SkillAgentSearch skills...

render-whiteboard-explainer

Assemble a whiteboard explainer video ad from a beats file — a narrator explains one idea while a real whiteboard fills up in black marker, with a hand-lettered title, bulleted rows down the left, a drawing filling the right, and a payoff that letters the closing line and rings the claim.

Install / Use

npx skills add gooseworks-ai/goose-skills --skill render-whiteboard-explainer

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Supported Platforms

Universal

Tags

Our assessment of render-whiteboard-explainer

render-whiteboard-explainer scores 85/100 on our quality scale, 2586th of 4,599 Development & Engineering skills we index.

Its SKILL.md is 8.4 KB long, well organised into 9 sections and no code examples: a thorough specification that gives an agent plenty to work with.

With 1,222 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
13/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 20 days ago, so render-whiteboard-explainer is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-10-13. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

render-whiteboard-explainer compared with similar skills

All 4 of these similar skills score higher than render-whiteboard-explainer; compare them before choosing.

SkillScoreStarsUpdatedFormat
render-whiteboard-explainer (this skill)by gooseworks-ai851.2k20d agoSKILL.md
ai-job-searchby MadsLorentzen10046.4k4d agoCLAUDE.md
claude-howtoby luongnv8910041.8k2d agoCLAUDE.md
algorithmic-artby anthropics100177.9k20d agoSKILL.md
pptxby anthropics100177.9k20d agoSKILL.md

Frequently asked questions

How do I install render-whiteboard-explainer?
Run npx skills add gooseworks-ai/goose-skills --skill render-whiteboard-explainer. The install tabs above show the steps for each supported agent.
Which AI agents does render-whiteboard-explainer work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is render-whiteboard-explainer safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is render-whiteboard-explainer still maintained?
The repository was last updated 20 days ago, so render-whiteboard-explainer is actively maintained.

name: render-whiteboard-explainer description: Assemble a whiteboard explainer video ad from a beats file — a narrator explains one idea while a real whiteboard fills up in black marker, with a hand-lettered title, bulleted rows down the left, a drawing filling the right, and a payoff that letters the closing line and rings the claim. The board is a PHOTOGRAPH and the ink is multiplied onto it, so the surface sheen and window light come through the strokes; the drawings are generated as line art and traced to ordered strokes, then revealed in drawing order on the word they belong to. The layout is SOLVED from the beats, never hand-placed. FREE assembly (Pillow plus ffmpeg) apart from one board photo and one drawing per subject, both one-time per brand. Use for the whiteboard format. status: draft

render-whiteboard-explainer

The renderer for the whiteboard video ad format: a voice explains one idea while a board fills up in marker, the way a graphic recorder works a room. Every mark lands on the word it belongs to, and the board is wiped and reused between sections.

Siblings in the chat-UI family are render-imessage-chat, render-chatgpt-chat and render-apple-notes-chat, where a screen is the creative. Reach for this one when the creative is someone explaining a thing by drawing it.

The three decisions that make this format work

The board is a photograph. A drawn board reads as a drawn board, and a plain white frame reads as a sketch film. Both were built and both were rejected. One generated still of a real blank whiteboard in a real room is the plate, and the ink is multiplied onto it so the surface sheen and the window light come through the strokes rather than sitting on top as flat black. The handheld drift is generated over both layers at once, so nothing can slide against anything.

The drawings are generated as line art, then traced. Do not hand-code them, and do not trace painterly images. Art traced from a photograph carries every contour the photograph had and reads as clip-art; art generated as a marker drawing traces to a handful of confident paths. An open hand came back as a single continuous stroke. Chain each generation off the first so the line weight matches across the set.

There is no colour. Black marker throughout. Do not add an accent.

Choices

The recipe asks these before any paid step; this renderer only draws what the beats say.

  • the script — what the narrator says. Everything downstream is anchored to its word timings, so it is settled first and never changed afterwards.
  • the beats — for each moment, what is SAID and what is DRAWN. A row of text, a drawing, or both. One number can be marked as the hero, which letters it large instead of as another row.
  • the title and subtitle — lettered on the first board.
  • the payoff — the closing line, lettered on the last board, with a ring closing around the claim it refers to.
  • the boards — how many times the board is wiped and reused. Three suits a half-minute. The split is automatic. To set it by hand, put "new_board": true on the beat that should open a board; any such mark turns the automatic split off. Use it when the split puts a line on the wrong board, such as the brand name landing on the problem board.

