REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent skill for browser motion graphics — openers, promos, bumpers, kinetic typography, and five explainer styles that move like video, not slides. Single index.html output. Works with Claude Code, Codex, Gemini CLI, Cursor.
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/bangtutorial-bang-motion)MCP servers that connect the AI to services for the same work
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
Same kind of work, ordered like the Skills list
| This one bang-motion | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | bangtutorial | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 2,279 | 463,670 | 233,682 | 148,887 | 143,987 |
| Last code change | Sep 15, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 16, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
1 skills (instruction sets) by bangtutorial that an AI reads and follows · not an MCP server
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Claude CodeCodexCursorGemini CLI
From the maker’s README and the folders in the repo
GitHub account bangtutorial (person), 1 years old
★ 2,279 stars · code last changed Sep 15, 2026
8 scripts that can run on a computer: scripts/ae/bridge/aset-svg.py, scripts/ae/bridge/rig-tokoh.py, scripts/ae/bridge/svg2png.cjs, scripts/export-frames.mjs and 4 more
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit c1aa65e (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Uploading to claude.ai would fail: the description is over 200 characters (940). Use "Let the AI install it" instead
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /bang-motion or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Put the bang-motion folder at ~/.agents/skills/bang-motion
~ is your home folder ($HOME)
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick bang-motion
Checked against official docs Nov 12, 2026 · Source: cursor.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: bang-motion
description: Membangun motion graphic sinematik di browser (promo video, opener, intro, bumper, kinetic typography, explainer/video penjelasan bergambar 16:9 atau 9:16) memakai HTML + CSS + GSAP (+ Three.js bila perlu), dengan hasil yang bergerak seperti video sungguhan — bukan slide presentasi. Gunakan skill ini setiap kali user meminta "video promo", "opener", "intro animasi", "motion graphic", "bumper", "kinetic typography", "animasi teks sinematik", "explainer", "video penjelasan" (jurnalisme visual, kartun edukasi, kolase), atau menunjukkan referensi video promosi/explainer dan ingin dibuatkan versi web-nya — bahkan bila mereka tidak menyebut kata "motion graphic" secara eksplisit. Juga gunakan bila user mengeluh hasil animasi web "seperti PPT/presentasi" dan ingin lebih sinematik, atau ingin merender animasi web menjadi file video MP4, atau ingin explainer kartun/animasi dibangun LANGSUNG di After Effects lewat bridge/MCP Higgsfield.
license: MIT
metadata:
author: Bang Tutorial
author_url: https://youtube.com/bangtutorial
version: "1.19.0"
updated: "2026-09-14"
homepage: https://github.com/bangtutorial/bang-motion
---
# Bang Motion — motion graphic web yang bukan PPT
**v1.19.0 · by [Bang Tutorial](https://youtube.com/bangtutorial) · MIT.** Riwayat perubahan di `CHANGELOG.md`;
cara pasang di `README.md`.
Skill ini untuk AI coding agent apa pun (format Agent Skills terbuka).
Isinya hukum dan resep untuk motion graphic yang bergerak seperti video, bukan
presentasi — patuhi sebelum menulis kode.
## Prasyarat — hanya browser
Deliverable (`index.html`) hanya butuh browser modern + internet untuk CDN
(GSAP, font). Python dan Node **opsional**, dipakai hanya untuk alat kerja:
`scripts/serve.py` (server no-cache, cuma perlu bila memakai module lokal),
puppeteer (snapshot/verifikasi otomatis, `scripts/export-frames.mjs` → MP4).
Kalau user tidak punya keduanya: (1) tetap bangun satu-berkas, buka lewat
klik dua kali; (2) verifikasi visual lewat `?debug=1` (panel scrub) dan
screenshot manual per detik kunci; (3) MP4 lewat rekam layar (OBS / rekam
tab browser) — jelaskan bahwa hasil rekam layar bisa drop frame, dan render
frame-by-frame butuh Node. Jangan pernah membuat deliverable yang butuh
`npm install` untuk DITONTON.
**ffmpeg juga opsional.** Cek dulu (`ffmpeg -version`); bila tidak ada:
| Kebutuhan | Dengan ffmpeg | Tanpa ffmpeg |
|---|---|---|
| Sinkron VO (batas kalimat/paragraf) | `silencedetect` | `scripts/vo-pauses.html` — buka di browser, pilih audio, salin `SEG`/`PARA`; hasilnya sama persis (Web Audio, tanpa instal) |
| Durasi/format audio | `ffprobe` | angka `DUR` dari vo-pauses.html; browser memutar wav/mp3/m4a/ogg langsung |
| Export MP4 | gabung PNG dari export-frames.mjs | tidak ada MP4 — tawarkan instal satu perintah (`winget install Gyan.FFmpeg` / `brew install ffmpeg`) atau rekam layar |
| Mempelajari video referensi (ekstrak frame) | `fps=` + `tile=` | minta user mengirim screenshot di detik kunci, atau buka videonya di browser dan potret pada detik tertentu |
Tanpa ffmpeg alur explainer tetap lengkap sampai sinkron VO; hanya MP4 yang
butuh instalasi.
