft: Keep its prompt, model, settings, reference paths, operation ID, and output together.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Video Generation

This plugin packages production guidance; it does not bundle a Veo MCP server or a video-generation script. Discover the connected provider and read its current tool schema before calling it. If none is available, preserve a generation-ready brief and identify the missing provider.

Workflow

  1. Fix the brief. Record subject, motion, camera, duration, aspect ratio, audio, destination, and supplied assets. Use an anchor image when continuity matters; text-only generation is also supported where the provider permits it. Completion: one bounded shot specification with explicit acceptance criteria.
  2. Verify capability. Read provider-details.md for the current provider snapshot, then check live model availability, input constraints, pricing, and the actual tool/API schema. Do not translate a provider feature into an invented MCP tool name. Completion: a supported request and an authorized spend/attempt limit.
  3. Generate one draft. Keep its prompt, model, settings, reference paths, operation ID, and output together. A running operation is pending; poll that operation rather than launching a duplicate. Completion: terminal result or preserved provider failure.
  4. Inspect the artifact. Download the successful output, probe duration/resolution/audio with ffprobe, inspect a contact sheet and motion playback. Check subject identity, object integrity, timing, and audio against the brief. Completion: evidence for every acceptance criterion, including failures.
  5. Repair only a measured defect. Change one variable, retain the earlier output, and use at most one repair attempt within the existing budget. Stop on a repeated infrastructure failure, exhausted budget, or terminal refusal. Completion: an accepted local clip or a precise unresolved defect.

For an approved draft, generate a final only if the requested delivery settings require it. Re-check the final artifact; a winning draft does not prove the final has the same quality. For multi-shot continuity and assembly, use video-production; for encoding use ffmpeg-production.

Prompt Template

[Subject and setting]. [One primary action over the requested duration]. Camera [movement and framing]. Light comes from [physical source]. Maintain [specific reference features]. Audio: [dialogue, ambience, or intended silence]. Deliver [aspect ratio and supported resolution].

Include exact spoken words when dialogue matters. Preserve the user's exclusions using a supported negative-prompt field or clear instructions. Reference images guide appearance; they do not guarantee identity or text fidelity.

Delivery

Return the playable clip path, inspected properties, provider/model, reference provenance, and remaining defects. Distinguish prepared, pending, failed, and verified local output. Publication requires the user's destination authority.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.