メニュー
Generates images using OpenRouter. Triggers on /generate-image [prompt] [--model model-id] or automatically when an image is needed in context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Gathers the project details each specialized coder needs before it writes code — frontend theme/typography/layout, backend API/caching/DB shape, containerization build/runtime shape, CI/CD pipeline shape — then hands each coder only its scoped answers. Use before invoking any coder, once a worktree feature is scoped, or whenever splitting work across parallel coders.
Builds a missing `<lang>-guidelines` skill for a language/stack, packaged as a standalone plugin and registered in a marketplace, before any code is written. Use whenever no `<lang>-guidelines` skill exists yet for the stack about to be coded (React, FastAPI, Docker, CI/CD, or anything else) — invoke this FIRST, before any coder runs, then follow the generated skill.
Invoke BEFORE writing any Dockerfile or containerizing an app for deployment. Language-agnostic image-build conventions — multi-stage builds, non-root, layer caching, healthcheck, and hadolint tooling.
Invoke BEFORE writing any Python code (CLI tools, libraries, APIs, modules, tests). Encodes the project's Python + uv + ruff + pyright + pytest architecture, plus conditional references for DB, API, and caching work.
Invoke BEFORE writing any React/TypeScript frontend code (components, hooks, routes, forms). Encodes the project's React + TypeScript + Vite + pnpm conventions, architecture rules, and tooling commands.
Running log of the user's environment preferences and configuration changes — CLAUDE.md rules, settings, and conventions. Use to recall how the user likes their environment set up, and append a dated entry whenever you make an environment change (anything that isn't building a skill).
SOC 職業分類に基づく
| name | generate-image |
| description | Generates images using OpenRouter. Triggers on /generate-image [prompt] [--model model-id] or automatically when an image is needed in context. |
Invoke this skill when:
/generate-image [prompt] — optionally with --model [model-id]The generate-image script path was provided at session start (see [image-generator] Tool script ready in session context).
Use the Bash tool to call it directly:
node "<script-path-from-session-context>" "<prompt>" [--model <model-id>] [--output-dir <dir>]
The script handles everything: API call, response parsing, base64 decode, file save.
It prints Image saved: <path> on success or a clear error message on failure.
# Default model (google/gemini-3.1-flash-image-preview)
node "/path/to/scripts/generate.js" "a sunset over mountains"
# Override model
node "/path/to/scripts/generate.js" "a minimalist cat logo" --model google/imagen-4.0-generate-001
# Save to a specific directory
node "/path/to/scripts/generate.js" "abstract art" --output-dir ./assets
Report to the user:
All models use OpenRouter's /api/v1/chat/completions endpoint — no special routing needed.
| Model | Notes |
|---|---|
google/gemini-3.1-flash-image-preview | Default — best quality |
google/imagen-4.0-generate-001 | High-fidelity photorealism |
black-forest-labs/flux-kontext-pro | Fast, artistic styles |