agentleFS
holon-runholon-run/holon/skills/video-production/SKILL.md

video-production

Skill194 starsChanged 5 days agoApache-2.0View on GitHub

Assemble existing local images, videos, audio and subtitles into preview/final videos with FFmpeg, technical QC and provenance. Use for local media production, not publishing or programmatic Remotion animation.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use email-marketing, backend-development and 8 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.
  • claude-office-skillsSkill

    email-marketing

    Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics

    Also in 3 projects that use this

  • mrgoonieSkill

    backend-development

    Build robust backend systems with modern technologies (Node.js, Python, Go, Rust), frameworks (NestJS, FastAPI, Django), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), testing strategies, security best practices (OWASP Top 10), performance optimization, scalability patterns (microservices, caching, sharding), DevOps practices (Docker, Kubernetes, CI/CD), and monitoring. Use when designing APIs, implementing authentication, optimizing database queries, setting up CI/CD pipelines, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

    Also in 3 projects that use this

  • nilssonrSkill

    seo

    Full SEO workflow for auditing pages and creating SEO-optimized content. Provides checklists with educational explanations aligned with Google Search Central documentation.

    Also in 3 projects that use this

  • SupabaseSkill

    copywriting

    Write or audit UI copy (buttons, labels, empty states, error messages, tooltips, form text) anywhere in the monorepo. Load it before shipping or reviewing any user-facing text — including when copy is incidental to the task, like a new feature that adds buttons, toasts, dialogs, or validation messages.

    Also in 3 projects that use this

  • AnthropicSkill

    design-system

    Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    design

    Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before rendering, establish audience, script/storyboard, asset order and timing, aspect ratio, resolution, audio/caption requirements and …

    line 10
  2. Distinctive:

    Keep that editorial production checklist alongside the project.

    line 14
  3. Distinctive:

    Use the script below for straight-cut, 16:9 local assembly.

    line 16
  4. Distinctive:

    Write a UTF-8 JSON manifest.

    line 29
  5. Distinctive:

    Run from this skill directory (or use an absolute script path):

    line 42
  6. Distinctive:

    Use ordinary standalone local media, not playlists or externally linked media.

    line 52
  7. Distinctive:

    Do not process untrusted media without an appropriately isolated environment.

    line 53
  8. Distinctive:

    Run that test command from the repository root.

    line 90

“Common” is measured: kept by at least 6 in 10 of the 20 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 Production

Production contract

Before rendering, establish audience, script/storyboard, asset order and timing, aspect ratio, resolution, audio/caption requirements and intended delivery. Inventory local sources, ownership/license/consent, and missing assets. Do not invent provenance or assume that a technical pass establishes usage rights. Keep that editorial production checklist alongside the project.

Use the script below for straight-cut, 16:9 local assembly. For programmatic animation use the separately installed official Remotion skill; this skill does not install Remotion or provide a rendering backend. Generating images, video, voice or TTS is an optional external capability: verify availability, consent, cost and upload permission first. Missing generation capability is not a reason to block assembly when local assets suffice. Never publish automatically.

Local execution

Requires Python 3.10+, ffmpeg with libx264/AAC and ffprobe on PATH. Report missing binaries/codecs explicitly; do not silently install, substitute a cloud service, or claim an unavailable render succeeded.

Write a UTF-8 JSON manifest; relative paths resolve against its directory:

{
  "clips": [
    {"path": "title.png", "kind": "image", "duration": 2},
    {"path": "demo.mp4", "kind": "video", "duration": 3}
  ],
  "audio": "narration.wav",
  "subtitles": "captions.srt"
}

Run from this skill directory (or use an absolute script path):

python3 scripts/produce.py /project/manifest.json /project/preview-v1 --mode preview
python3 scripts/produce.py /project/manifest.json /project/final-v1 --mode final

Output directories must be new. Original assets are not overwritten. The helper accepts PNG/JPEG stills, MP4/MOV videos, optional WAV/MP3/M4A audio, and UTF-8 SRT captions only. Unknown manifest fields and unsupported extensions are errors. Use ordinary standalone local media, not playlists or externally linked media. Do not process untrusted media without an appropriately isolated environment; this helper is not a sandbox.

Clips start at time zero, cut at their requested positive duration, and are scaled/padded (not cropped) to 640×360 preview or 1280×720 final at 25 fps, H.264/yuv420p. Each duration is rounded to the nearest 25 fps frame (ties up, minimum one frame); audio/caption validation and muxing use that same timeline, recorded in the report. Source clip audio is explicitly removed; the single optional audio track replaces it, must cover the whole timeline, and is trimmed to length and encoded to AAC. There is no mixing, transition, animation, trim-offset or portrait support. Do not silently convert an unsupported request into this contract: adapt the workflow explicitly. SRT cues must be ordered, nonoverlapping and within the timeline; captions are selectable MP4 subtitles, not burned in. Confirm player/platform compatibility.

Review and delivery

Each output directory contains the MP4 and report.json: source paths/SHA-256, manifest, tool versions, output hash, ffprobe metadata and full audio/video decode result. Hash provenance identifies files; add original source URLs, licenses and generation details to the production checklist when known.

Inspect the preview visually and audibly: framing, pacing, text legibility, caption timing, pronunciation, transitions, silence and clipping. Technical QC checks streams, dimensions/pixel format, exact video frame count and duration, and complete decoding; it does not prove editorial quality, loudness compliance, accessibility or rights. Resolve issues before final rendering and inspect the final too. Deliver source manifest/checklist, preview/final and QC report, noting limitations and any unverified requirement. Publication requires separate operator authorization.

Offline fixture verification (creates and cleans temporary assets):

python3 -m unittest discover -s skills/video-production/tests -v

Run that test command from the repository root.

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.