scenario-playable-ads — скилл для Claude Code: playable-реклама
Скилл scenario-playable-ads для Claude Code превращает запись игры, скриншоты или идею в HTML5 playable-рекламу. Он собирает интерактивный игровой фрагмент и конечную карточку с кнопкой установки для рекламных сетей.
MIT 196 установок ★ 3 964 обновлён 2026-10-23
npx skills add scenario-labs/skills --skill scenario-playable-ads -a claude-codeЧто делает scenario-playable-ads
Скилл собирает HTML5 playable-рекламу или конечную карточку из записи мобильной игры, скриншотов, готовых материалов либо краткой идеи. Он готовит игровой цикл как код, а имеющиеся графику и звук использует в исходном виде; недостающие материалы создаёт в том же стиле. Результат включает сборки для девяти сетей, локальный предпросмотр и ZIP-файлы.
Работа проходит через этапы анализа, подготовки ресурсов, сборки и проверки. Скрипты и шаблон лежат в папках scripts/ и assets/; сборку запускают через build.py, а проверку — через qa.py. Нужны локальная оболочка, Python 3.12 или новее с Pillow, numpy, scipy, fontTools и brotli, Playwright для Python с Chromium и ffmpeg. Для доступа к Scenario, загрузок и основного цикла требуется скилл scenario.
Какие задачи решает
- собрать playable-рекламу из записи игрового процесса
- превратить скриншоты и готовые ресурсы в интерактивный рекламный фрагмент
- подготовить рекламную игру по краткой идее или названию жанра
- упаковать HTML5-сборки для рекламных сетей
Примеры запросов агенту
- Сделай playable-рекламу по записи игры и скриншотам.
- Собери HTML5-рекламу по этой идее: мир, действие игрока, главный момент и завершение раунда.
- Подготовь игровые рекламные сборки для нужных сетей из этих ресурсов.
Как установить scenario-playable-ads
1Через Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-playable-ads -a claude-code2Вручную: положить файлы
~/.claude/skills/scenario-playable-ads/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/scenario-playable-ads/
1Через Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-playable-ads -a codex2Вручную: положить файлы
.agents/skills/scenario-playable-ads/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-playable-ads -a cursor2Вручную: положить файлы
.cursor/skills/scenario-playable-ads/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install scenario-labs/skills skills/scenario-playable-ads2Вручную: положить файлы
.github/skills/scenario-playable-ads/SKILL.md1Через Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-playable-ads -a gemini-cli2Командой платформы
gemini skills install https://github.com/scenario-labs/skills --path skills/scenario-playable-adsВручную: положить файлы
.devin/skills/scenario-playable-ads/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-playable-ads -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о scenario-playable-ads
Как установить scenario-playable-ads в Claude Code?
Запусти npx skills add scenario-labs/skills --skill scenario-playable-ads -a claude-code. Файл скилла находится по пути ~/.claude/skills/scenario-playable-ads/SKILL.md.
Что делает scenario-playable-ads?
Скилл превращает запись игры, скриншоты, готовые материалы или идею в HTML5 playable-рекламу либо конечную карточку с кнопкой установки. Он также собирает ZIP-файлы для рекламных сетей.
Что нужно для работы scenario-playable-ads?
Нужны локальная оболочка, Python 3.12 или новее с Pillow, numpy, scipy, fontTools и brotli, Playwright для Python с Chromium и ffmpeg. Для доступа к Scenario, загрузок и основного цикла нужен скилл scenario.
Исходный текст
SKILL.md · MIT
---
name: scenario-playable-ads
description: "Use when a mobile game's gameplay recording, screenshots, existing art and sound, or only an idea or a genre name should become a playable ad: an HTML5 interactive ad or end card for Meta, Google Ads App campaigns, AppLovin, Unity Ads, Mintegral, Moloco, Liftoff, TikTok Pangle or any MRAID network. Keywords: playable ad, HTML5 playable, MRAID, FbPlayableAd, ExitApi, crowd runner, merge, sort puzzle, survivor, tower defense, pin pull. Not for a video ad (scenario-game-ua-ads)."
license: MIT
---
# Scenario Playable Ads
## Overview
A playable is a 35 to 45 s slice of a real game that runs inside an ad network's container. It has:
- one self-contained HTML file with no network requests;
- one verb the viewer understands within 2 s;
- a game that waits for the viewer and never plays itself;
- a mute button, always;
- the genre's signature payoff;
- a win or an honest near-fail, then an end card with an install button.
