claudeers.
// Claude Skills

rob-janoff-design

Agent Skill for logo design with Rob Janoff's method from "Taking a Bite out of the Apple": design, critique and refresh logos as three one-ink SVG concepts…

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up rob-janoff-design (claude-plugin project) into my current project.
Found on https://claudeers.com/rob-janoff-design
Repo: https://github.com/carrapido/rob-janoff-design
Homepage/docs: —
Detected install method: claude-plugin → /plugin install rob-janoff-design@carrapido/rob-janoff-design
Category: skills. Platforms: cli.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or install directly (claude-plugin)

⚠ Unverified / not recently updated — review before pasting a run-this config.

/plugin marketplace add carrapido/rob-janoff-design
/plugin install rob-janoff-design@carrapido/rob-janoff-design
// or clone
git clone https://github.com/carrapido/rob-janoff-design

// compatibility

Platformscli
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguageTypeScript

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

rob-janoff-design

An Agent Skill that makes an AI agent design logos, icons and monograms with Rob Janoff's methodology from Taking a Bite out of the Apple:

  1. Do your homework: business, audience, USP.
  2. Abstract the shape: silhouette, cross-section, scale relation.
  3. Add "a wink and a smile".
  4. Show three one-ink SVG concepts and wait for the client's pick; then test the chosen one in color, solid monochrome, at 256, 48 and 16 px and in context.
  5. Build every curve with ruler and compass from one golden series, and fit the client's hand-drawn edits back onto it.

Install

Paste this prompt into your agent (Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor or any agent that supports Agent Skills):

Install the rob-janoff-design skill from https://github.com/carrapido/rob-janoff-design, refer to the repo's AGENTS.md for instructions.
Install with a CLI instead
AgentCommand
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and 70+ morenpx skills add carrapido/rob-janoff-design
Claude Code (plugin)/plugin marketplace add carrapido/rob-janoff-design, then /plugin install rob-janoff-design@rob-janoff-design
Gemini CLIgemini skills install https://github.com/carrapido/rob-janoff-design.git --path skills/rob-janoff-design

Manual install

Copy skills/rob-janoff-design/ into your agent's skills directory:

AgentPersonalProject
Claude Code~/.claude/skills/.claude/skills/
Codex~/.agents/skills/.agents/skills/
Gemini CLI~/.gemini/skills/.gemini/skills/
GitHub Copilot~/.copilot/skills/.github/skills/
Cursor~/.cursor/skills/.agents/skills/

What changes

Before

Cat logo before the skill: round head, dark face with light eyes and a thin gap around the hair

A personal brand logo for a developer and video editor: a geometric cat that mixes Neco-Arc with the Superintendent from Halo 3: ODST, before running the skill.

After

Cat logo after the skill: light face with dark eyes, hair falling behind the head as a hood and a fang shaped like a 7

The same logo after the skill's critique and the ruler-and-compass fit:

  1. The face turns light, so the fringe is the edge between two tones instead of a thin gap that vanishes below 48 px.
  2. The hair falls behind the head as a hood, built from the same golden series.
  3. The fang becomes a 7, a wink to Bungie.
  4. The gap around the hair widens to D7, so it still shows at 48 px.

Ruler and compass, step by step

Every curve of the After logo is an arc from one golden series, R(n) = 240 / φⁿ, and every distance is a step of it, D(n) = 2·R(n). Nothing is set by eye. The full method is in 04-ruler-and-compass.md.

R−1 388.3 · R0 240 · R1 148.3 · R2 91.7 · R3 56.7 · R4 35 · R5 21.6 · R6 13.4 · R7 8.3

Step 1: the dashed head square and the golden-section eye line over the faded logo
1 · Series and square
The head's square is 2·R0 = 480. Its golden section sets the eye line.
Step 2: the R0 head circle and the dashed face circle inside it
2 · Head and face
The head is R0 and the face R0 − R4. The hair falls behind and the face stands out against it.
Step 3: an R1 and an R−1 circle crossing at each ear tip, with the D5 lines above and below the square
3 · Ears
Each ear is the lens between an R1 circle and an R−1 circle. The tip sits D5 above the square.
Step 4: six R1 circles along the fringe and four large R−1 circles along the locks
4 · Fringe and locks
Six R1 arcs draw the fringe. Four R−1 arcs, tangent to the head, draw the locks.
Step 5: two crossing R3 circles for each eye and the fang's slope drawn as a 7
5 · Eyes and mouth
Each eye is where two R3 circles cross. The fang drops R3 and moves in R4: a φ slope that reads as a 7.
Step 6: R2 circles at the hood's lower corners, the head square and the D5 lines at top and bottom
6 · Hood and frame
R2 corners and a bottom D5 below the square, the same D5 as the ears, so the margins match top and bottom.

From a sketch to three concepts

A second example, starting from a hand-drawn sketch (@marsanwishito): a melancholic girl with a side fringe over one eye and a red heart on her chest, tied by a red thread to a poster. The brief was a T-shirt logo: vectorize her head and hair, imagine how the hair falls behind her head, then design. Each concept pulls a different detail out of the drawing.

