菜单
Generate images from prompts using AI APIs (OpenAI GPT Image, Google Gemini/Nano Banana, Google Imagen, fal.ai Flux). Use when the user asks to generate, create, make, render, or produce an image, icon, visual asset, illustration, mockup, texture, poster, or other raster image file.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Markdown task backlog and project roadmap (backlog/{todo,doing,done,failed}/, backlog/ROADMAP.md) for adding, advancing, recording progress, rescuing, cancelling, retrying, failing, maintenance, or reflecting on backlog priorities and roadmap direction.
Write, review, or improve SwiftUI code. Use for SwiftUI features/refactors, state management, view composition, performance, concurrency, modern Apple APIs, or native UI quality.
Work with Claude Code configuration at global (~/.claude) or project (.claude/) level. Use when editing settings.json (permissions, hooks, statusline, model), managing MCP servers, creating agents/commands/skills, writing CLAUDE.md, setting up rules files, or configuring a new project. Determines context automatically and provides guidance on global vs project placement to avoid duplication.
Session continuity for coding work. Default to /chronicle to capture, /chronicle catchup to resume, and /chronicle pending to review open threads. Use curate, recap, wrapup, summarize, publish, insights, search, and ui only when the user explicitly needs them.
Analyze AI coding assistant usage patterns across Claude Code, Codex, and Cursor. Use when user asks about their coding usage, tool statistics, productivity patterns, skill popularity, session history, or wants to query their AI coding logs. Triggers include "usage", "how much have I used", "most used tools", "skill popularity", "coding stats", "productivity patterns".
Fix misaligned right borders in ASCII art diagrams
| name | image-gen |
| description | Generate images from prompts using AI APIs (OpenAI GPT Image, Google Gemini/Nano Banana, Google Imagen, fal.ai Flux). Use when the user asks to generate, create, make, render, or produce an image, icon, visual asset, illustration, mockup, texture, poster, or other raster image file. |
| license | Apache-2.0 |
Generate raster images by running the bundled provider scripts. Do not stop at a prompt description when the user asked for an image file.
After generation, return the absolute output path and, when the client supports it, render the image with Markdown:
| Use case | Provider/script | Notes |
|---|---|---|
| General prompt-to-image default | generate_openai.py | Defaults to gpt-image-2; strong output controls. |
| Gemini/Nano Banana output | generate_gemini.py | Defaults to Nano Banana 2 (gemini-3.1-flash-image-preview). |
| Complex Gemini or text-heavy visual work | generate_gemini.py --model gemini-3-pro-image-preview | Nano Banana Pro; supports 1K/2K/4K size controls. |
| Specific Imagen requirement | generate_imagen.py | Imagen 4 GA models are listed by Google with a 2026-06-30 discontinuation date; prefer Gemini for new work unless Imagen is requested. |
| Flux or fal model ecosystem | generate_fal.py | Defaults to fal-ai/flux-2-pro; supports fal size presets, seed, output format, and optional model-specific controls. |
For the current comparison model matrix, read references/current-models.md. For model/API refreshes and long-term data handling, read references/maintenance-workflow.md. For the implemented design and provider protocol approach, read references/provider-protocol-architecture.html. For why generated outputs and local history live in ignored skill-local directories, read references/storage-policy.md.
The Python entrypoints are executable UV scripts. Prefer direct execution:
~/.claude/skills/image-gen/scripts/<script>.py \
--prompt "a cat wearing a top hat" \
--output /tmp/cat.png
uv run --script ~/.claude/skills/image-gen/scripts/<script>.py ... remains a valid fallback if a copied checkout has lost executable bits.
Provider scripts are image generation adapters. Keep their interface stable: executable UV script, --prompt, --output, --output-dir, --model, --check, --protocol, successful generation history, and resolved output path as the final stdout line.
scripts/common.py is the only shared local helper.
Common examples:
# Default OpenAI path
~/.claude/skills/image-gen/scripts/generate_openai.py \
--prompt "a cat wearing a top hat" \
--output /tmp/cat.png
# Gemini Pro / Nano Banana Pro
~/.claude/skills/image-gen/scripts/generate_gemini.py \
--model gemini-3-pro-image-preview \
--prompt "a typography-forward launch poster for a boutique coffee app" \
--output /tmp/poster.png \
--aspect-ratio 16:9 \
--image-size 2K
# fal with repeatability
~/.claude/skills/image-gen/scripts/generate_fal.py \
--prompt "isometric game asset of a glass greenhouse" \
--output /tmp/greenhouse.jpg \
--seed 1234
Use each script's --help as the full option reference:
~/.claude/skills/image-gen/scripts/generate_openai.py --help
Use run_examples.py to compare current model presets. It dry-runs by default and only makes paid API calls with --generate.