**Input:** a gameplay recording and/or screenshots of the user's game, or only an idea (see Start
here), plus a logo, store links, a description and a genre pick when the user has them. When the
studio already has art, 3D, sound or music, the build uses those files as they are, generates only
what is missing in their style, or derives the rest from one key art
([references/existing-assets.md](references/existing-assets.md)).
**Output:** `dist/<network>/index.html` for nine networks and a local preview, the ZIP each ZIP
network takes, and a bundle of all of them. A build ships only when it passes the 19 base QA checks
plus the per-network checks.
**What was tested.** The scripts pass 67 of 67 checks on the template's placeholder game inside fake
containers in headless Chromium. On 2 November 2026 that game also passed AppLovin's playable
preview (portrait), Google's HTML5 validator (App Campaigns profile) and Meta's playable preview
(spec checks and the CTA tap). Google's Campaign Manager and Display & Video 360 reject the `google`
ZIP, which needs a `clickTag` there. No other network's own tool was run. Run each network's preview
first, and say which tools ran when you hand a build over
([references/networks.md](references/networks.md)).
Requirements: a local shell, Python 3.12 or later with Pillow, numpy, scipy, fontTools and brotli;
Playwright for Python with Chromium; ffmpeg. Install with
`pip install "pillow>=13,<14" "numpy>=2.5,<3" "scipy>=1.18,<2" "fonttools>=4.60,<5" "brotli>=1.1,<2" "playwright>=1.64,<2"`
then `playwright install chromium`; check with `ffmpeg -version`. The scripts, runtime and template
sit in this skill's `scripts/` and `assets/` folders, so the agent needs file access to the skill.
Connection, uploads and the core loop: the `scenario` skill. Image edits: `scenario-image`. Sheets
and cut-outs: `scenario-game-assets`. SFX and music: `scenario-audio`. Image-to-3D: `scenario-3d`.
If a sibling skill named here is missing from your available skills, load it with `skill_get`
(Scenario MCP) or ask the user to install it (https://github.com/scenario-labs/skills#install);
unattended, proceed from tool schemas and flag the gap.
## Quick reference
1. **Intake:** `intake/`: recording and/or screenshots (or the brief and two concept screens), logo,
`intake.json` (store links, networks, genre)
2. **Analysis:** contact sheet, key frames, `analysis/brief.md` and `analysis/design.md` (beats,
asset map)
3. **Assets:** plate, transparent sheets, HUD crops, logo, SFX, music in `assets/raw/`, or studio
files
4. **Build:** `src/game.js`; `assets/manifest.json` + `sounds` in `index.src.html`; `prep_assets.py`
5. **Package:** `build.py --networks all` (the default is `meta,google`)
6. **QA:** `qa.py --speed 2`, then look at every frame it writes
7. **Report:** `notes.md`: job ids, the source frame of every asset, tuning, open questions
```bash
SKILL=<path to this skill>; P=<project dir>
cp -Rn "$SKILL/assets/template/." "$P/" && mkdir -p "$P/runtime" && cp "$SKILL/assets/runtime/runtime.js" "$P/runtime/"
python3 "$P/make_placeholders.py" "$P" --font "$SKILL/assets/fonts/fredoka/Fredoka-Bold.woff2" # optional
python3 "$SKILL/scripts/asset_inventory.py" "$P" # only with the studio's own files: analysis/assets_inventory.md
python3 "$SKILL/scripts/prep_assets.py" "$P" # assets/raw and intake/ to assets/web/
python3 "$SKILL/scripts/build.py" "$P" --networks all
python3 "$SKILL/scripts/qa.py" "$P" --speed 2 # qa/report.json and qa/*.png
```
- `cp -Rn` never overwrites what the project already has, such as `intake/`.
- Never edit the runtime or the scripts per game. Work around a gap in the game's own code and write
it in `notes.md`.
