Agent skill

Media Production

by WrongStack in WrongStack/WrongStack

Create and process finished videos with Remotion, Motion Canvas, Manim, FFmpeg or an available AI video provider.

MITAuto-check passedMedia & Creative

Install Media Production

skills CLI
$ npx skills add WrongStack/WrongStack --skill media-production -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install WrongStack/WrongStack media-production --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/media-production .claude/skills/media-production && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
media-production
GitHub stars
371
Token cost
~1k tokens
SKILL.md length
435 words
Files
3 (incl. references)
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

Create and process finished videos with Remotion, Motion Canvas, Manim, FFmpeg or an available AI video provider.

  • Works in 6 steps: Inspect the existing media project,… → Choose the engine by the intended… → Make time deterministic. Render from… → …
  • Producing a video
  • SKILL.md covers Selection card, Overview, Rules and Choose and load, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Media Production is an agent skill from WrongStack/WrongStack. Create and process finished videos with Remotion, Motion Canvas, Manim, FFmpeg or an available AI video provider. Use when producing a video, UI demo, explainer, subtitles, narration timeline or format conversion; select the renderer from the content rather than defaulting every video to one engine.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/ffmpeg.md` and `references/remotion.md`).

It sits in Media & Creative, covering Video production, AI video generation and Transcription. It works with Remotion, Manim and FFmpeg. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.

When your agent uses it

  • Producing a video
  • Narration timeline
  • Format conversion
  • Select the renderer from the content rather than defaulting every video to one engine

Example prompts

  • “/media-production”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the existing media project, renderer, lockfiles and installed codecs.
  2. Choose the engine by the intended content. Multiple engines can contribute
  3. Make time deterministic. Render from frames or a controlled timeline, never
  4. Specify dimensions, duration, fps, safe areas, delivery codec/container,
  5. Inspect rights and renderer/provider licensing. Local rendering consumes
  6. Render into a task-owned output directory. Preserve accepted masters and

What it can do on your machine

Read from SKILL.md and the folder at commit a744bdc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Media Production loads about 1k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 435 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from WrongStack/WrongStack at commit a744bdc, republished under its MIT licence (© WrongStack). 435 words, ~1,043 tokens.

Download SKILL.mdSave it as .claude/skills/media-production/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
media-production
description
Create and process finished videos with Remotion, Motion Canvas, Manim, FFmpeg or an available AI video provider. Use when producing a video, UI demo, explainer, subtitles, narration timeline or format conversion; select the renderer from the content rather than defaulting every video to one engine.
version
1.2.1
required-capabilities
filesystem.read, filesystem.write
optional-capabilities
verification.run, web.research
trigger
producing a video, UI demo, explainer, subtitles, narration timeline or format conversion; select the renderer from the content rather than defaulting every…
metadata.routing-group
media

Media Production

Selection card

  • Task: Produce Remotion videos or assemble and encode media. / TR: Remotion videosu üret veya medyayı birleştirip kodla.
  • Start: Identify the existing engine, scene, timeline and delivery format.
  • Finish: apply the acceptance checks below; report observed results and unresolved constraints.

Overview

Deliver a playable video with reproducible source and observed output checks. Latest stable targets checked 2026-10-09: Remotion 4.0.534, Motion Canvas 3.17.2, Manim Community 0.22.0 and FFmpeg 9.0.2. Refresh these before a new setup.

Rules

  1. Inspect the existing media project, renderer, lockfiles and installed codecs. Preserve an established pipeline unless a change is requested or necessary.
  2. Choose the engine by the intended content. Multiple engines can contribute shots, but normalize their framerate, dimensions and audio before assembly.
  3. Make time deterministic. Render from frames or a controlled timeline, never wall-clock timers, unseeded randomness or live network state.
  4. Specify dimensions, duration, fps, safe areas, delivery codec/container, caption treatment and audio requirements. Label demo data and generated media.
  5. Inspect rights and renderer/provider licensing. Local rendering consumes compute and may carry license obligations; never promise universal zero cost.
  6. Render into a task-owned output directory. Preserve accepted masters and source assets. Clean only disposable intermediates you own after validation.

Choose and load

ContentPreferred pathRead when selected
React UI, product demo, data-driven variationsRemotionRemotion workflow
Diagram, vector scene, timed code animationMotion Canvasmotion-canvas-video skill
Equations, geometry, scientific explanationManim Communitymanim-video skill
Trim, transcode, crop/pad, subtitles, audio muxFFmpegdelivery workflow
Cinematic or photographic generated shotsAvailable AI video providerLive provider model/API documentation
Show full SKILL.md (174 more words)Show less

Workflow

  1. Turn the brief into a shot list: purpose, duration, visuals, voice/captions, transitions and assets. A small clip needs a short list, not a production bible.
  2. Prototype one representative shot, including text at delivery resolution. Resolve font/loading/export dependencies before building the full timeline.
  3. Implement reusable scenes. For AI shots, record the exact supported model, aspect ratio, duration, settings, request id and chosen take.
  4. Render low-cost previews of first/last frames and transition boundaries. Inspect legibility, clipping, safe areas and continuity; listen to the audio.
  5. Render the final file. Probe dimensions, fps, streams and duration, then play it. A successful process or nonzero file size alone is not delivery proof.
  6. Report source entrypoint, render command, final artifact, output properties, checks and any missing audio/visual verification.

