Papercut Build logo

Papercut Build

Community
0xS4N4TG
papercut-build

Build and render a papercut episode from a storyboard with the library. Scaffolds the project, builds scenes with parallel agents, assets and audio, renders the mp4, then harvests reusables. Use for "build the reel", "scaffold an episode", "rebuild scene 4", "render it".

Overview

Publisher0xS4N4TG
Repositorypapercut-explainer
Skill namepapercut-build
Stars
106
Forks
10
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by 0xS4N4TG on GitHub. Read the source before you install it.

Installation

Install the Papercut Build AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/0xS4N4TG/papercut-explainer/tree/main/skills/papercut-build
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/0xS4N4TG/papercut-explainer.git /tmp/papercut-explainer
mkdir -p .claude/skills
cp -r /tmp/papercut-explainer/skills/papercut-build .claude/skills/papercut-build
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Papercut Build in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Papercut Build on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Papercut Build is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Papercut build

Build every episode on the library instead of writing a Remotion project from scratch. Read library/README.md once.

Preflight

  • Install: Standard or Full. Needs the library, node 20+, npm, ffmpeg, Python tools (numpy, Pillow, soundfile) and Chrome or Chromium for the audio render. Probe with the commands in papercut-explainer; if something is missing, run ./install.sh --doctor and hand over to papercut-setup.
  • Library: $PAPERCUT_LIB, else the PAPERCUT_LIB= line in ~/.config/papercut-explainer/config.env, else ask once. With no library at all, build from the sketches in ../papercut-explainer/references/remotion-recipes.md.
  • Load the Remotion best-practices skill first (remotion-best-practices, from the Remotion plugin, or npx skills add remotion-dev/skills -g -y -a <your harness id>; install.sh --mode standard does this) and follow its routing for markup, captions and the Studio.
  • Needs papercut/STORYBOARD.md and narration/script.json from the earlier stages.
  • Smoke test of the whole toolchain: library/tools/selftest.sh builds examples/hello-reel/ in a throwaway folder and renders one still.

1. Scaffold

$PAPERCUT_LIB/new_episode.sh <series-dir> NN-slug CompId [out-name]

It creates <series>/episodes/NN-slug/{research,narration/voice,papercut} with the template project and a synced copy of the kit in src/lib/. node_modules comes from $DONOR, else the newest sibling episode, else npm i. If <series>/papercut-assets/ exists, it is laid over the default textures and props.

The folder may already exist, because the earlier stages wrote research/, narration/script.json and papercut/STORYBOARD.md into it. The script merges into it and never overwrites a file that is there. It stops only if papercut/package.json exists (already scaffolded).

Never edit src/lib/ in a project. It is a snapshot, so an old episode renders the same after the library changes. Fix the library, then re-sync with papercut/sync_kit.sh.

2. Plan: episode.json, voice, timing

From the storyboard, fill papercut/episode.json:

  • scenes: [["S01Hook", "l1_hook", 0], ["S02Name", "l2_name", "called"], ...] (scene id, narration line id, first word as an index or the exact word).
  • banners: {"S01Hook": "TAKEAWAY IN CAPS"}. hook: see papercut-hook. cuts: the Camera / Cut table's cut column. bed, whipScene, cutSfx, gaps (extra beat after a line, in seconds).

Then run papercut-voice through its timing step (it ends with build_vo.py and timing_md.py). Then, from papercut/:

python3 $PAPERCUT_LIB/papercut/stubs.py        # src/scenes/index.ts + a stub per scene

build_vo.py flags any scene under 1.2 s; merge it into a neighbour. timing_md.py writes the Timing section of STORYBOARD.md (absolute frames and word cues), so agents never open plan.json.

3. Assets

Follow ../papercut-explainer/references/asset-prompts.md: an image tool (anything that outputs transparent PNGs) for backgrounds and complex static props, code for characters, all text, tags, gauges, buttons and UI. No text inside generated images. With no image tool, build every prop in code with the paper filter; the style holds up. Backdrops: use the library's <Backdrop> set (library/papercut/public/bg/backdrops/_sheet.jpg); generate a new one only when an episode needs a place the library lacks. The proof screenshot: node $PAPERCUT_LIB/tools/capture.mjs <url> public/proof/x.png, shown with the kit's RealShot.

