anbeime/skill / skills/handraw-style/handraw-style
handdraw-style-prompter
FlaggedTurn a 001–368 hand-drawn and realistic style number and image theme into bilingual prompts, using model capability data to decide when core traits and a numbered reference image are required.
build_workbuddy_release.py
View on GitHubimport os, zipfile, sys
from pathlib import Path
sys.stdout.reconfigure(encoding='utf-8')
ROOT = Path(__file__).resolve().parent
skill_dir = ROOT / "skills" / "handdraw-style-prompter"
zip_path = ROOT / "dist" / "handraw-skill-workbuddy-v1.0.3.zip"
# Ensure layouts/ exists under skill_dir
layouts_src = skill_dir / "references" / "layouts"
layouts_dst = skill_dir / "layouts"
if layouts_src.exists() and not layouts_dst.exists():
import shutil
shutil.copytree(layouts_src, layouts_dst)
print(f"Copied {len(list(layouts_dst.glob('*.md')))} layouts to {layouts_dst}")
# Whitelist allowed scripts
allowed_scripts = {
'resolve_reference.py',
'prompt_style.py',
'layout_library.py',
'style_asset_paths.py'
}
with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as z:
for item in skill_dir.rglob("*"):
if not item.is_file():
continue
rel = item.relative_to(skill_dir)
# Exclude pycache and nested subfolders
if "__pycache__" in str(item) or item.suffix in [".pyc", ".pyo"]:
continue
# Allow layouts/*.md (1-level subfolder)
if rel.parts[0] == 'layouts':
if len(rel.parts) == 2 and rel.suffix == '.md':
z.write(item, arcname=rel.as_posix())
continue
# Strictly <= 2 levels
if len(rel.parts) > 2:
continue
# In scripts/, only include allowed scripts
if rel.parts[0] == 'scripts' and rel.name not in allowed_scripts:
print(f"Excluding non-runtime script: {rel}")
continue
z.write(item, arcname=rel.as_posix())
print(f"\nCreated: {zip_path}")
size_kb = zip_path.stat().st_size / 1024
print(f"Size: {size_kb:.2f} KB ({size_kb / 1024:.2f} MB)")
# Verify all zip entries
with zipfile.ZipFile(zip_path, "r") as z:
names = z.namelist()
print(f"Total files in zip: {len(names)}")
max_depth = max(len(Path(n).parts) for n in names)
print(f"Max directory depth in zip: {max_depth}")
assert max_depth <= 2, f"Depth exceeded: {max_depth}"
print("Verification PASSED: Strictly <= 2 levels!")
# Check key files
assert "SKILL.md" in names
assert "layouts/SC-001.md" in names
assert "references/layouts.json" in names
assert "references/styles.json" in names
assert "scripts/prompt_style.py" in names
print("All critical files verified present in zip!")
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: 471k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |