Menü
Generate images using FAL.ai FLUX API. Requires FAL_KEY environment variable.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
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 $0 local tier, no API keys needed.
| name | fal-image |
| description | Generate images using FAL.ai FLUX API. Requires FAL_KEY environment variable. |
Generate an image via FAL.ai FLUX API.
PLUGIN_ROOT=$(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 not found" && exit 1; fi
Parse $ARGUMENTS for:
output/fal-YYYYMMDD-HHMMSS.png)1920x1080 or 2048x2048). Translated to FAL image_size={"width":W, "height":H}. If both --size and --resolution are passed, --size wins and a warning is logged. If omitted, --resolution selects a sensible preset.fal-ai/flux-2-pro). Other options: fal-ai/flux-2-klein, fal-ai/ideogram/v3.1K, 2K). Default: 1K. FLUX 2 Pro supports both; Klein and Ideogram support 1K only. Unsupported model/resolution combinations raise ProviderResolutionUnsupportedError; the exception message lists supported tiers.PYTHONPATH="$PLUGIN_ROOT" python3 -c "
import os
configured = bool(os.environ.get('FAL_KEY'))
print('available' if configured else 'not_configured')
"
If not_configured, tell the user to set FAL_KEY and stop.
PYTHONPATH="$PLUGIN_ROOT" python3 -c "
import json
from src.generate_cloud_image import generate_cloud_image
kwargs = dict(
prompt='$PROMPT',
provider='fal',
output_path='$OUTPUT_PATH',
model='$MODEL',
resolution='$RESOLUTION',
)
# --size 1920x1080 translates to image_size dict (FAL's native parameter form).
size = '$SIZE'
if size and 'x' in size:
w, h = size.split('x')
kwargs['image_size'] = {'width': int(w), 'height': int(h)}
result = generate_cloud_image(**kwargs)
print(json.dumps(result, indent=2))
"
If successful, report the file path and cost. If failed, report the error.
| Model | 1K (1MP) | 2K (~4.2MP) | Notes |
|---|---|---|---|
| fal-ai/flux-2-pro | $0.030 | $0.078 | tiered: $0.030 first MP + $0.015/extra MP (2048² is ~4.19 MP) |
| fal-ai/flux-2-klein | $0.014 | n/a | flat |
| fal-ai/ideogram/v3 | $0.060 | n/a | flat |