К основному содержанию
скилл CX Codex

ai-illustrations — скилл для Claude Code: генерация иллюстраций

Скилл ai-illustrations для Claude Code добавляет сгенерированные изображения в видеомонтаж. Он включается, когда в задании разрешены AI-иллюстрации или запрошены изображения для видео.

MIT ★ 147 обновлён 2026-11-13

Установить в Claude Code · Через Skills CLI (Vercel) Все способы и платформы ↓
npx skills add notivn/AIEVv2 --skill ai-illustrations -a claude-code
Открыть на GitHub

Что делает ai-illustrations

Скилл выбирает фрагменты видео, которым нужна иллюстрация, готовит промпт и отправляет запрос на POST /api/illustrations. Сервер выбирает подключённого провайдера, применяет стиль проекта и подгоняет изображение под размер кадра. Скилл также описывает, как добавить результат в композицию.

Иллюстрации создаются только при включённом переключателе «Ảnh minh họa AI» в задании. Если он выключен или строка отсутствует, запросы не отправляются. Для генерации нужен работающий сервер и настроенный провайдер: Gemini API с ключом GEMINI_API_KEY, учётная запись ChatGPT через локальный шлюз или cookie Google через gemini-webapi worker. В каждом запросе передаётся styleId из задания; промпт описывает содержание сцены, а не её расположение.

Какие задачи решает

  • выбрать фрагменты видео для иллюстраций
  • создать изображения в стиле проекта
  • добавить иллюстрации в видеокомпозицию
  • соблюсти переключатель генерации из задания

Примеры запросов агенту

  • Добавь AI-иллюстрации к видео по включённому переключателю в задании.
  • Выбери фрагменты, где иллюстрация прояснит содержание, и добавь их в монтаж.
  • Сгенерируй иллюстрации для проекта, сохрани стиль из задания.

Как установить ai-illustrations

1Через Skills CLI (Vercel)

npx skills add notivn/AIEVv2 --skill ai-illustrations -a claude-code

2Вручную: положить файлы

~/.claude/skills/ai-illustrations/SKILL.md

Папка скилла целиком; для одного проекта — .claude/skills/ai-illustrations/

По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов

Вопросы об ai-illustrations

Как установить ai-illustrations в Claude Code?

Выполни npx skills add notivn/AIEVv2 --skill ai-illustrations -a claude-code. Файл скилла появится по пути ~/.claude/skills/ai-illustrations/SKILL.md.

Что делает ai-illustrations?

Скилл выбирает моменты видео для изображений, отправляет запросы на POST /api/illustrations и описывает добавление результатов в композицию. Он работает только при включённых AI-иллюстрациях в задании.

Что нужно для работы ai-illustrations?

Нужен работающий сервер и настроенный провайдер: Gemini API с ключом GEMINI_API_KEY, учётная запись ChatGPT через локальный шлюз либо cookie Google и worker gemini-webapi.

Исходный текст

SKILL.md · MIT
---
name: ai-illustrations
description: Generate illustrations through the configured image provider (Gemini API, ChatGPT web account or Gemini web cookie - the server routes it) and composite them into the video being edited - how to pick the moments that need an image, write the prompt, call the /api/illustrations endpoint (images MUST match the selected Style Design), and composite into the composition. Read when the brief enables "Ảnh minh họa AI" (AI illustrations) or the user asks for generated illustrations for a video.
---

# AI Illustrations - Claude directs, the image provider draws, brand stays consistent

## ⛔ GATE - read before anything else

This skill applies **only when the edit prompt says "Ảnh minh họa AI: BẬT"** (AI illustrations ON).

If the edit prompt says **"Ảnh minh họa AI: TẮT"**, or has no illustration line at all: **generate nothing.**
Do not call `POST /api/illustrations`, do not composite AI-generated images into any scene, and do not let
another skill's "use an illustration here" suggestion talk you into it. Build the visuals from what the project
already has: assets in `assets/`, brand logos, and HyperFrames scenes (typography, graphics, shapes, motion).

The server enforces this too - with the switch off the endpoint returns `409 ILLUSTRATIONS_DISABLED` before it
spends anything. **Why this section exists:** the edit prompt used to stay silent when the switch was off, this
skill got read anyway, and finished videos came back full of AI images the user had explicitly turned off.
A silent prompt is not permission.