- Replace the template's game section with your genre. Keep its structure: config, reset, wait,
play, result, input on pointerdown, draw, `qa()` with `progress`, boot.
- The hint hand is a vector drawing unless the project adds `assets/web/hand.webp`.
## Start here
When the user has not yet said what they have (for example "how do I make a playable ad?"), ask
once, in one message, for everything the build needs, then wait. Do not generate anything yet.
1. A gameplay recording of 30 s to 2 min and/or store screenshots. With neither (only an idea or a
genre name), ask instead for one paragraph: the world, what the finger does, the big moment, how
a round ends. Then follow "From an idea" below.
2. The game name, the logo file, the App Store and Google Play links, and one line on what the
player does.
3. The ad networks they run, or "not sure" (the build covers nine).
4. Whether the game is 3D with a free camera (see the decision points below).
5. Any art, 3D, sound or music they already have for the game, and whether they own it for ads
([references/existing-assets.md](references/existing-assets.md)).
Say in two lines what they will get: the core loop rebuilt as code, their own art and sound where
sent and generated for the rest, never the recording itself, so side features are simplified. Then
ask the genre question below and, when they sent files, how to use each kind (as supplied,
complement or derive). Those are the only two rounds of questions; the Scenario team and project,
when the `scenario` skill asks for them, go in the first.
Asked which genres or mechanics it can build, list the **built** rows of
[references/genres.md](references/genres.md), then its _nearest_ rows with their starting guide.
Never call those built.
### From an idea
- The paragraph is the brief (`game_description`) and plays the recording's role. A genre the user
named answers the genre question.
- Build only what the brief and the genre guide state. The brief wins where they disagree; the guide
fills the rest, motion and timing included.
- A brief without what the finger does or the big moment gets one follow-up, in the genre round.
Unattended, or with no paragraph, stop and report what is missing.
- After the genre answer, unless supplied art replaces them, make two portrait concept screens, the
calm first screen and the big moment: `img2img` per section 4 of
[references/existing-assets.md](references/existing-assets.md) with supplied art, else `txt2img`
(the `scenario` skill's loop). State the `dry_run` price first; unattended, run them only within
the build's stated budget, else report and stop. They serve as the screenshots
([references/scenario-assets.md](references/scenario-assets.md)).
- Hand the build over as a concept, not their game. Without store links, the packages are preview
only.
## Two questions before generating anything
Answer both in `analysis/brief.md`.
1. **Which genre is it?** Watch the recording first (contact sheet and key frames). From an idea,
read the brief wherever this step says the recording. Then ask one question with these options:
- the two genres from [references/genres.md](references/genres.md) that fit best, each with a
one-line reason from the recording (what the finger does, the most satisfying moment);
- "I don't know, you choose": pick the best fit and say why in one line;
- "Other": ask what the player does and what makes it fun, and store it as `game_description`.
Record the answer in `intake.json`. Classify from the recording, not the label, and state your
confidence. No guide, a hybrid, or a game too big for one verb: follow
[references/unknown-genre.md](references/unknown-genre.md). Never invent a mechanic the recording
does not show.
2. **Why would someone install after playing?** Plan the levers from
[references/make-them-install.md](references/make-them-install.md): a first touch that pays off
at once, visible growth, one real choice, a tease from the recording or the brief, a cliffhanger
ending with the player's own state on the end card.
## Decision points
1. **Genre and product model** (hypercasual, hybrid-casual, casual, midcore) go into `intake.json`.
The genre's row names its guide or the nearest one.
2. **Hook:** one opening pattern while the game waits: a power spike, a near-win, a satisfying
motion, or a clear promise. One short line on a backing plate. Fail-bait is allowed only as the
player's own choice.
3. **Signature payoff:** the moment that makes the genre (a screen wipe, a crowd clash, a legendary
merge), at 10 to 25 s of play, the biggest and loudest thing in the ad.
4. **Ending:** a good player wins, a careless one ends one step short, an untouched viewer gets the
end card after 10 s. Cap play at 35 to 45 s after the first touch.
