Stitch to Remotion Walkthrough Videos
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
Plan and assemble 30–90 second motion graphics and character videos with six production stages, media gates, and visual review.
$ npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install unclejobs-ai/motion-video-skill motion-video-production --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/unclejobs-ai/motion-video-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/motion-video-production .claude/skills/motion-video-production && rm -rf skills-srcUse ~/.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/
Install the "motion-video-production" agent skill from https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-production into .claude/skills/motion-video-production/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "motion-video-production", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-productionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install unclejobs-ai/motion-video-skill motion-video-production --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unclejobs-ai/motion-video-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/motion-video-production .agents/skills/motion-video-production && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "motion-video-production" agent skill from https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-production into .agents/skills/motion-video-production/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "motion-video-production", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install unclejobs-ai/motion-video-skill motion-video-production --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unclejobs-ai/motion-video-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/motion-video-production .cursor/skills/motion-video-production && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "motion-video-production" agent skill from https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-production into .cursor/skills/motion-video-production/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "motion-video-production", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/unclejobs-ai/motion-video-skill.git --path skills/motion-video-production--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install unclejobs-ai/motion-video-skill motion-video-production --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unclejobs-ai/motion-video-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/motion-video-production .gemini/skills/motion-video-production && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "motion-video-production" agent skill from https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-production into .gemini/skills/motion-video-production/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "motion-video-production", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install unclejobs-ai/motion-video-skill motion-video-productionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/unclejobs-ai/motion-video-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/motion-video-production .github/skills/motion-video-production && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "motion-video-production" agent skill from https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-production into .github/skills/motion-video-production/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "motion-video-production", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install unclejobs-ai/motion-video-skill motion-video-production --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unclejobs-ai/motion-video-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/motion-video-production .opencode/skills/motion-video-production && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "motion-video-production" agent skill from https://github.com/unclejobs-ai/motion-video-skill/tree/main/skills/motion-video-production into .opencode/skills/motion-video-production/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "motion-video-production", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
motion-video-productionPlan and assemble 30–90 second motion graphics and character videos with six production stages, media gates, and visual review.
Motion Video Production is an agent skill from unclejobs-ai/motion-video-skill. Plan and assemble 30–90 second motion graphics and character videos with six production stages, media gates, and visual review. Use for video production, keyframes, character consistency, and Remotion assembly. 모션 그래픽·캐릭터 영상·오프닝 영상 제작에 사용한다.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 25 other files, including scripts and reference files (for example `agents/openai.yaml`, `harness/gate.py` and `harness/selftest.sh`).
It sits in Media & Creative, covering Video production. It works with Remotion. The repository describes itself as: Claude Code 스킬: 모션 그래픽·영상 제작 순서와 단계별 점검 하네스. The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit dd11881. It shows what the files ask for, not the result of running them.
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.
Ships 6 files in scripts/ (Shell and Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3bashnpxffprobeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Motion Video Production loads about 2k tokens when it runs, and up to ~9.8k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 1,362 words of instructions outside code blocks.
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.
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); the scripts in this folder are not scanned.
The full file from unclejobs-ai/motion-video-skill at commit dd11881, republished under its MIT licence (© unclejobs-ai). 1,362 words, ~1,973 tokens.
.claude/skills/motion-video-production/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.이 스킬은 모션 그래픽과 영상(예: 한 명의 캐릭터가 나오는 30~90초 영상)을 만드는 순서와 점검 기준을 제공합니다. 이 스킬을 따라가면 STORY.md, 캐릭터 시트, 키프레임, 장면 영상, 음악·목소리, 최종 mp4를 얻어가십니다.
모든 답변은 사용자의 언어(기본 한국어)로 합니다. 도구를 대신 로그인하거나 결제하지 않습니다. 로그인·결제·대용량 다운로드가 필요한 시점에서는 사용자에게 먼저 묻습니다.
이 스킬은 Agent Skills 형식의 공통 지침입니다. Codex, Claude Code 및 다른 스킬 지원 런타임에서 같은 폴더를 사용합니다. 특정 모델의 API나 생성 도구 연결을 포함하지 않습니다.