**Never route around the switch.** `POST /api/projects/:id/generate-image` is the editor's manual "AI filler"
button for the human user, not a tool for you - it returns `409 AGENT_BUSY` while your session runs. Do not
call it, and do not call a provider (Gemini API, the ChatGPT/Gemini gateways on 127.0.0.1) directly either.

## Image providers - the server picks, you do not

Every image goes through `POST /api/illustrations`; the server routes it to one of three providers
(`apps/server/src/imageProviders/`):

| Provider id | What it is | Cost / speed |
|---|---|---|
| `gemini-api` | Gemini API key (`GEMINI_API_KEY`) | ~$0.05-0.07 per image, ~10-20s |
| `chatgpt-web` | the user's ChatGPT account, via the local chatgpt2api gateway | uses the account's limited image quota, 30s to several minutes |
| `gemini-web` | the user's Google account cookie, via the gemini-webapi worker | uses the account's quota, 20-90s; visible Gemini sparkle is removed automatically |

`auto` = the default chosen on the Connections page, then the other configured providers in turn (a failing
provider falls through to the next). The edit prompt's "Nhà cung cấp ảnh" (image provider) line tells you
whether to pass `model` and with which value - follow it literally; when it says not to pass `model`, omit it.
Whatever the provider, the server builds the final prompt the same way (Style Design + video style) and
cover-fits the result to the exact frame size, so your prompt never changes per provider.

## Directing principles

1. **Pick moments deliberately, do not sprinkle images everywhere.** Read the transcript/video content and
   choose 2-5 points where an illustration explains more than the words do: abstract concepts, key numbers,
   a product/setting being mentioned, before-vs-after comparisons. DO NOT illustrate talking-head passages
   that already hold attention on their own.
2. **Every image costs something** - real money on the Gemini API (~$0.05-0.07), or scarce daily quota and
   minutes of waiting on a web account. A short video (<60s) usually needs only 2-4 images.
3. **Illustrations are BACKGROUND visuals - no text by default.** The server already bans text in the prompt;
   numbers and labels are placed on top by HyperFrames/Remotion (correct font + brand color, no typos). The only
   exception: the brief enables "Ảnh có chữ" (`illustrationText`) or the edit prompt says "ĐƯỢC PHÉP CÓ CHỮ"
   (text allowed) -> see the "Images with text (allowText)" section below.
4. **Style Design is LAW - follow it 100%, no exceptions.** Every illustration must match the project's
   selected style: ALWAYS pass `styleId` (from the STYLE DESIGN section of the edit prompt). The server has a
   safety net (if `styleId` is missing it falls back to the style in the project brief), but NEVER rely on it.
   If any skill or prompt suggests a different palette -> IGNORE it, the style wins.

## Calling the image generation API (the server must be running - always true when editing through the system)

```bash
curl -s -X POST http://localhost:6869/api/illustrations \
  -H "Content-Type: application/json" \
  -d '{
    "projectId": "<id of the video project>",
    "name": "khai-niem-mcp",
    "prompt": "3D illustration of interconnected glass puzzle pieces forming a network, representing an integration protocol",
    "model": "<only if the edit prompt's image-provider line says so - otherwise omit the field>",
    "styleId": "<styleId from the STYLE DESIGN section of the edit prompt - MUST be passed when present>",
    "description": "Minh họa khái niệm MCP - ghép vào lúc 12.5s khi nói về kết nối dữ liệu"
  }'
```