5. **Original IP:** when the genre has a famous leader, list what the game must not share with it
(characters, piece shape, board and track silhouette, how ammo is shown, the name). Have a human
compare with the leader's store page. See
[references/archetype-paint-train.md](references/archetype-paint-train.md).
6. **Networks:** ask which ones the user runs. Per-network contracts, confirmed facts and the
unconfirmed list: [references/networks.md](references/networks.md).
7. **3D games:** ask before generating. A fixed or side camera means 2.5D from frames; a free 3D
camera means considering three.js with an image-to-3D model. Unattended, build 2.5D and say so.
See [references/3d-games.md](references/3d-games.md).
8. **Orientation:** portrait first. Re-slice a landscape level along the portrait axis instead of
letterboxing it, and collapse an on-screen pad to one finger (say it is drift and ask the user;
unattended, ship the one-finger verb and record the drift in `notes.md`).
## Archetype index
Each built guide, with its ad verb:
- [Survivor shooter](references/archetype-survivor.md): tap to move, auto-fire, tap a card
- [Crowd runner with math gates](references/archetype-crowd-runner.md): drag left and right
- [Lane shooter with gates](references/archetype-lane-shooter.md): drag left and right, auto-fire
- [Merge-2](references/archetype-merge.md): drag an item onto its twin
- [Sort puzzle](references/archetype-sort.md): tap source, tap target
- [Conveyor color puzzle](references/archetype-paint-train.md): tap to dispatch a shooter
- [Pin pull](references/archetype-pin-pull.md): tap or swipe a pin
- [Idle arcade](references/archetype-idle-arcade.md): tap to move
- [Tower defense](references/archetype-tower-defense.md): tap a pad to build or upgrade
- [Platformer, as a portrait climb](references/archetype-platformer.md): tap where to land, tap
again in the air
- [Racing, real 3D](references/archetype-racing.md): drag to steer, tap to boost
A new archetype gets `references/archetype-<name>.md` with these sections: Controls, Beat sheet,
Tuning, QA bot pattern, Asset map with source frames, Mistakes seen. Then add it here and mark it
built in `genres.md`.
## Rules every playable follows
- **Never autoplay.** The game never makes a move for the player: no demo, no rescue autopilot, no
auto-picked card. The world may run where that is the genre (a crowd runs forward), but every
choice is the player's.
- **Wait, alive, for the first touch.** The gameplay clock is held, the target glows, and the hand
loops the exact gesture on a real good move. `qa()` exposes `progress`, which stays 0 until the
first touch.
- **Three endings:** the goal, a time cap of 35 to 45 s of play, and a 10 s idle timeout. After a
start, an honest line shows for at most 1.5 s before the end card.
- **Hint, never a move.** The hand returns after 2.5 s idle and only points.
- **Mute button, always.** The runtime draws it and it cannot be turned off; `cfg.mute` only moves
it. It never counts as the first touch.
- **The first tap never opens the store** on `applovin`, `unity` and `mraid`. The runtime enforces
it.
- **Calm sounds.** Nothing repeats faster than about 3 times a second (`cfg.soundGap`). Duck the
music around each payoff (`PA.audio.duck`) and boost quiet takes with `boost_db`, never plain
gain.
- **Honest result text,** computed from the real state: "SO CLOSE! 1 left!" only when one move
remains.
- **A near-fail for bad play.** Scripted luck rewards the player's own good moves, so careless play
ends just short.
- **Replay** calls `PA.clearTweens()` before `reset()`, and the game waits again.
Asset sourcing, prompts and model discovery:
[references/scenario-assets.md](references/scenario-assets.md). Starting from the studio's own
files: [references/existing-assets.md](references/existing-assets.md). Lessons and known runtime
gaps: [references/build-lessons.md](references/build-lessons.md). Every QA check, build refusal and
the game contract: [references/qa-checks.md](references/qa-checks.md).
## Worked example: a sort puzzle from a 40 s recording
1. The user drops `gameplay.mp4`, a logo and store links in `intake/`. A 4 fps contact sheet shows
taps that pour liquid between jars, and a jar that pops when full. Ask the genre question with
`sort-puzzle` and `match-tile`; the user picks `sort-puzzle`.