SKILL.md의 실제 경로에서 부모 폴더를 SKILL_ROOT로 정합니다. ~/.claude/skills 같은 특정 설치 경로를 가정하지 않습니다. 아래 references/, templates/, harness/, scripts/는 모두 이 폴더 기준입니다.PROJECT_ROOT로 정합니다. 두 경로를 구분하고, 스크립트는 python3 "$SKILL_ROOT/harness/gate.py" <단계> "$PROJECT_ROOT"처럼 절대 경로로 실행합니다. 보조 스크립트는 산출물 폴더에서 bash "$SKILL_ROOT/scripts/<파일>.sh" ...로 실행합니다..sh 스크립트에는 Bash가 필요합니다(macOS/Linux 또는 Windows의 WSL). Remotion은 Node.js와 별도 설치가 필요합니다.STORY.md는 제공된 템플릿의 한국어 항목명과 표 구조를 유지하고, 내용은 사용자 언어로 채웁니다. 게이트가 이 항목명을 읽습니다. 한국어 외의 character.txt에는 색 이름과 함께 #RRGGBB 색상 코드를 적습니다(현재 색 검사에서 인식 가능).작업을 시작할 때 아래 4가지를 사용자에게 한 번에 묻고 STORY.md 맨 위에 기록합니다.
references/cost-rules.md)각 단계는 산출물이 있고, 아래 Harness의 게이트가 종료 코드 0으로 끝나야 다음 단계로 넘어갑니다. 작업 전에 아래 Gotchas(함정 목록)를 먼저 읽습니다.
| 단계 | 하는 일 | 쓰는 도구(예시) | 산출물 |
|---|---|---|---|
| 1. 스토리·장면 기획 | 한 줄 줄거리, 장면 목록(시간·장소·행동·대사), 음악 싱크 지점 확정 | 현재 에이전트 | STORY.md, 장면 목록 |
| 2. 캐릭터 시트 | 정면·측면·표정·의상을 한 장에 고정한 기준 이미지 | 이미지 생성 도구 | 캐릭터 시트 PNG, 외형 고정문 |
| 3. 키프레임 | 장면마다 시작 화면 1장씩 생성 | 이미지 생성 도구 | 키프레임 PNG |
| 4. 영상 변환 | 키프레임을 시작 화면으로 고정하고 3~6초 클립 생성 | 영상 생성 도구 | 장면별 mp4 |
| 5. 음악·목소리 | 음악 1곡, 캐릭터 목소리 1개(ID 고정), 대사 음성 | 음악·음성 도구 | 음악 wav/mp3, 대사 wav |
| 6. Remotion 조립 | 박 격자에 맞춰 컷 배치, 자막·타이틀·엔드카드 모션 그래픽, 믹스, mux | Remotion, ffmpeg | 최종 mp4 |
자주 생기는 함정 8가지입니다. 전체 29가지(증상, 원인, 예방, 하네스 검사 ID)는 references/gotchas.md에 있습니다.
| tail)로 검사 출력을 자르면 종료 코드가 사라집니다. 판정은 하네스의 종료 코드와 보고서 파일로 합니다. (G21)ffprobe -of csv=p=0을 쓰면 30,처럼 읽혀 정상 영상이 막힐 수 있습니다. -of default=nw=1:nk=1을 씁니다. (G27)단계의 산출물은 harness/gate.py가 측정해서 종료 코드로 판정합니다. 게이트가 통과(종료 코드 0)하기 전에는 다음 단계로 넘어가지 않고, 완료라고 보고하지 않습니다.