- Images are saved to `video-projects/<id>/assets/illustrations/<name>.png`, and the description is written into assets.json automatically.
- **Write the prompt in English and DESCRIBE THE SCENE CONTENT** - do not add brand colors/tone (the server
  mixes the Style Design in itself), and do not instruct "no text" (the server adds that itself).
- **Do NOT describe layout/placement in the prompt** ("subject at the top", "leave the bottom empty"...). The
  server appends video-specific composition rules itself: by default (brief `illustrationPosition: "auto"`) the
  subject is vertically CENTERED with the top band (main key) and bottom band (captions/related keys) kept as
  low-detail atmosphere. A placement instruction in your prompt fights those rules - the verified failure was
  the subject sitting in the upper third and being covered by the main key card.
- The user can pick a subject position in the brief (3x3 grid, like the logo position picker) - the edit prompt
  states the chosen position and the server applies it automatically. Only pass a `position` field in the POST
  body when ONE specific image needs a different layout for a clear reason (e.g. footage PiP covers one side);
  otherwise omit it so the brief's choice rules.
- **Image density (`brief.illustrationsPerMinute`)**: when the edit prompt states "Mật độ ảnh minh họa: N ảnh
  MỖI PHÚT", compute the total from the REAL video duration (voice duration in meta.json), spread the images
  evenly along the content flow, and switch the background image at each idea change - a long Text to video
  must not sit on one static background. Each image still needs its own content-specific prompt; do NOT
  mass-generate near-identical variations. When the prompt says "AI tự quyết" (density null), keep the old
  behavior: pick only the moments that genuinely need an illustration.
- **Omit `aspect`**: the server then cover-fits the image to the project's exact `width x height`. Pass
  `aspect` ("9:16" | "16:9" | "1:1" | "4:5") only when one image is meant for a box with a different shape
  (e.g. a square card inside a vertical video).
- The response carries `provider` (which one actually drew it). Errors and what to do:
  `NO_IMAGE_PROVIDER` / `NO_GEMINI_KEY` / `GATEWAY_NOT_INSTALLED` (nothing configured),
  `GATEWAY_AUTH_FAILED` (token/cookie expired), `GATEWAY_RATE_LIMITED` (quota used up) -> say so in the final
  report (the user fixes it on the "Kết nối" (Connections) tab) and build that moment with HyperFrames instead -
  do not get stuck and do not retry in a loop. `GATEWAY_TIMEOUT` / `GATEWAY_FAILED` -> retry once with a
  reworded prompt, then move on. A web-account image can take minutes: use a long curl timeout
  (`--max-time 900`) and generate images one at a time, not in parallel. The server enforces this too:
  ChatGPT web / Gemini web images run through a per-gateway queue (one image at a time, plus a
  configurable pause between images - "Kết nối" tab, default 10s), so a parallel call just waits its turn
  and a slow response is the queue, not a hang - do not retry it.
- `description` MUST always state which point the image illustrates + the second it is expected to be composited at.

## Images with text (allowText)

Only use this when the brief enables `illustrationText` (the edit prompt says "Ảnh minh họa ĐƯỢC PHÉP CÓ CHỮ")
or the user explicitly asks for it. How to do it:

- Pass `"allowText": true` in the POST /api/illustrations body. If the field is missing the server falls back to
  the project's `brief.illustrationText` - but NEVER rely on that, pass it explicitly.
- In the prompt, spell out the EXACT Vietnamese text you want to appear (3-6 words, correct spelling, all diacritics),
  e.g. `... with the exact Vietnamese headline "TĂNG TRƯỞNG 300%"`. Never let the model invent the text itself.
- **You MUST verify the spelling after generation**: Read the image file and inspect every character and Vietnamese
  diacritic. Image models (all three providers) often mangle diacritics (Ề->E, ữ->u) or add garbage text. If it is wrong -> regenerate (rephrase
  the prompt if it keeps failing), or give up after 2-3 attempts and generate a text-free version (`allowText:false`),
  then let HyperFrames/Remotion place the text as usual.
- If the text is already inside the image, DO NOT overlay duplicate text with HyperFrames/Remotion.

## Compositing into the video

- HyperFrames: insert `<img src="assets/illustrations/<file>.png">` in the scene, animate it in and out
  (gentle fade/slide/scale per the hyperframes skill's house-style), and hold it 2-4 seconds around the exact sentence it relates to.
- Sensible coverage: an illustration usually covers 50-75% of a vertical frame and MUST NOT cover the speaker's face
  mid-way through an important sentence; bring it in on the sentence beat (use transcript timestamps).
- Verify with a snapshot after inserting: image in the right place, not distorted (aspect ratio preserved), not bleeding off the edge.

## The brand logo is NEVER generated

If the selected Style Design has a logo, the real file is copied into the project at
`assets/brand-logo.<ext>` before the edit session starts, and the edit prompt carries a mandatory
LOGO block. Rules:

- Insert **that exact image file** (`<img>` in a HyperFrames scene, or `srcImage`/overlay in Remotion).
- Never redraw the logo in CSS/SVG/shapes, never ask the image model for it, and never substitute the brand
  name set in a font. A typeset name where a logo belongs is a brand violation, not a fallback.
- Only size and position may change: no distortion, recolouring, rotation, cropping, or added
  borders/shadows on the mark itself.
- If it genuinely cannot be placed, say so in the final report instead of improvising.

