메뉴
Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2. Trigger on "generate image", "create diagram", "edit image", or "make illustration". Supports 1K/2K/4K resolution, masked inpainting, and text-accurate generation.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | image-gen |
| description | Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2. Trigger on "generate image", "create diagram", "edit image", or "make illustration". Supports 1K/2K/4K resolution, masked inpainting, and text-accurate generation. |
Multi-provider image generation. Default provider is Gemini (nano-banana-pro); pass --provider openai to use gpt-image-2.
The skill ships a pre-bundled Node script — no tsx or dependency install required on the user side. Invoke with node. Run node ${CLAUDE_PLUGIN_ROOT}/skills/image-gen/dist/generate_image.js --help at any time for the full flag reference printed by the script itself.
Generate:
node ${CLAUDE_PLUGIN_ROOT}/skills/image-gen/dist/generate_image.js \
--prompt "your description" --filename "output.png" \
[--provider gemini|openai] [--resolution 1K|2K|4K] [--size WxH] [--quality low|medium|high|auto] [--api-key KEY]
Edit (image-to-image):
node ${CLAUDE_PLUGIN_ROOT}/skills/image-gen/dist/generate_image.js
--prompt "editing instructions" --filename "output.png"
--input-image "path/to/input.png" [--mask "path/to/mask.png"]
## Flag reference
| Flag | Values | Notes |
|------|--------|-------|
| `--prompt` | text | Required. |
| `--filename` | path | Required. Output PNG. |
| `--provider` | `gemini` \| `openai` | Default: `gemini` (or `openai` if only `OPENAI_API_KEY` is set). |
| `--resolution` | `1K` \| `2K` \| `4K` | Default `1K`. `4K` clamps to `3840x2160` on OpenAI. |
| `--size` | `WxH` | OpenAI only. Overrides `--resolution`. Max edge 3840, multiples of 16. |
| `--quality` | `low` \| `medium` \| `high` \| `auto` | OpenAI only. Default `auto`. Ignored on Gemini. |
| `--input-image` | path | Switches to edit mode. Repeatable on Gemini for multi-image composition; OpenAI accepts only one. |
| `--mask` | path | OpenAI only. Inpainting mask. Requires `--input-image`. |
| `--api-key` | key | Overrides env for selected provider. |
| `-h`, `--help` | — | Print CLI help and exit. |
## Resolution
- `1K` (default) — 1024px
- `2K` — 2048px
- `4K` — 4096px on Gemini; silently clamped to `3840x2160` on OpenAI (OpenAI's hard cap is 3840).
- `--size WxH` (OpenAI only) overrides `--resolution`. Max edge 3840, both edges must be multiples of 16.
## Quality (OpenAI only)
`low | medium | high | auto` (default `auto`). Ignored on Gemini with a warning.
## Masks (OpenAI only)
`--mask <path>` enables inpainting. Requires `--input-image`. Error if used with Gemini.
## API keys
Resolution order:
1. `--api-key` flag (applied to selected provider)
2. Provider-specific env:
- Gemini: `GEMINI_API_KEY` or `GOOGLE_API_KEY`
- OpenAI: `OPENAI_API_KEY`
## Filename convention
YYYY-MM-DD-HH-MM-SS-descriptive-name.png
Use OpenAI at 2K for anything with readable labels or callouts. Save to the appropriate content dir (e.g., src/content/blog/post-name/). Prefer clean, minimalist styles.
Use when the user is weighing or pressure-testing an idea rather than committing to build it — 'should I do X', 'which of these approaches', 'is this worth doing', 'what am I missing', 'am I overthinking or over-engineering this'. A lightweight thinking partner that surfaces hidden assumptions and argues for the simplest version, in conversation — no files, no spec. Once the idea is settled and the user wants it turned into an actual plan or spec, that's planning work — hand off to the ideation skill if it's available. Not for writing code to a known spec, bug fixes, or refactors.
Read and drive other tmux panes when Claude runs inside tmux. Use whenever the user points at something running in another pane/split/window — their dev server, test watcher, build, logs, REPL, or another shell — e.g. "errors in my dev server", "read/tail my other pane", "is my server up and on what port", "run this in my other split", "restart the watcher". Also for driving interactive/long-running CLIs (Node REPL, vite/next dev, vitest, node inspect) and spawning isolated background tmux sessions.
Socratic tutor that drills the user until they deeply understand a change — the problem, the solution, the design decisions, the edge cases, and what it impacts. Use after completing or reviewing work (a diff, PR, or session) when the user wants to truly own it, not just skim it — or when the user says /socratic-tutor, "teach me what we just did", "quiz me on this", "walk me through this change", or "make sure I understand this". Restates-first, quizzes, and does not stop until the user demonstrates mastery.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. User-invocable only — does not auto-trigger. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Phased maintainability migration that transforms messy, overgrown, or slop-prone repos into product-shaped codebases while preserving behavior. Covers file splitting, typed boundaries, test hardening, feature folders, API consolidation, and a final migration audit microsite. Use when the user asks to "rehab this codebase", "run a maintainability migration", "modernize structure", "clean up this messy repo and make it maintainable", or "productionize this prototype". Unlike codebase-sweep (parallel quick audit), this is a deep, staged refactor with migration planning and checkpoint commits. Do not use for security audits, observability, compliance, or SRE work.
Comprehensive, codebase-wide quality sweep that dispatches parallel subagents to find and fix structural issues. Covers deduplication, type consolidation, dead code removal, circular dependencies, weak types, defensive try/catch, deprecated paths, and AI slop. Primary support for JS/TS projects (knip, madge, TypeScript types); other languages get grep-based analysis. Use when the user asks to "deep clean the whole repo", "run a full codebase audit", "nuclear cleanup", "deslop everything", or "sweep the entire codebase for quality issues". Do NOT use for single-file fixes, branch-scoped diffs (use de-slopify instead), or targeted refactors.