python3 "$SKILL_ROOT/harness/gate.py" <단계> "$PROJECT_ROOT"| 제작 단계 | 게이트 | 하는 검사 |
|---|---|---|
| 1. 스토리·장면 기획 | story | STORY.md 빈칸, BPM, 음악 싱크 지점 표(시간이 숫자인지), 장면 표 |
| 2. 캐릭터 시트 | character | character.txt(1개 문단 평문, 색 표현), 시트 이미지 |
| 3. 키프레임 | keyframes | 중복 파일, 클립과의 화면비 |
| 4. 영상 변환 | clips | 길이, 프레임 수, 시작 화면 일치, 프레임 스트립 생성, 눈 검수 기록과 클립별 판정 |
| 5. 음악·목소리 | audio | 음성 ID 1개, 대사 파일 |
| 6. 조립 전 | edit | 박 격자(컷 경계), 컷 연결, 반복 컷, 대사 길이, src 클립과 사용 구간 |
| 6. 조립 후 | final | 프레임 수, 해상도, fps, 오디오 길이, 라우드니스, true peak, 눈 검수 기록 |
harness/gate.py 첫머리에 있습니다. (STORY.md, character.txt, voices.json, edit.json, sheet/, key/, clip/, out/final.mp4, qa/) 클립 이름, 키프레임 이름, edit.json의 clip:<이름>@<시작초>는 같은 이름을 씁니다.qa/gate-<단계>.txt에 보고서를 남깁니다. 보고할 때는 이 파일의 BLOCK, WARN 줄을 그대로 인용합니다.qa/clips-review.md: REVIEWED: <이름> <YYYY-MM-DD> 줄과, 클립마다 <클립 이름>: ok|trim|redo|replace 줄. redo, replace가 남아 있으면 통과하지 못합니다. 키프레임이 없는 클립은 nokey: <클립 이름> 줄로 허용합니다.qa/review.md: REVIEWED: <이름> <YYYY-MM-DD> 줄과, 본 결과를 적은 줄. 최종본(out/final.mp4)보다 나중에 작성해야 합니다.GATE_SSIM_START, GATE_LUFS, GATE_LUFS_TOL, GATE_TP_MAX)bash "$SKILL_ROOT/harness/selftest.sh"가 종료 코드 0으로 끝나야 합니다. 막아야 할 사례를 합성 프로젝트로 실제로 막는지 확인하는 셀프테스트이고, 새 검사에는 막아야 할 사례를 함께 추가합니다.templates/STORY.md를 복사해 채웁니다. 장면마다 시간대, 장소, 캐릭터 행동 1개, 감정 1개를 적습니다.templates/CHARACTER_SHEET.md로 시트를 점검합니다. 시트·키프레임·클립 프롬프트 틀은 templates/PROMPTS.md에 있습니다.character.txt 파일로 저장합니다. 이후 모든 프롬프트에 이 파일의 문장을 그대로 붙입니다.scripts/clipsheet.sh로 프레임 시트(클립의 모든 프레임)를 만들어 눈으로 확인하고, 결함이 있는 구간은 잘라 내고 쓸 수 있는 구간만 사용합니다. (templates/SCENE_AUDIT.md에 기록)scripts/key-plate.sh를 사용합니다.references/beat-grid.md의 계산으로 컷 길이를 박 단위로 맞춥니다.모션 그래픽(자막, 타이틀, 엔드카드, 화면 효과)과 최종 조립은 Remotion으로 합니다. 아래는 Remotion 공식 구성요소(Composition, Sequence, OffthreadVideo, Audio, useCurrentFrame, staticFile)를 쓰는 구조입니다.
npx create-video@latest로 직접 만듭니다. 이 스킬은 Remotion 코드를 포함하지 않습니다. (라이선스는 references/licensing.md)edit.json)으로 두고, 각 컷을 <Sequence from={시작프레임} durationInFrames={길이}> 안에 <OffthreadVideo src={staticFile(...)} />로 배치합니다.useCurrentFrame() 값에서 계산하는 순수 함수로 작성합니다. 같은 프레임을 다시 렌더해도 같은 결과가 나옵니다.npx remotion render <컴포지션ID> out/picture.mp4로 하고, 렌더 후 scripts/mix-mux.sh로 음악·대사를 섞어 입힙니다.scripts/verify.sh로 하고, 생성된 컨택트 시트를 직접 봅니다.캐릭터 시트, 외형 고정문, 키프레임 시작 화면, 목소리 고정(같은 음성 ID), 대사와 입 모양 타이밍, 음악 박자, 품질 검수가 모두 맞물려야 장면이 바뀌어도 얼굴과 목소리가 같습니다. 항목별 문제와 맞추는 방법은 references/consistency-7.md에 있습니다.
무료 플랜으로 시안을 만들고, 상업 공개용 최종본의 음악·목소리만 유료 플랜에서 다시 생성합니다. 유료 대량 생성 전에는 예상 크레딧을 알리고 승인을 받습니다. 전체 규칙은 references/cost-rules.md, 현재 약관은 references/licensing.md에 있습니다.