**Symptom:** the image model renders an invented logo - a glossy monogram on a wall, a mark on a t-shirt or phone screen.
**Cause:** the scene prompt mentioned a logo, which flipped the permissive "decorative brand logos are allowed"
clause on. Adding a prohibition alongside it is **not enough** - measured: with both clauses present the model
followed the permissive one and drew an "N" monogram.
**Fix (already in `buildImagePrompt`):** when `design.logoPath` exists the permissive branch is dropped entirely,
the prohibition tells the model to leave that surface *blank*, and it is repeated as a FINAL RULE at the end of
the prompt. Verified on three hard prompts (logo on a wall / on a t-shirt / on a phone screen): all three came
back with a clean empty surface, which is exactly what you want to composite the real logo onto.
So: **do not write "with the brand logo" into an illustration prompt.** Ask for the blank surface you need
(an empty plaque, a blank screen) and place the real file on top yourself.

**The corner logo is automatic.** When the style has a logo, the assemble step stamps it top-left over the
whole video (`manifest.watermark`). Do not add your own corner logo as well - that yields two overlapping
marks. Place the logo by hand only where you deliberately want it (intro card, end card, a framed mention).

## Other companies' logos - use the library, never draw them

`assets/brand-logos/` holds official brand marks with each brand's official hex colour;
`assets/brand-logos/library.json` is the index - read it rather than guessing file names. The library grows
by itself: any brand a video mentions gets fetched once and stays for every later video.

**Workflow:** read the script, list every brand it names, and resolve each one *before* building the scene
that mentions it.

- Need Facebook / TikTok / Claude / Gemini in a scene? **Use the file.** Never redraw a third-party logo and
  never ask an image model for one; a wrong brand mark is spotted instantly.
- **Copy the file into the project's `assets/` first**, then reference it. Remotion only stages paths inside
  the project, so pointing straight at `assets/brand-logos/` renders a 404.
- The SVGs are single-colour (black by default). To recolour, inline the SVG and set `fill` - use the official
  hex from `library.json`, or plain white/black when the background demands it.
- (Same rule for every image provider: never ask an image model to draw a third-party logo.)
- **Brand not in the library? Fetch it, do not skip it.** `POST http://localhost:6869/api/brand-logos`
  with `{"name":"OpenAI"}`. The server looks in Simple Icons, then Wikidata's P154 "logo image" property,
  downloads the official file into `assets/brand-logos/`, and returns `relPath`. 201 = newly fetched,
  200 = already there. Brands missing from Simple Icons because their owners asked to be removed
  (OpenAI, Amazon, Microsoft…) come back from Wikidata in **full colour**.
- Only a `404 BRAND_LOGO_NOT_FOUND` justifies going without: then set the brand name in the Style Design
  font and record it in the final report. **Never** draw, improvise or generate a brand logo - in any case.
- CC0 covers the *files*, not the trademarks. Referring to a brand is fine; implying it sponsors or endorses
  the video is not.

## Known issues

- Generating an image and forgetting to composite it - final checklist: every image in `assets/illustrations/` must
  either appear in the composition or be deleted (do not leave orphan images that wasted money).
- Overly generic prompts ("technology background") -> lifeless images. Describe specific objects/setting/camera angle.
- The SAME image need across multiple scenes -> generate one image and reuse it, do not call the API twice.
- **Garbage text baked into the image despite allowText=false** (verified 2026-08, gemini-3.1-flash-lite-image):
  the model sometimes prints prompt-like gibberish ("Overlay cards", hex codes, pseudo-lorem) in the letterbox
  bands, or invents a brand tag, even though the server prompt bans text. Measured on one batch: 3 of 12 images
  affected; one concept needed 2 retries. So you MUST Read every generated PNG before compositing. On failure,
  regenerate with a reworded prompt (same content, different sentence structure) - that was enough in every
  observed case. Delete the bad files so they are not composited by accident.
- **Web-account providers ignore exact sizes.** ChatGPT web and Gemini web have no real size parameter - they
  return roughly the requested ratio. The server cover-fits every image to the exact frame with ffmpeg, which
  can crop a little off the long edge: keep important detail away from the edges (the composition rules the
  server adds already ask for that).
- **Gemini web may answer with text instead of an image** ("I can't create images for you right now"): that is
  a signed-out/expired cookie or a region without image generation - the server reports it as
  `GATEWAY_AUTH_FAILED`/`GATEWAY_FAILED`; tell the user, do not rephrase the prompt over and over.

© notivn · MIT · notivn/AIEVv2

Похожие скиллы

Все скиллы по теме «Дизайн» →
create-svg-illustrations narumiruna Скилл create-svg-illustrations для Claude Code и Codex создаёт и правит векторные иллюстрации и диаграммы SVG. Помогает встроить графику в презентации, документацию и веб-страницы с учётом доступности. CX Codex +1 211установок hyperframes-keyframes coco-research Скилл hyperframes-keyframes держит анимацию в композиции HyperFrames перематываемой: собирает кейфреймы для GSAP, CSS, Anime.js и WAAPI и проверяет кадры до рендера. CX Codex +1 ★ 328звёзд репо hyperframes coco-research Точка входа для сборки видео, анимаций и моушн-графики в Claude: ведёт от идеи или брифа до готовой HTML-композиции HyperFrames. CX Codex +1 ★ 328звёзд репо c-video-edit daxaur Скилл c-video-edit для Claude Code создаёт и собирает видео из кода с помощью Remotion и Editly: анимированные ролики, заставки и слайд-шоу. CX Codex +1 ★ 179звёзд репо slidewright tronghieu Скилл slidewright собирает слайды как сайт для показа на большом экране: один ведущий, аудитория только смотрит. Два варианта — один HTML-файл или проект на Vite + React. CX Codex +1 ★ 117звёзд репо design-thinking tronghieu Скилл design-thinking для Claude Code, ведёт проект через этапы Empathize, Define, Ideate, Prototype и Test на реальных данных о пользователях. Разбирается, почему люди уходят или чего им не хватает. CX Codex +1 ★ 117звёзд репо

Из того же набора15

Весь набор →
key-layout Скилл key-layout для Claude Code размещает главную тему видео сверху, а связанные тезисы — над субтитрами. Подключается, когда в брифе включён keyLayoutEnabled или в промпте есть раздел «Bố cục Key: BẬT». CX Codex +1 ★ 147звёзд репо offline-voice Скилл offline-voice для Claude Code объясняет настройку локального движка озвучки VieNeu-TTS и клонирования голоса. Включается при отладке маршрутов /api/tts и озвучки видео. CX Codex +1 ★ 147звёзд репо make-a-video make-a-video — скилл для Claude Code, который ведёт от идеи к готовому MP4 через HyperFrames. Он собирает требования, готовит сценарный план и проверяет видео перед финальным рендером. CX Codex +1 ★ 147звёзд репо auto-cut Скилл auto-cut для Claude Code убирает тишину, оговорки и повторы дублей из видео с говорящей головой до монтажа. Включается по флагу autoCut в брифе или при жалобах на паузы. CX Codex +1 ★ 147звёзд репо remotion-assemble Скилл remotion-assemble для Claude Code настраивает сборку видео из сцен HyperFrames, футажей, голоса и звуков по файлу meta.json. Инструкции включаются при редактировании кода в каталоге engines/remotion. CX Codex +1 ★ 147звёзд репо video-pipeline Скилл video-pipeline для Claude Code описывает путь от запроса до MP4 и распределяет работу между HyperFrames и Remotion. Запускается при создании видео или настройке очереди рендеринга. CX Codex +1 ★ 147звёзд репо noti-tiktok-full-text Скилл noti-tiktok-full-text для Claude Code собирает вертикальные TikTok-видео с разбором научных статей через HyperFrames. Включается по стенограмме, иллюстрациям и сканам страниц PDF. CX Codex +1 ★ 147звёзд репо short-form-video Скилл short-form-video для Claude Code помогает собирать и править вертикальные ролики в Hyperframes с говорящей головой, графикой и караоке-субтитрами. Запускается по запросам о TikTok, Reels, Shorts и пересборке короткого видео. CX Codex +1 ★ 147звёзд репо

Спонсоры проекта

Компании, которые помогают держать аналитику открытой