Skip to content
SkillScript-led3,998 tokens in use

Logo Design

Turns the agent into an identity designer: brief, concepts built as clean SVG, tests at 16 px and in one colour, then a logo kit and guidelines once you pick a direction.

7,424 stars on the repository MIT Licensekaankiziltug/logo-design-skill · skills/logo-design
/plugin install logo-design@logo-design-skill
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Logo Design costs

214tokens idle
3,998tokens in use
35,089tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/build_catalog.py, scripts/concept_sheet.py, scripts/export_variants.py, scripts/presentation_board.py, scripts/preview_sheet.py, scripts/render_png.py, scripts/search_library.py, scripts/svg_audit.py, scripts/svglib.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output10/15
  • Size13/15
  • Resources12/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 100
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/build_catalog.py, line 201
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/render_png.py, line 320

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance96
  • Community48
  • Maturity12
  • Momentum40

Logo Design guides an agent through discovery, a design brief, eight to twelve concept sentences, three concepts built as geometric SVG, and repeated testing. It always pauses at a checkpoint where it shows the concepts on one overview image with a recommendation and waits for your choice before building the full kit.

The skill ships a library of more than 1,400 real SVG logos classified by type, technique, geometry and industry, and dependency-free Python scripts that audit SVGs, render PNGs, build test sheets and presentation boards, and export favicon and app-icon sets.

What You Get

  • A concept overview image with true 64, 32 and 16 pixel sizes, one-line ideas and a recommendation
  • Clean SVG masters whose letters are built as paths
  • Black, white, brand-colour, square, favicon and app-icon variants, plus a web icon set and manifest
  • A presentation board with mockups chosen for your industry, exportable as PNG slides
  • A one-page guideline with clear space, minimum sizes, colour codes and misuse examples

Common Use Cases

  • Design a logo for a new company or app from a short description
  • Get a structured critique of an existing logo with a scorecard
  • Refresh an old mark while keeping brand equity
  • Generate favicon, app icon and web manifest files from a symbol
  • Build lockups and basic guidelines for a small brand

What Makes It Unique

The skill stops at a checkpoint before doing the expensive kit work, so you steer cheaply. It also checks its own drawings: an audit script flags near-miss angles, live text, rasters and tiny details, and a preview sheet runs the 16 px, one-colour, squint, mirror and competitor shelf tests. The reference library is for study only, and the skill warns against tracing it.

Under The Hood

The agent reads SKILL.md and reference documents on principles, mark types, colour, typography and testing, and runs bundled Python scripts from the shell. The scripts search the logo catalog, audit SVG files, build HTML test sheets and presentation boards, and render PNG files with whichever renderer is installed, such as cairosvg, Inkscape, macOS Quick Look or headless Chrome, which the agent launches on your machine. The agent writes SVG, PNG, HTML and icon files into your project folder. The scripts need no extra Python packages.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers