gooseworks-ai/goose-skills / skills/video/create-image-fal
create-image-fal
VerifiedGenerate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), routed through the GooseWorks proxy, so the call is charged to your GooseWorks credits. image_urls must be public URLs; --image puts a local file on the fal CDN first. The recipe names the model + prompt. Use for keyframes, flat-cover transforms, product hero edits. (For the OpenAI gpt-image family specifically, create-image-gpt-image-fal also exists.)
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.0 KB |
| references/avatar-generation.md | markdown | 9.0 KB |
| scripts/brand_pack_lint.py | script | 4.4 KB |
| scripts/gen_image.py | script | 6.6 KB |
| scripts/image_quality.py | script | 1.5 KB |
| scripts/media_proxy.py | script | 56.8 KB |
| skill.meta.json | config | 177 B |
| tests/smoke-test.md | markdown | 280 B |
| tests/test_brand_pack_lint.py | script | 4.8 KB |
| tests/test_image_quality.py | script | 1.2 KB |
tests/test_brand_pack_lint.py
View on GitHub"""1.3.0: a brand-pack prompt that asks for an unprinted, blank, unlabeled or back-facing pack is
refused, and a pack held on screen needs GPT Image 2 edit with the real photo as image 1. Free:
every refusal stops before any upload or paid call."""
from pathlib import Path
import subprocess
import sys
import unittest
SCRIPTS = Path(__file__).resolve().parents[1] / "scripts"
sys.path.insert(0, str(SCRIPTS))
from brand_pack_lint import FRONT, HELD_MODEL, blank_words, lint_brand_pack, with_front_line # noqa: E402
# The 15 Oct test video's own prompts.
SACHET = ("The left hand holds an already-open cream-colored food pouch with its unprinted back facing the "
"camera, ready to put it into a small empty waste bowl. No printed words.")
POUR = "The unprinted back of the pouch faces the camera. A small amount of dry dark lentil pieces is visible."
GOOD = "She tips the open pouch of dal into the pot of boiling water; steam rises, her eyes on the pot."
class BlankWordsTests(unittest.TestCase):
def test_the_test_videos_prompts_are_caught(self):
self.assertEqual({label for label, _ in blank_words(SACHET)}, {"unprinted", "no printed words", "back facing the camera"})
self.assertIn("unprinted", {label for label, _ in blank_words(POUR)})
def test_each_word(self):
for text, label in [("an unlabeled box", "unlabeled"), ("an unlabelled jar", "unlabeled"),
("a blank white pouch", "blank"), ("the pack is blank", "blank"),
("no printed words on the box", "no printed words"), ("a bottle without a label", "no printed words"),
("the back of the pack faces the camera", "back facing the camera")]:
self.assertIn(label, {l for l, _ in blank_words(text)}, text)
def test_ordinary_words_pass(self):
for text in (GOOD, "a blank wall behind her", "the pack front faces the camera",
"no text overlays or captions", "she types on a blank screen"):
self.assertEqual(blank_words(text), [], text)
class LintTests(unittest.TestCase):
def test_static_refuses_blank_words_only(self):
self.assertEqual(lint_brand_pack(GOOD, "static", "fal-ai/nano-banana/edit", []), [])
self.assertTrue(lint_brand_pack(SACHET, "static", HELD_MODEL, []))
def test_held_needs_gpt_image_2_edit_and_the_real_photo_first(self):
self.assertEqual(lint_brand_pack(GOOD, "held", HELD_MODEL, None, "pack.jpg"), [])
self.assertEqual(lint_brand_pack(GOOD, "held", HELD_MODEL, ["pack.jpg", "presenter.png"], "pack.jpg"), [])
wrong_model = lint_brand_pack(GOOD, "held", "fal-ai/nano-banana/edit", None, "pack.jpg")
self.assertTrue(any("openai/gpt-image-2/edit" in p for p in wrong_model))
no_photo = lint_brand_pack(GOOD, "held", HELD_MODEL, ["presenter.png"])
self.assertTrue(any("--product-image" in p for p in no_photo))
second = lint_brand_pack(GOOD, "held", HELD_MODEL, ["presenter.png", "pack.jpg"], "pack.jpg")
self.assertTrue(any("must be image 1" in p for p in second))
def test_the_front_line_is_added_once(self):
once = with_front_line(GOOD)
self.assertTrue(once.endswith(FRONT))
self.assertEqual(with_front_line(once), once)
class GenImageRefusalTests(unittest.TestCase):
"""gen_image.py refuses before resolve_images (no upload) and before fal_generate (no paid call)."""
def run_gen(self, *args):
return subprocess.run([sys.executable, str(SCRIPTS / "gen_image.py"), *args, "--out", "/nonexistent/x.png"],
capture_output=True, text=True, env={"PATH": "/usr/bin:/bin", "HOME": "/nonexistent"})
def test_a_blank_pack_prompt_is_refused_with_nothing_sent(self):
import json
r = self.run_gen("--model", HELD_MODEL, "--brand-product", "held", "--product-image", "/nonexistent/pack.jpg",
"--payload", json.dumps({"prompt": SACHET}))
self.assertNotEqual(r.returncode, 0)
self.assertIn("refused, nothing sent", r.stderr)
self.assertIn("unprinted", r.stderr)
def test_held_without_the_photo_or_on_another_model_is_refused(self):
import json
r = self.run_gen("--model", HELD_MODEL, "--brand-product", "held", "--payload", json.dumps({"prompt": GOOD}))
self.assertIn("--product-image", r.stderr)
r = self.run_gen("--model", "fal-ai/nano-banana/edit", "--brand-product", "held", "--product-image", "x.jpg",
"--payload", json.dumps({"prompt": GOOD}))
self.assertIn("openai/gpt-image-2/edit", r.stderr)
r = self.run_gen("--model", HELD_MODEL, "--product-image", "x.jpg", "--payload", json.dumps({"prompt": GOOD}))
self.assertIn("--product-image goes with --brand-product held", r.stderr)
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |