Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cxcscmu/SkillLearnBench --skill image-generation-pillowgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cxcscmu/skilllearnbench/image-generation-pillow)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/image-generation-pillow"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/image-generation-pillow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00643 |
| Opus 5 | $0.00015 | $0.00321 |
| Sonnet 5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
image-generation-pillow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Pillow (PIL) is a robust library for image processing and creation in Python. It's ideal for generating technical diagrams, exploded views, and annotated posters.
Installation
Ensure Pillow is installed in your environment:
pip install Pillow
Usage Patterns
Basic Canvas Setup
from PIL import Image, ImageDraw, ImageFont
# Create a blank canvas
width, height = 1200, 1600
background_color = (250, 249, 245) # Anthropic Identity Light
image = Image.new('RGB', (width, height), background_color)
draw = ImageDraw.Draw(image)
Drawing Technical Shapes
Use draw.polygon, draw.rectangle, and draw.line to create exploded views. Parallelograms can represent layered hardware components.
def draw_hardware_layer(draw, top_left, size, color, offset=20):
# top_left: (x, y)
# size: (w, h)
# color: (r, g, b)
# Draw a 3D-like box
x, y = top_left
w, h = size
# Base rectangle
draw.rectangle([x, y, x + w, y + h], fill=color, outline=(20, 20, 19), width=2)
Exploded View Strategy
To create an exploded view, stack layers vertically with a consistent Y-offset and use leader lines for annotations.
layers = [
{"name": "Casing", "color": (20, 20, 19)},
{"name": "Thermal Unit", "color": (106, 155, 204)},
{"name": "PCB", "color": (120, 140, 93)},
{"name": "Battery", "color": (176, 174, 165)},
{"name": "Interface", "color": (217, 119, 87)}
]
for i, layer in enumerate(layers):
draw_hardware_layer(draw, (300, 200 + i * 200), (600, 100), layer['color'])
Annotations and Typography
# Load a font (ensure the font file exists or use a default)
try:
font_heading = ImageFont.truetype("Poppins-Bold.ttf", 48)
except:
font_heading = ImageFont.load_default()
draw.text((50, 50), "NOVA", fill=(20, 20, 19), font=font_heading)
Best Practices
- Use high DPI (e.g., 300) for print-quality posters (multiply width/height accordingly).
- Use
ImageDraw.linewith specific widths for leader lines. - Antialias lines by drawing at 2x size and resizing down.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 74 lines · 31 tokens per session scan A 320dbeb51736
image-generation-pillow is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 643 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Ferramenta Python de Divisão de Áudio com GUI e FFmpeg Local
Cria um script Python completo com interface gráfica (Tkinter) para dividir arquivos de áudio em segmentos, utilizando um executável FFmpeg localizado na mesma pasta do script.
manimgl-best-practices
Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains from manimlib import , (3) User runs manimgl CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown…
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
pcap-analysis
Guidance for analyzing network packet captures (PCAP files) and computing network statistics using Python, with tested utility functions.
composing-with-pytheory
Compose music with PyTheory — chord progressions, melodies, basslines, drum grooves, and full multi-part arrangements written in pure Python and rendered to audio or MIDI. Use whenever the user wants to write, sketch, generate, or arrange music — "write me a bossa nova in G minor", "make a four-chord pop loop", "lay…