Brand facts come from the brand kit.

What it renders

  1. The plate. One photograph of a blank board in a room, generated once per brand, then cropped so the board fills the frame with its side edges running out of shot. The writable surface is measured off the image and pulled inside the caption safe zone before anything is mapped through it.
  2. The drawings. One black line drawing per subject the script names, generated once per brand and traced into ordered stroke paths.
  3. The layout. Solved from the beats, not authored. Rows go down a left column, drawings down a right one, with an enforced gutter between them, and the content runs the full height of the board. Boards are split at a pause near a balanced boundary, which is where a person would wipe.
  4. The video. Marks appear stroke by stroke in drawing order, each starting on its own word. Text is written letter by letter. The board wipes between sections. Captions sit inside the safe zone and never run ahead of the voice.
  5. The master. Gentle compression before a measured two-pass loudness normalisation, then a limiter. Targets minus fourteen LUFS with true peak under minus one and a half, and keeps the payoff hold intact.

Non-negotiables

  • Every mark lands on its own word. The voiceover is the clock. An anchor that resolves to the wrong word does not look wrong, it silently reorders the video: one that matched an early word instead of a late one once dragged a whole section to the front, and the ad played its ending first with nothing reporting a problem. Anchors are resolved once, shared by the solver and the renderer, and an ambiguous one is refused rather than guessed at.

  • Nothing is hand-placed. Anything that refers to something else — an arrow, a note, a ring — takes its target as an argument and works out its own position. Anything sharing space with a drawing is bounded by that drawing's box. Two things placed at coordinates chosen independently will eventually meet.

  • Copy a reference's grammar, never its content. The reference board bullets its rows with a drawn eye and fans emphasis marks beside its phrases, but those belong to that board's brand. Reproduced on another script they are decoration that means nothing. Filler has to be about something: a drawing of what the line refers to, never abstract specks.

  • Two reviews, both human. The storyboard still costs seconds and is where relevance is judged — whether a mark is about the line it sits under, whether the payoff says the closing line. No automated check decides that. Then the finished cut, watched end to end with the watch skill.

  • It runs on any machine. The two board fonts ship in assets/fonts (see the NOTICE.md there), and the image tool is found beside this skill. The caption pill uses Segoe Script Bold where Windows has it and Permanent Marker everywhere else, so captions look slightly different off Windows.

  • The caption pill ends above y=1520. review-finished-ad flags the bottom 400px, so the default caption_y is 1440 and the layout keeps every row, drawing and the payoff above the pill. An episode.json written before this keeps its own caption_y; delete the key and re-solve to move it.

  • The board photo carries no logo. The prompt forbids a maker's badge. Look at the plate anyway: a real manufacturer's name on the frame is a third party's mark in a brand's ad.

Inputs

  • the spoken audio and its word-level timings, as described below
  • a beats file — see the example beside the scripts
  • a brand kit for the facts

The voice comes with its word timings. create-vo-elevenlabs returns audio only, and this format needs a timing for every word. scripts/gen-voice.py --project <dir> reads vo and voice from beats.json and calls the proxy's /with-timestamps route, writing voice/vo.mp3 and voice/words.json, which make-episode.py requires. A dry run prints the character count and the cost; --yes spends. It routes through the GooseWorks proxy (scripts/media_proxy.py), never the speech provider directly, and refuses a payload it has already paid for.

Checks it runs itself

The build refuses to continue when any of these fail, and names what broke:

  • every anchor resolves to exactly one intended word
  • sections start in script order
  • every mark finishes being drawn before its board is wiped
  • rows stay inside the column and cannot reach a drawing
  • loudness, true peak and the payoff hold

Cost

The board photo and the drawings are one-time per brand. A second video for the same brand costs only the voiceover. Everything else — the layout, the lettering, the tracing, the render and the master — is free and local. Rendering a half-minute takes under three minutes.

Honest ceiling

Measured against the filmed reference this reaches about a fifth of its ink cover, because the reference is a time-lapse of a much longer drawing session while every mark here waits for its word. Filler narrows that and does not close it. If a brief needs a genuinely full board, the script has to be longer or the marks have to stop waiting for words.

Related Skills

View on GitHub
GitHub Stars1.2k
CategoryDevelopment
Updated20d ago
Forks208

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions