AI Skills Catalog
Skills pack Tools

Video Conform

Prepare and optionally execute an ffmpeg delivery pass for a supplied video or frame render. Can mix audio, write captions and check duration and loudness; defaults to showing the plan.
SKILL SCORE78How it is scored
VerifiedFreeMIT

Works with

Packaged from the source skill for Claude, Codex and 4 more.

About this skill

Video Conform handles the delivery stage of a short-video workflow. Its Python wrapper can start from a supplied video or frame-render manifest, combine the available audio and scene data, and prepare an ffmpeg command. Encoding is a separate explicit execution mode rather than the default.

Use this skill when

  • A reviewed cut needs a delivery file with consistent audio handling and captions.
  • A frame sequence and scene data need to become a final video without overlooking missing frames.
  • You want to inspect the proposed encoding and quality checks before running them.

What it can do

The wrapper supports loudness presets, voice-and-music mixing, scene-based caption output and optional burned captions. It checks selected duration and loudness results after encoding and can refuse incomplete frame inputs. The package can also accept an independent existing video, so the sibling director and animatic tools are not required for every use.

ffmpeg and ffprobe must be installed separately. Caption timing depends on the supplied scene and narration, and a numerical loudness check does not replace listening to the mix. Very short clips need particular attention to normalization results. Inspect subtitle legibility, sync, playback and platform requirements before delivery; this is not a guarantee that every channel will accept or correctly label the file.

Typical workflows

  1. Inspect the plan: provide the cut or render manifest and audio inputs, select a suitable preset and review the proposed command before execution.
  2. Conform the approved media: encode in an authorized output location, retain caption output and inspect any failed quality gate.
  3. Review the delivery: listen to the mix, inspect captions and duration, and check the final file on the intended device or publishing channel.

What is inside the skill

Section headings from the original SKILL.md (about 304 words of instructions). Read the full text in the source repository before installing.

  1. Workflow
  2. Delivery checklist

Bundled files

  • references/delivery_specs.md
  • scripts/conform.py
  • LICENSE

Example prompts

  • Prepare a delivery plan for this approved video, scene JSON and recorded voice track. Show the ffmpeg command and expected caption artifacts without running the encode.
  • Conform this frame-render manifest with the supplied voice-over and music after I approve the plan. Reject missing frames, keep captions as a sidecar and report any duration or loudness check that fails.
  • Review this short delivery clip after encoding. Check caption timing and legibility, listen for voice-versus-music balance and explain whether a normalization failure needs new inputs rather than repeated retries.

How to install Video Conform

Claude Packaged
  1. Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
  2. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
  3. For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
  4. Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
More about skills for Claude
Codex Packaged
  1. Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
  2. Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
  3. Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
  4. AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
More about skills for Codex
GPT Packaged
  1. Download the GPT package from the skill page.
  2. Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
  3. Upload the bundled reference files as knowledge so the GPT can consult them.
  4. Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
More about skills for GPT
Gemini Packaged
  1. Download the Gemini package from the skill page.
  2. For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
  3. Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
  4. Test a matching task and verify the referenced tools and files are available.
More about skills for Gemini
Cursor Packaged
  1. Download the Cursor package from the skill page.
  2. Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
  3. Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
  4. Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
More about skills for Cursor
OpenCode Packaged
  1. Download the OpenCode package from the skill page.
  2. Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
  3. Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
  4. Start OpenCode in the project and test a matching task with the model and permissions you use.
More about skills for OpenCode

Permissions & security

Low risk

Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method

Read project files
Write generated skill files

Video Conform FAQ

What does the Video Conform skill do?

Prepare and optionally execute an ffmpeg delivery pass for a supplied video or frame render. Can mix audio, write captions and check duration and loudness; defaults to showing the plan.

Which AI agents can use Video Conform?

Packages for Claude, Codex and 4 more are built from the same source instructions.

How do I install Video Conform in Claude?

Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.

Who made Video Conform and what is the license?

Video Conform is published by Alireza Rezvani under the MIT license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/video/skills/video-conform. The catalog keeps the original attribution.

What permissions does Video Conform need?

Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.

Video Conform Skill — Alireza Rezvani | AI Skills Catalog