Acceptance checks

  • Render, probe and play the final video; verify dimensions, timing, streams, captions and audio.

Skills in scope

  • audio-studio — music and narration.
  • motion-canvas-video — generator-based animated scenes.
  • manim-video — mathematical and scientific scenes.
  • threejs-3d — real-time 3D assets and scene integration.
  • office-documents — related slide or document deliverables.

© WrongStack, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in packages/core/skills/media-production of WrongStack/WrongStack.

  • SKILL.md
  • references/ffmpeg.md
  • references/remotion.md

Open the folder on GitHubat commit a744bdc

Compare with similar skills

Media Production next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Media Production compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Media Production this skillWrongStack/WrongStack371—~1kAutomated safety check: PassMIT
Anything2explainerVincentwei1021/anything2explainer2.4k—~2.7kAutomated safety check: PassCustom licence
Qiaomu Cutjoeseesun/qiaomu-cut-skill372—~6.8kAutomated safety check: NotesMIT
ShowtimeFavioVazquez/showtime220—~3kAutomated safety check: PassMIT
Super Video MakerBomx/super-video-maker-skill310—~11kAutomated safety check: NotesNone
AI Mediaericrisco/rsc-harness180—~3.3kAutomated safety check: PassMIT

Similar skills

  • Anything2explainer

    Vincentwei1021/anything2explainer

    给一个主题,产出一条黑底 MG 风格(幕底可选星点或点阵波)、有配音字幕章节进度条的科普讲解视频(中文或英文;Remotion 代码动画;时长由用户定,常用 3–5 分钟)。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据,以及一条完整样片(《RAG 与知识库》)作为质量标尺。Turn any topic into a narrated…

    2.4k GitHub stars~2.7k tokensUpdated 22 days ago
    Media & CreativeAuto-check passed
  • Qiaomu Cut

    joeseesun/qiaomu-cut-skill

    把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频:介绍…

    372 GitHub stars~6.8k tokensUpdated 12 days ago
    Media & CreativeAuto-check: notes
  • Showtime

    FavioVazquez/showtime

    A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…

    220 GitHub stars~3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • AI Media

    ericrisco/rsc-harness

    A skill your agent uses when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-video clips, score — then glue them with…

    180 GitHub stars~3.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Post Production

    AnastasiyaW/codex-claude-code-config

    Video post-production rules: audio mastering, color, captions, platform export.

    154 GitHub stars~1.7k tokensUpdated today
    Media & CreativeAuto-check passed

More from WrongStack/WrongStack

All 100 skills in this repo
  • Tech Stack

    WrongStack/WrongStack

    Validate and upgrade dependencies against live registries and official migration guides in any ecosystem.

    371 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Skill Creator

    WrongStack/WrongStack

    Create, improve and validate WrongStack SKILL.md bundles with precise discovery, progressive resources and current runtime contracts.

    371 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Bug Hunter

    WrongStack/WrongStack

    A skill your agent uses when scanning source code for bugs, anti-patterns, code smells, or quality issues in a codebase, or when running a proof-driven bug hunt that must find, prove, fix, and…

    371 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Design Craft

    WrongStack/WrongStack

    Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.

    371 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Design Critique

    WrongStack/WrongStack

    A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…

    371 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Mailbox Bridge

    WrongStack/WrongStack

    A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…

    371 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Questions about Media Production

What does Media Production do?

Create and process finished videos with Remotion, Motion Canvas, Manim, FFmpeg or an available AI video provider. Media Production is an agent skill from WrongStack/WrongStack. Create and process finished videos with Remotion, Motion Canvas, Manim, FFmpeg or an available AI video provider.

When should I use Media Production?

Media Production fits situations like: producing a video; narration timeline; format conversion; select the renderer from the content rather than defaulting every video to one engine.

How do I install Media Production in Claude Code?

Run `npx skills add WrongStack/WrongStack --skill media-production -a claude-code`. Or copy the skill folder (packages/core/skills/media-production in WrongStack/WrongStack) into .claude/skills/media-production in your project. Claude Code loads it when a task matches its description.

How do I install Media Production in Codex?

Run `npx skills add WrongStack/WrongStack --skill media-production -a codex`. Or copy the skill folder (packages/core/skills/media-production in WrongStack/WrongStack) into .agents/skills/media-production in your project. Codex loads it when a task matches its description.

Can I use Media Production in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WrongStack/WrongStack --skill media-production -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/media-production, .gemini/skills/media-production, .github/skills/media-production and .opencode/skills/media-production in your project.

What does Media Production need to run?

SKILL.md names no scripts, command-line tools or credentials: Media Production is instructions for the agent only.

Does Media Production access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Media Production safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Media Production use?

Media Production is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Media Production use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 954 tokens, read only when the agent opens those files.

What are the alternatives to Media Production?

Skills that share tags, products or a category with Media Production: Anything2explainer (Vincentwei1021/anything2explainer, 2.4k stars), Qiaomu Cut (joeseesun/qiaomu-cut-skill, 372 stars), Showtime (FavioVazquez/showtime, 220 stars) and Super Video Maker (Bomx/super-video-maker-skill, 310 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Media Production?

WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 371 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.

Source: WrongStack/WrongStack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.