4. Scenes

  1. Build S01Hook yourself first, from the HOOK block. It is the reference scene the agents match (cue constants, the camera, clamped interpolate).
  2. Hand the rest to scene agents in parallel, grouped by scene (2-3 scenes each; more agents cost more startup context). Use the papercut-scene agent that install.sh wrote for your harness (Claude Code ~/.claude/agents, OpenCode ~/.config/opencode/agents, Codex ~/.codex/agents, Gemini CLI ~/.gemini/agents); a general agent also works. Spawn it with your harness's own mechanism (the Task tool in Claude Code, the subagent tool in opencode, Codex's subagents, Gemini's agent tool). If your harness has no subagents, build the scenes yourself one at a time, in the same order and with the same brief; it is slower, not different. The brief is library/papercut/AGENT_BRIEF.md. The spawn message gives the project path, each agent's scenes with absolute frame ranges, a QA folder name and the value of $PAPERCUT_LIB.
  3. File ownership: an agent writes only src/scenes/<Scene>.tsx, an optional <Scene>.parts.tsx and tools/cue_sheet.d/<Scene>.json. Never src/lib/**, other scenes, index.ts, plan.json, episode.json or the storyboard.
  4. Agents read library/papercut/CATALOG.md and library/audio/CATALOG.md, not the kit source, and reuse components, prop sets and scene templates (kit/scenes/, for example CtaPhoneDM for the CTA) before drawing anything new.

Build rules: 1080x1920, 30 fps, scenes chained in the kit's transition series. Global layers: VO and music <Audio>, the taped banner with <Boil>, <WordTagCaptions>, <GrainOverlay>. Every prop is wrapped in <Paper>, entrances use <PopIn>, each scene runs inside its storyboard camera. No CSS animations. Keep the bottom 20% clear. Neighbouring scenes never share a backdrop. The default hero is a boxy orange critter (token C.hero #D67354, shade C.heroLo #A9553B, alias you); accessories and name pills tell the cast apart.

5. Sound

Pick SFX by name from library/audio/sfx/*.js and the bed by preset from library/audio/beds/*.json. From papercut/:

python3 $PAPERCUT_LIB/tools/cues.py && node $PAPERCUT_LIB/audio/render.mjs

cues.py merges the agents' rows into tools/cues.json and prints a note if air sounds exceed one per 2.5 s. render.mjs writes public/audio/music.wav and fx.wav.

6. Render

Preview in the Studio (npx remotion studio). Render only when asked:

$PAPERCUT_LIB/tools/render.sh        # -> out/<out>.mp4

Flags: --workers N (default 3), --conc N, --force, --keep. Each scene is cached, so after a fix only the changed scene re-renders; a change to the kit, plan, voice or captions re-renders everything. The first run downloads Remotion's headless Chrome, and out/cache takes several GB of ProRes.

To fix or rebuild one scene: edit src/scenes/<Scene>.tsx, check it with papercut-qa, then run render.sh again.

7. Harvest (after the episode)

python3 $PAPERCUT_LIB/tools/harvest.py .       # from papercut/; read-only report
python3 $PAPERCUT_LIB/tools/catalog.py         # regenerate both catalogs

Promote kit fixes, reusable components, new SFX and recurring beats as library/HARVEST.md describes, and add an entry to library/CHANGELOG.md.

  • When a move looks stiff or muddy, check ../papercut-explainer/references/motion-principles.md for the matching principle and its kit helper.

Hand-off

Next is papercut-qa, which reads stills from the project and STORYBOARD.md. Run it per scene while building and once on the whole reel before the final render. After posting, papercut-strategy runs the autopsy.

Frequently asked questions

What does the Papercut Build AI skill do?

Build and render a papercut episode from a storyboard with the library. Scaffolds the project, builds scenes with parallel agents, assets and audio, renders the mp4, then harvests reusables. Use for "build the reel", "scaffold an episode", "rebuild scene 4", "render it".

Why use Papercut Build on TypingMind?

Because you install it once and use it with any model. Papercut Build is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Papercut Build in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/0xS4N4TG/papercut-explainer/tree/main/skills/papercut-build. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Papercut Build?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Papercut Build?

As many as you like. As long as a model supports skills, you can use Papercut Build with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Papercut Build AI skill free?

Yes. It is published on GitHub by 0xS4N4TG under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