video-shotcraft vs Remotion's official skills: same brief, both rendered

Tested and written by Fred at SkillsTested · Published 2026-07-25 · Updated 2026-08-02

Two Claude Code skill layers promise to turn an agent into a video studio — a 51.1MB community production kit and the framework vendor's own 11-skill pack. Instead of comparing READMEs, we gave both the identical five-second brief, followed each skill's own methodology to the letter, rendered both results, and then wrote up what we would fix in each repo. This is the comparison a directory cannot write.

Tested 2026-07-29

The two contenders

The size gap is the first real finding: one side is a kit (shot recipe cards, a finished template, bundled SFX with attribution), the other is rules (11 top-level instruction skills, no bundled media). Neither is wrong — they are different theories of what an agent needs. The rest of this page tests those theories.

The brief (identical for both)

Small on purpose: typing animation, a spring, one composition — enough to force each skill to reveal how it actually directs an agent, without a day of rendering.

How each side told the agent to work

video-shotcraft: pick a card, inherit its taste

The skill's workflow is opinionated before a single frame exists. Its SKILL.md hard-gates the session: introduce the bundled Ink Press template first and ask whether to use it or go free-form. For our free-form brief, its methodology routes you into references/shots/ — we used the typewriter card, and it handed over implementation-grade specifics: characters revealed every 2 frames, a block cursor on an f%12<6 square wave that stays solid while typing and dies two blinks after, an overshoot bezier lifted from the template's own tuned component for the check pop, and an explicit "hold ≥50 frames of stillness" ending. The agent inherits a cinematographer's defaults.

Remotion official skills: correct by construction

The official pack routes through remotion-create into remotion-markup's rulebook. Its timing file states a clear default — prefer interpolate() with a bezier over spring() unless the user explicitly asks for physics; our brief said "with a spring", so a spring it was. Rules covered clamping extrapolation, keeping animation inline in the style prop so Remotion Studio can write edits back to code, and individual transform properties. What the rulebook never offers is an opinion about how the result should look.

What actually rendered

Complete current-commit MP4s, unretouched. Press play and unmute:

Same brief, same fonts available, same renderer — and the difference is exactly the two theories made visible. The card path produced a composition: centered title, a badge (green disc, white check) scaling in below it, because the card and the template component it borrows encode design decisions. The rules path produced a correct implementation: the text types on, the spring springs — as a bare glyph sitting wherever the agent happened to put it. Every API rule was followed; no one was directing.

The numbers

The pure 150-frame render times are near-identical. The first-run browser downloads differ sharply and dominate the fresh setup totals; that is network/cache cost, not a skill-speed win. Everything that separates these skills happens before the render: what the agent is told to care about, and what it ships to your disk to say it.

What broke, verbatim

On the video-shotcraft path

On the official-skills path

Both current paths rendered successfully after the dependency step. The current shared risk is the first Chrome Headless Shell download: it succeeded here but dominated elapsed time. In restricted CI, preinstall an approved browser and pass --browser-executable; on low-core machines, cap concurrency to the available cores.

Current-commit status

A note on the star counts

We record stars with dates because they move — and not always up. video-shotcraft's count fell between our test and this comparison while the official pack's rose. We log the readings and draw no conclusion beyond the obvious one: star counts are a weak signal, which is why this site measures installs instead.

What we would fix upstream

A deep comparison should pay its subjects back. These are concrete, evidence-backed suggestions from the current rerun. One important historical issue is now closed in practice: the installed official hub references that failed in the July 25 test resolve on the current commit.

To video-shotcraft

1. Finish the English instruction path

The current trigger is bilingual, but the detailed root SKILL.md body remains Chinese-first. English-speaking users can activate the skill, yet still pay a translation cost when inspecting or editing the workflow.

2. Keep separating preview media from the default payload

The default install has improved from 164MB to 51.1MB, but it remains roughly twenty times the official rules pack because templates and media are copied per project.

3. Add a browser preflight to the starter flow

The first successful render spent 134.8 seconds downloading Chrome Headless Shell, far more than the 8.7-second frame render. A preflight would expose that cost before the user waits at export time.

To remotion-dev/skills

1. Document the first-render browser cost

The first successful render spent 375.5 seconds downloading Chrome Headless Shell while the 150-frame render itself took 8.1 seconds. The user should see that boundary before starting.

2. Add a consumer-facing skill map

The installed pack now contains 11 top-level skills and its internal references resolve, but the repository front door still does little to explain which skill a user should start with for a concrete deliverable.

3. Clarify pnpm build-script handling

The pnpm setup path returned ERR_PNPM_IGNORED_BUILDS for esbuild even though the subsequent render succeeded. A one-line npm/pnpm note would distinguish a package-manager warning from a render failure.

Verdict: which one, when

Choose video-shotcraft when the deliverable is a product promo and you want it to look directed: the cards carry taste (timing, easing, composition, even sound design with bundled, attributed SFX), and the Ink Press template is the fastest path from screenshots to a finished-looking film. Budget 51.1MB per local install and preflight the browser in restricted CI.

Choose the official pack when you are building your own visual language or anything that is not a promo — captions, audio visualization, SaaS embedding, interactive Studio work. It is roughly 20× lighter, English-first, API-correct by construction, and covers far more of Remotion's surface. Just bring your own art direction, because it will not offer any.

Run both if you can: they do not conflict, and the combination — official rules for correctness, shot cards for taste — is what actually resembles a studio.