~/.claude/skills/image-gen/scripts/run_examples.py --list
~/.claude/skills/image-gen/scripts/run_examples.py
~/.claude/skills/image-gen/scripts/run_examples.py --generate --example typography-poster
Single-example generated manifests are reviewable directly with review_gallery.py.
Use review_gallery.py for local winner selection, image-order ranking, an optional comment, and one/all candidate regeneration:
~/.claude/skills/image-gen/scripts/review_gallery.py --run-dir <comparison-run-dir>
Click-to-rank assigns rank 1 to the first distinct image clicked, rank 2 to the second, rank 3 to the third, then leaves remaining unclicked images in current order. Clicking an already-ranked image or clicking after a completed pass starts a fresh ranking pass from rank 1.
The review page opens image-only. Tap or click outside the image cards and controls to toggle prompt, actions, status, and comment; press Esc to hide them. R reveals or hides only provider/model details, even while the rest of the chrome stays hidden.
After changing the review UI or generating comparison outputs, run the visual evaluator and inspect its screenshots/checks before reporting:
~/.claude/skills/image-gen/scripts/evaluate_review_gallery.py --run-dir <comparison-run-dir>
It captures default, interaction, and mobile screenshots under outputs/evaluations/ and checks that the default view is image-only, images load, metadata does not overlap the image, click-to-rank works, keyboard ranking works, R toggles details, and S saves with a visual indicator. With --run-dir, it serves a temporary copy so validation does not mutate the original comparison run.
--prompt: Required prompt.--output, -o: Output path. Parent directories are created automatically.--output-dir: Default directory when --output is omitted.--model: Override the default provider model.--aspect-ratio, -a: Gemini and Imagen aspect ratio.--size or --image-size, -s: Provider-specific output size control.--output-format, -f: Use when the file suffix should not determine PNG/JPEG/WebP.--check: Validate provider configuration without generating an image.--protocol: Print provider adapter protocol JSON without API keys.| Provider | Env var | Key URL |
|---|---|---|
| OpenAI | OPENAI_API_KEY | https://platform.openai.com/api-keys |
GOOGLE_API_KEY or GEMINI_API_KEY | https://aistudio.google.com/apikey | |
| fal.ai | FAL_KEY | https://fal.ai/dashboard/keys |
Scripts read exported variables first, then simple KEY=value lines from .env in the current directory and ~/.env.
If --output is omitted, scripts save under skills/image-gen/outputs/ by default. Override that with IMAGE_GEN_OUTPUT_DIR or --output-dir. The outputs directory is intentionally gitignored except for its README.
Successful generations are also logged to skills/image-gen/data/generations.jsonl by default. Set IMAGE_GEN_DISABLE_HISTORY=1 for sensitive prompts, or IMAGE_GEN_DATA_DIR=/path/to/dir to move local history elsewhere.
Check keys without spending generation credits:
~/.claude/skills/image-gen/scripts/generate_openai.py --check
~/.claude/skills/image-gen/scripts/generate_gemini.py --check
~/.claude/skills/image-gen/scripts/generate_imagen.py --check
~/.claude/skills/image-gen/scripts/generate_fal.py --check
Inspect provider protocol metadata without API keys:
~/.claude/skills/image-gen/scripts/generate_openai.py --protocol
~/.claude/skills/image-gen/scripts/check_protocol.py
Generation may incur provider costs. If a key is missing or invalid, fix the env var rather than changing the script.
~/.claude/skills/image-gen/scripts/check_protocol.py
~/.claude/skills/image-gen/tests/test_image_gen.py
~/.claude/skills/image-gen/tests/test_image_gen.py --check-env
~/.claude/skills/image-gen/tests/test_image_gen.py --generate --provider openai
Default testing is free and does not require API keys. check_protocol.py is the focused adapter-contract check and is also run by PR validation when skills/image-gen/ changes. --check-env reports configured keys. --generate makes real API calls and stores outputs in skills/image-gen/outputs/test-runs/.