A collection of two Agent Skills (Signal Geometry and Chalk Logic) that convert abstract concepts into stylized, wordless illustrations with precise visual constraints.

Stars

79

7-day growth

No data

Forks

2

Open issues

0

License

MIT

Last updated

2026-07-24

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides ready-to-use, prompt-controlled artistic styles for AI agents, enabling consistent, high-fidelity visuals without manual tuning, and is openly licensed under MIT.

Who it is for

  • AI agent developers integrating image generation skills
  • Designers and artists seeking structured generative prompts
  • Tech educators or communicators visualizing abstract ideas
  • Users of the skills.sh platform looking for reusable agent tools

Use cases

  • Generate a sparse geometric poster from a scientific concept
  • Create a quiet chalkboard illustration explaining a natural process
  • Use prompt-only mode to plan visual recipes without generating images
  • Integrate into workflows that require consistent visual style across outputs

Strengths

  • Clear, repeatable visual constraints (geometry, chalk) ensure style consistency
  • Dual modes (rendered and prompt-only) offer flexibility for limited capabilities
  • Simple installation via npx or pnpm and invocation by name
  • MIT license permits modification and redistribution

Considerations

  • Rendered mode requires external image generation and inspection tools
  • Only two specific visual styles are provided, limiting variety
  • Skills must be explicitly invoked by name; no automatic style detection

README quick start

Skills

A collection of Agent Skills by Cali Castle. Currently includes Signal Geometry and Chalk Logic.

Signal Geometry

Signal Geometry is an Agent Skill for turning one concept into a sparse abstract illustration or poster. It uses precise geometry, quiet matte fields, restrained contrast, and one legible spatial event.

Install

Using npm:

npx skills add CaliCastle/skills --skill signal-geometry

Using pnpm:

pnpm dlx skills add CaliCastle/skills --skill signal-geometry

Use

Invoke the skill explicitly with $signal-geometry:

Use $signal-geometry to create a dark 4:5 poster about a weak signal becoming stable through repeated filtering. No text.

For a prompt without rendering:

Use $signal-geometry in prompt-only mode for an ultrawide illustration about two systems finding equilibrium.

Output

Rendered work includes the accepted image, its exact final prompt, and the complete composition recipe. Prompt-only mode returns the prompt and recipe without generating an image.

Requirements

  • Prompt-only mode works without image tools.
  • Rendered mode requires image generation and image inspection capabilities.
  • The Codex integration is explicit-only by design, so invoke $signal-geometry by name.

License

Signal Geometry and its reference images are released under the MIT License.

Chalk Logic

Chalk Logic is an Agent Skill for turning one concept into a quiet, wordless white-chalk illustration on a desaturated green board. It supports explanatory systems, natural processes, observed objects, and sparse editorial scenes without drifting into classroom clutter or polished digital graphics.

Install

Using pnpm:

pnpm dlx skills add CaliCastle/skills --skill chalk-logic

Using npm:

npx skills add CaliCastle/skills --skill chalk-logic

Use

Invoke the skill with $chalk-logic:

Use $chalk-logic to create a quiet 16:9 wordless illustration about a heavy thought becoming easier to carry.

For a prompt without rendering:

Use $chalk-logic in prompt-only mode for a portrait illustration explaining how a key opens a lock. No labels.

Output

Rendered work includes the inspected image, its exact prompt sequence, the complete composition recipe, and QA

Description

A collection of Agent Skills by Cali Castle.

Related repositories

Similar projects matched by category, topics, and programming language.

op7418
op7418 GitHub avatar

guizang-material-illustration

A skill for AI agents like Claude Code and Codex to generate explanatory illustrations with Chinese labels in the 'Guizang' material style, making abstract concepts, charts, and reference-based content into clear center visuals.

Empty
835
HezaoHezao
Featured
HezaoHezao GitHub avatar

poirot

Poirot is a deep research agent kernel with a middleware-first architecture, five-layer long-term memory, multi-agent orchestration, sandbox isolation, and a three-layer skill self-evolution system, backed by 2400+ tests.

AI & Machine LearningLarge Language Models
25
AgriciDaniel
Featured
AgriciDaniel GitHub avatar

anti-slop

Anti-slop is a tool for detecting and repairing substance defects in AI-assisted prose, code, documentation, and agent output using deterministic scanners and structural procedures that produce verifiable artifacts rather than authorship judgments.

AI & Machine LearningLarge Language Models
9