하네스 검사가 없는 실수는 references/pitfalls.md, 도구별 사용법은 references/providers.md를 참고합니다.
scripts/ 아래, 프로젝트 폴더에서 실행)| 파일 | 용도 |
|---|---|
dupcheck.py | 같은 키프레임을 쓰는 반복 컷 검출 |
clipsheet.sh | 프레임 시트(클립의 모든 프레임을 6x5 칸으로 배치) |
key-plate.sh | 초록 배경 -> 투명 PNG |
mix-mux.sh | 음악·대사 믹스와 프레임 수 게이트 mux |
verify.sh | 영상 측정과 컨택트 시트 (받아쓰기 연동은 미검증) |
beat-grid.py | BPM 기준 박 길이·스냅 계산 |
../harness/gate.py | 단계별 통과 여부를 종료 코드로 판정 |
© unclejobs-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 21 other files (scripts, references) in skills/motion-video-production of unclejobs-ai/motion-video-skill.
Open the folder on GitHubat commit dd11881
Motion Video 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Motion Video Production this skillunclejobs-ai/motion-video-skill | 111 | — | ~2k | Automated safety check: Pass | MIT | |
| Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills | 8.5k | 6 repos | ~3.2k | Automated safety check: Notes | Apache-2.0 | |
| Video ShotcraftVincentwei1021/video-shotcraft | 11k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| HyperFrames Video Entry Pointheygen-com/hyperframes | 60k | 3 repos | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Writing Docsremotion-dev/remotion | 63k | 1 repos | ~1.9k | Automated safety check: Pass | Custom licence | |
| Brand Launch Video Starvibe-motion/skills | 1.3k | — | ~2.3k | Automated safety check: Pass | None |
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
Vincentwei1021/video-shotcraft
Makes cinematic product videos with Remotion from shot recipe cards, a ready template, real page screenshots, camera moves and sound design, or builds a single animated shot.
heygen-com/hyperframes
Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.
remotion-dev/remotion
Guides for writing and editing Remotion documentation. An agent skill from remotion-dev/remotion.
vibe-motion/skills
Create fast, high-impact 15-30 second brand and product marketing videos from an official company website, verified brand sources, or user-uploaded product imagery.
itwanger/toBeBetterJavaer
把口播稿做成二哥风格的 Remotion 视频,包括整理视频用稿、火山 TTS 配音、音画对齐、逐章动画预览和导出带配音的 MP4。用户说“做视频”“口播稿转视频”“Remotion”“继续做下一章”“出片”“渲染”“改读音”“配音读错了”,或给出 docs/src/ai/video/ 下的稿子要做成视频时使用。共享工具、配置和素材在…
Works with
Categories
Plan and assemble 30–90 second motion graphics and character videos with six production stages, media gates, and visual review. Motion Video Production is an agent skill from unclejobs-ai/motion-video-skill. Plan and assemble 30–90 second motion graphics and character videos with six production stages, media gates, and visual review.
Motion Video Production fits situations like: video production; character consistency; remotion assembly.
Run `npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a claude-code`. Or copy the skill folder (skills/motion-video-production in unclejobs-ai/motion-video-skill) into .claude/skills/motion-video-production in your project. Claude Code loads it when a task matches its description.
Run `npx skills add unclejobs-ai/motion-video-skill --skill motion-video-production -a codex`. Or copy the skill folder (skills/motion-video-production in unclejobs-ai/motion-video-skill) into .agents/skills/motion-video-production in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add unclejobs-ai/motion-video-skill --skill motion-video-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/motion-video-production, .gemini/skills/motion-video-production, .github/skills/motion-video-production and .opencode/skills/motion-video-production in your project.
Going by SKILL.md and its folder, Motion Video Production needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (python3, bash, npx and ffprobe). Our summary lists: Python 3; Node.js; A Bash shell.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Motion Video Production is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 7.9k 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 7.8k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Motion Video Production: Stitch to Remotion Walkthrough Videos (google-labs-code/stitch-skills, 8.5k stars), Video Shotcraft (Vincentwei1021/video-shotcraft, 11k stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars) and Writing Docs (remotion-dev/remotion, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
unclejobs-ai (a GitHub user) maintains it in unclejobs-ai/motion-video-skill, which has 111 GitHub stars. The repository was last updated on October 9, 2026.
Source: unclejobs-ai/motion-video-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.