## Player — tidak ada, autoplay, loop
Default deliverable: **tanpa panel/player apa pun di layar**, langsung
memutar saat dibuka, dan mengulang dari awal saat selesai (`onComplete →
play(0)`; bila ada suara, audio ikut diulang). Kontrol tersembunyi: R ulang,
Space jeda. Panel scrub/jam hanya muncul dengan `?debug=1` (alat review),
dan `?clean=1` menahan autoplay untuk export. Ada suara? Coba `play()`
langsung; bila diblokir browser, tahan di frame 0 dan mulai pada klik
pertama — tanpa teks "ketuk untuk mulai". Ini sudah tertanam di kedua
starter.
## Larangan struktural — uji PPT yang bisa diperiksa mekanis
Model lain (dan kamu, bila lelah) akan jatuh ke pola ini walau sudah membaca
hukum di bawah. Sebelum menyerahkan, cek KODE, bukan perasaan:
1. `grep -c "class=\"scene\"\|<section" index.html` — bila ≥ 3 adegan
berupa `<section>` yang dinyalakan-dimatikan dengan `autoAlpha`/opacity
→ itu slide deck. Adegan harus berganti karena DUNIA/KAMERA bergerak
(kamera bergerak, whip ke sudut lain, push-through, latar berganti),
bukan karena section di-fade. Pengecualian yang sah: **kartun panggung**
(`references/kartun-panggung.md`) memakai cut/geser 96 px antar panggung
— boleh, karena tiap panggung hidup penuh (≥10 benda beraksi), bukan
gambar diam yang di-fade.
2. Ada benang merah visual yang bertahan: satu subjek (aksi kontinu) ATAU
satu dunia kolase/kertas/putih yang disusuri kamera (kartun, foto,
katalog, sketsa). Foto full-bleed berganti-ganti tanpa dunia bersama →
PPT. Satu gambar + satu kalimat per adegan, berganti tiap adegan →
tetap slideshow walau kameranya bergerak: tiap adegan 3–5 elemen yang
masuk bertahap per frasa (explainer.md "Satu adegan = 3–5 elemen").
3. Per adegan hitung node teks: eyebrow/kicker + judul + body/kredit = 3
tingkat → PPT. Maksimum dua: satu angka/kalimat besar + satu label dunia.
Dokumen/stempel/blok tanggal berisi ≤ 3 baris pendek dihitung objek,
bukan tingkat teks.
4. Ken Burns (scale 1.0→1.05 pada foto) sebagai satu-satunya gerak → PPT.
Gerak tiap detik harus datang dari BAHASA GERAK LATAR yang dipilih di
style brief dari menu `techniques.md` §7c (kamera bernapas di latar
bertekstur, gradien berpindah, blob mengambang, grain hidup, sapuan
cahaya per segmen, bentuk besar berputar lambat, partikel naik, grid
bernapas, teks hantu bergeser, Ken Burns + parallax…). Batang/garis/
potongan yang melintas ke samping ("lane", "range", "streak", hujan
partikel horizontal) SUDAH dipakai dua proyek berturut-turut dengan nama
berbeda — itu bukan default; hanya bila tema memang kecepatan/aliran,
dan tidak boleh dua proyek berturut-turut.
5. Transisi hanya fade + scale bump + light leak di semua cut → template PPT.
Whip ke sudut lain, cut ke instrumen (peta/speedometer/profil), push-through.
6. Explainer dimulai dari starter GAYANYA: `starter-explainer-kartun`,
`-jurnalisme`, `-katalog`, `-sketsa` (mode kolase: kamera menyusuri aset
diam), `starter-explainer` (aksi kontinu: dunia mengalir), atau
`starter-explainer-panggung` (kartun panggung: satu panggung per adegan,
rig sendi, kamera hanya di dalam panggung). Yang kolase satu rig; yang
panggung rignya lain. BUKAN dari `assets/starter-opener.html`
(opener teks), dan bukan dari nol.
7. **Miniatur adalah slide.** Kamera zoom < 1,08 sehingga rumah sebesar ibu
jari dan tanah kosong mengisi separuh layar → PPT walau semua bergerak.
Dunia dipecah jadi panggung seukuran frame, bukan satu peta besar yang
dijelajahi (`kartun-panggung.md` Hukum 1).
8. **Kerangka template (opener/promo).** Cek rundown dan kode: adegan pertama
berupa teks yang diperbesar lalu keluar ke kiri; tiga tile/kartu fitur
sejajar; kotak input/searchbar yang diketik; urutan hook → fitur → fitur →
janji → logo → CTA. Dua atau lebih tanpa tuntutan konsep → template, walau
kulitnya baru. Pilih ulang kerangka dari `references/opener-konsep.md`.
Gagal satu poin saja → rombak sebelum ditunjukkan ke user.
## Jenis pekerjaan yang dicakup
Skill ini untuk motion graphic web secara UMUM. Explainer hanya salah satu
jenis — ia punya dokumen sendiri karena strukturnya beda, bukan karena ia
yang utama.
Starter dinamai menurut kategorinya: `starter-opener.html` untuk opener, promo,
bumper, intro, dan kinetic typography; `starter-explainer-*.html` untuk explainer,
dengan akhiran mode/gaya (`-kartun`, `-jurnalisme`, `-katalog`, `-sketsa` = kolase;
tanpa akhiran = aksi kontinu; `-panggung` = kartun panggung). Kartun panggung adalah
mode explainer (gaya 6), bukan kategori sendiri: tujuannya tetap menjelaskan dengan
VO, yang berbeda hanya cara produksinya.
| Jenis | Durasi lazim | Ciri | Resep |
|---|---|---|---|
| Opener / promo produk | 25–40 dtk | satu konsep dari menu (kerangka lahir dari produk, bukan urutan baku)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.