2. `analysis/design.md`: the hook "Can you sort them all in one go?", a jar pop at about 12 s, a
near-fail with one jar left, and a tease of a locked level 25 on the end card.
3. Upload three frames. Generate the plate (an image edit that removes jars, liquids and HUD), one
transparent sheet of jars and the mascot, five SFX and a 30 s music loop, each via `recommend`,
`model_schema_get`, `dry_run`, `model_run` with `wait=false`, and `jobs_wait`. Key the user's
logo with `"key": true`.
4. Write the solver and the game from [references/archetype-sort.md](references/archetype-sort.md).
Run `prep_assets.py`, then `build.py --networks all`.
5. `qa.py --speed 2` fails `idle_never_autoplays`: a demo pour moved `progress` before the first
touch. Remove it, let the hand loop the pour gesture instead, and rebuild.
6. Open every `qa/story_*.png`: a banner covers the jar it describes. Move it to the top band.
7. Hand over the bundle ZIP with `notes.md`, naming the networks whose own tools ran
([references/networks.md](references/networks.md)); the rest ran only in fake containers.
## Common mistakes
- **An ad that plays itself.** A demo takes the move away from the viewer.
- **A dead waiting screen,** which fails `hook_moves_without_input` and looks broken.
- **A hint on the wrong spot.** The hand must point at a real good move from the solver or the level
script.
- **Chattering sounds:** a tick per coin at 10 to 25 a second. One sound per event group.
- **Paying for sound variants.** A rising or alternate version of a sound is the same take at
another `rate` (`PA.audio.play(name, vol, rate)`), not a new job. Generate one take per event
group, and a second only for a rejected take: the archetype tables' "2 takes each" records past
builds, not a target. `dry_run` each sound payload and state the sum before launching any
(unattended: only within a stated budget, else report and stop). A variant needing its own repeat
limit gets its own manifest and `sounds` entry on the same raw file: a new name, never a new job.
- **Hard-coded near-fail text,** which lies to players who lost by a lot.
- **Copying recording glitches or platform UI,** or baked HUD numbers. Redraw numbers live.
- **Cutting a sheet by grid math.** Sprites cross the cells: use `"blob": n` and check `--blobs`.
- **Decorative buttons that look live.** Make them work, or make them a CTA.
- **Units or zeros the game never shows** on the end card.
- **An asset with no source frame** in the asset map.
- **Editing the studio's files in place,** or generating a piece they supplied.
- **Claiming a network passed** when only `qa.py` ran.
## Files
- Scripts, run by the agent: [scripts/asset_inventory.py](scripts/asset_inventory.py) (catalog the
studio's own files), [scripts/prep_assets.py](scripts/prep_assets.py) (crop, cut out, key,
compress, subset fonts), [scripts/build.py](scripts/build.py) (inline and package per network),
[scripts/qa.py](scripts/qa.py) (Playwright QA in fake containers),
[scripts/pack_glb.py](scripts/pack_glb.py) (a GLB into a JS include for three.js).
- Runtime, copied into each project: [assets/runtime/runtime.js](assets/runtime/runtime.js)
(`window.PA`).
- Template game: [index.src.html](assets/template/src/index.src.html),
[game.js](assets/template/src/game.js), [manifest.json](assets/template/assets/manifest.json),
[intake.json](assets/template/intake/intake.json), [qa_bot.py](assets/template/qa_bot.py),
[make_placeholders.py](assets/template/make_placeholders.py).
- OFL fonts with their licenses: [Fredoka](assets/fonts/fredoka/Fredoka-Bold.woff2)
([OFL](assets/fonts/fredoka/OFL.txt)), [Rajdhani](assets/fonts/rajdhani/Rajdhani-Bold.woff2)
([OFL](assets/fonts/rajdhani/OFL.txt)),
[Lilita One](assets/fonts/lilita-one/LilitaOne-Regular.woff2)
([OFL](assets/fonts/lilita-one/OFL.txt)),
[Orbitron](assets/fonts/orbitron/Orbitron-ExtraBold.woff2) ([OFL](assets/fonts/orbitron/OFL.txt)).
© scenario-labs · MIT · scenario-labs/skills