python-pillow-graphics

A Python-based tool for creating images such as diagrams, posters, and technical graphics. It uses Pillow, a Python library for making and editing images, with control over colors, shapes, and text.

In plain words
What is it for?
Use it to generate diagrams, posters, and other technical visuals with Python. It supports drawing rectangles, circles, lines, polygons, and text onto images.
Why use it?
It helps when you need repeatable, precisely sized graphics without drawing them by hand. You can set exact colors, lines, shapes, and typography in code.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cxcscmu/skilllearnbench/python-pillow-graphics
Any agent
npx skills add cxcscmu/SkillLearnBench --skill python-pillow-graphics
Clone the repo
git clone --depth 1 https://github.com/cxcscmu/SkillLearnBench

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00831
Opus 5 $0.00013 $0.00415
Sonnet 5 $0.00005 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 2d ago against content hash 900048eeae2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-pillow-graphics 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 2d 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.

skills/b1-one-shot-claude-haiku-4-5/anthropic-poster-design/python-pillow-graphics/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Pillow Graphics Generation

Overview

Pillow (PIL) is the standard Python library for image manipulation and creation. It's ideal for generating technical diagrams, posters, and graphics with precise control over colors, shapes, and text.

Installation

pip install Pillow

Key Concepts

Image Creation

from PIL import Image, ImageDraw, ImageFont

# Create a new image with specific background color
width, height = 1920, 1200
background_color = (240, 240, 240)  # RGB tuple
image = Image.new('RGB', (width, height), background_color)
draw = ImageDraw.Draw(image)

Color Management

  • RGB Tuples: (R, G, B) where each value is 0-255
  • Hex to RGB Conversion:
    def hex_to_rgb(hex_color):
        hex_color = hex_color.lstrip('#')
        return tuple(int(hex_color[i:i+2], 16) for i in (0, 2, 4))
    

Drawing Shapes

# Rectangles
draw.rectangle([x1, y1, x2, y2], fill=color, outline=color, width=stroke)

# Circles/Ellipses
draw.ellipse([x1, y1, x2, y2], fill=color, outline=color)

# Lines
draw.line([(x1, y1), (x2, y2)], fill=color, width=stroke_width)

# Polygons (for 3D perspective)
draw.polygon([(x1, y1), (x2, y2), (x3, y3)], fill=color, outline=color)

Typography

# Load system fonts or TTF files
try:
    font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", size=48)
except:
    font = ImageFont.load_default()

# Draw text
draw.text((x, y), "TEXT", fill=color, font=font, anchor="lm")  # anchor: "lm"=left-middle

Best Practices

  • Use anchor parameter for precise text positioning
  • Work with RGB tuples consistently throughout
  • Set image DPI metadata for high-quality output
  • Use layers approach: background → shapes → text → details
  • Save as PNG for transparency or high-quality technical graphics

Saving Output

image.save('/path/to/image.png', quality=95, dpi=(300, 300))

Advanced Techniques

Creating 3D Perspective

Use polygons and shading to create depth:

# Front face (lighter)
draw.polygon([(x1, y1), (x2, y2), (x3, y3), (x4, y4)], fill=light_color)
# Side face (darker for depth)
draw.polygon([(x2, y2), (x3, y3), (x5, y5), (x6, y6)], fill=dark_color)

Read the full file on GitHub · 104 lines

Changes

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.

  1. 2d ago First seen · 104 lines · 25 tokens per session scan A 900048eeae2d

Subscribe to this mod's changes

python-pillow-graphics is a skill published in the GitHub repository cxcscmu/SkillLearnBench (82 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 831 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

creating-skills

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.

letta-ai/letta-code · 47 tokens

Context Doctor

Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.

letta-ai/letta-code · 30 tokens

image-generation

Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.

letta-ai/letta-code · 47 tokens

adding-models

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.

letta-ai/letta-code · 58 tokens

hotpath_init

Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…

pawurb/hotpath-rs · 88 tokens

writing-bench-task-judge

Use when writing or modifying checkgoals() / getanswer() / App check methods in benchenv/task/, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.

Purewhiter/mobilegym · 68 tokens