ワンクリックで
openai-image
Generate images using OpenAI GPT Image API. Requires OPENAI_API_KEY environment variable.
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。
メニュー
Generate images using OpenAI GPT Image API. Requires OPENAI_API_KEY environment variable.
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。
SOC 職業分類に基づく
Produce a labeled figure with PERFECT text — render a label-free image locally (or take an external image) then overlay leader lines and typeset labels programmatically from vision-derived anchor coordinates. Text is correct by construction; only pointer placement is reviewed.
Ask which image models fit a set of tasks — get evidence-based recommendations with per-image costs, which external services to pay for, and which local models to install (with disk/RAM/licence guidance). Reads the live model catalog and probes what is actually available on this machine.
Check mflux (MLX) availability, per-family runtime presence, cached weights, and report readiness status.
Top-level image orchestrator. Routes all slide image generation to the appropriate skill (jack-tar-ollama:image, jack-tar-ollama:icon, jack-tar-ollama:pattern, jack-tar-ollama:diagram, jack-tar-cloud:image, jack-tar-cloud:icon, render_chart). Produces ImageManifest and ChartManifest. Also reads strategy-map.json to determine per-slide rendering approach (full_render, backdrop_render, composed).
Meta-verify — discover all jack-tar engine plugins, call each verify, report aggregate pipeline capability and discipline-hook readiness.
Generate an image locally on Apple Silicon via the mflux CLI (MLX). Flag-compatible with jack-tar-ollama's /image — a $0 local tier, no API keys needed.
| name | openai-image |
| description | Generate images using OpenAI GPT Image API. Requires OPENAI_API_KEY environment variable. |
Generate an image via OpenAI GPT Image API and report the file path with cost.
This skill wraps src/generate_cloud_image.py. It does NOT call APIs directly -- it delegates to the Python module which handles authentication, API calls, and file saving.
PLUGIN_ROOT=$(python3 -c "
from pathlib import Path
import sys, os
if os.environ.get('JACK_TAR_CLOUD_ROOT'):
print(os.environ['JACK_TAR_CLOUD_ROOT']); sys.exit()
home = Path.home()
for base in [home / '.claude' / 'plugins' / 'cache']:
for p in base.rglob('jack-tar-cloud/.claude-plugin/plugin.json'):
print(str(p.parent.parent)); sys.exit()
dev = Path.cwd() / 'plugins' / 'jack-tar-cloud'
if dev.exists():
print(str(dev)); sys.exit()
print('NOT_FOUND')
" 2>/dev/null)
if [ -z "$PLUGIN_ROOT" ] || [ "$PLUGIN_ROOT" = "NOT_FOUND" ]; then
echo "ERROR: jack-tar-cloud plugin not found."
exit 1
fi
Parse $ARGUMENTS for:
output/openai-YYYYMMDD-HHMMSS.png)1536x1024 (landscape). Options: 1024x1024, 1536x1024, 1024x1536low, medium, high). Default: mediumauto, transparent). Default: autogpt-image-1.5)1K, 2K, 4K). Default: 1K. Note: gpt-image-1.5 supports 1K only; passing 2K/4K raises ProviderResolutionUnsupportedError with a recommendation to switch provider.If no prompt is provided, stop and tell the user to provide a prompt.
Before generating, verify the provider is configured:
PYTHONPATH="$PLUGIN_ROOT" python3 -c "
from src.provider_discovery import discover_providers
providers = discover_providers()
p = providers.get('openai', {})
print('available' if p.get('available') else 'not_configured')
"
If not_configured, tell the user to set OPENAI_API_KEY and stop.
PYTHONPATH="$PLUGIN_ROOT" python3 -c "
import json
from src.generate_cloud_image import generate_cloud_image
result = generate_cloud_image(
prompt='''$PROMPT''',
provider='openai',
output_path='$OUTPUT',
size='$SIZE',
quality='$QUALITY',
background='$BACKGROUND',
model='$MODEL',
resolution='$RESOLUTION',
)
print(json.dumps(result, indent=2))
"
Report to the user:
If the generation fails, show the error message. For ProviderNotConfiguredError, include the setup documentation reference.
| Provider | Model | Quality | Size | Resolution tier | Cost |
|---|---|---|---|---|---|
| OpenAI | gpt-image-1.5 | low | 1024x1024 | 1K | $0.009 |
| OpenAI | gpt-image-1.5 | medium | 1024x1024 | 1K | $0.034 |
| OpenAI | gpt-image-1.5 | medium | 1536x1024 | 1K | $0.051 |
| OpenAI | gpt-image-1.5 | high | 1024x1024 | 1K | $0.133 |
| OpenAI | gpt-image-1.5 | high | 1536x1024 | 1K | $0.200 |
OpenAI does not support 2K or 4K resolution tiers; route to Google Nano Banana for those.
Configured providers are detected at runtime via src/provider_discovery.py. Run /jack-tar-cloud:verify for the current state of all configured providers.