The sketch traced in vectors with the pencil's varying width; the heart badge and the thread are red
Reference
The sketch traced in vectors, keeping the pencil's width.
Three details, three concepts
  1. The fringe over one eye becomes the cut of concept A.
  2. The heart on her chest becomes the hair of concept B.
  3. The red thread becomes the single line of concept C.

All three start from the same one-ink head: the hair is the mass and the face is the hole.

Concept A: a solid head built from circular arcs, the fringe cut straight across the face leaving one eye
A · Silhouette and cut
The fringe becomes a straight cut that leaves one eye. Every arc is a Fibonacci radius × 1.5 (89, 55, 13, 8, 3). At 16 px the head and the cut still read.
Concept B: red hair shaped like an upside-down heart, with the face as the hole inside it
B · Negative-space wink
The heart on her chest becomes her hair: an upside-down heart with the face as its hole. Turn it 180° and the heart appears.
Concept C: one black line draws the hair and face and turns into a red thread ending in a heart
C · Graphic continuum
One line runs from the hair to the chin and turns into the red thread, ending in her heart. At 16 px the line breaks up, so an icon needs a simpler cut.

Usage

Ask your agent in plain words. The skill picks one of three modes:

ModeExample requestWhat you get
Design"Design the logo for a specialty coffee shop in Oaxaca"Three one-ink concepts, then the full preview of the one you pick
Critique"Critique our logo: logo.svg"A verdict with evidence (renders, on-screen sizes) against Janoff's golden rules, nothing redrawn
Refresh"Refresh our logo, people already know it: logo.svg"Rebuild, refine and rethink-one-element options beside the original, like the cat above

Evals

evals/ holds one case per mode (design, critique and refresh) for claude plugin eval. Each case runs with and without the skill, and graders score it: the commands the agent ran, the files it did or did not write, and an LLM judge for the message it ends with. The agent writes SVGs and runs Node, so the operator grants those tools:

claude plugin eval . --allow-tools Write Edit Bash "Bash(node *)" "Bash(mkdir *)"

Every run is a full agent session billed to your account; add --runs 1 and --max-cost-usd <usd> to keep a check cheap. Results go to evals/results/, which git ignores.

Repository layout

.
├── .claude-plugin/
│   ├── marketplace.json        # Claude Code plugin marketplace
│   └── plugin.json             # Plugin manifest
├── .github/workflows/test.yml   # CI: npm test and the type check on Linux, macOS and Windows
├── AGENTS.md                   # Install steps the agent follows
├── evals/                      # One claude plugin eval case per mode: design, critique, refresh
├── tests/                      # Tests for the skill's scripts: npm test
└── skills/
    └── rob-janoff-design/
        ├── SKILL.md            # Workflow the agent follows
        ├── references/         # Loaded on demand
        │   ├── 01-apple-process.md
        │   ├── 02-case-studies.md
        │   ├── 03-rules-and-typography.md
        │   └── 04-ruler-and-compass.md   # Golden-series construction, hand-edit fitting, tests
        ├── examples/           # Worked examples, also the README images
        │   ├── cat.md          # Critique and refresh of the cat, step by step with the series
        │   └── sketch-to-concepts.md     # Three different concepts from one sketch
        └── scripts/            # Node 24, no dependencies
            ├── series-audit.ts # Checks that every curve is an arc of the golden series
            ├── series-fit.ts   # Fits the client's hand-drawn edits back onto the series
            ├── scale-report.ts # On-screen size of every gap, shape and stroke at 256, 48 and 16 px
            └── render-png.ts   # PNGs at 256, 48 and 16 px and a sheet to look at before showing

Disclaimer

Unofficial project, not affiliated with or endorsed by Rob Janoff. The references are original summaries of the book with short quotations; no text or files from the book are included.

License

MIT

// faq

What is rob-janoff-design?

Agent Skill for logo design with Rob Janoff's method from "Taking a Bite out of the Apple": design, critique and refresh logos as three one-ink SVG concepts built from a golden series, measured and rendered at 256, 48 and 16 px before they are shown.. It is open-source on GitHub.

Is rob-janoff-design free to use?

rob-janoff-design is open-source under the MIT license, so it is free to use.

What category does rob-janoff-design belong to?

rob-janoff-design is listed under skills in the Claudeers registry of Claude-compatible tools.

5 views
★ 20 stars
unclaimed
updated 6 days ago

// embed badge

rob-janoff-design on Claudeers
[![Claudeers](https://claudeers.com/api/badge/rob-janoff-design.svg)](https://claudeers.com/rob-janoff-design)

// retro hit counter

rob-janoff-design hit counter
[![Hits](https://claudeers.com/api/counter/rob-janoff-design.svg)](https://claudeers.com/rob-janoff-design)

// reviews

// guestbook

0/500

// related in Claude Skills

🔓

An agentic skills framework & software development methodology that works.

// skillsobra/⟨Shell⟩★ 314,126◷ MIT[ claude ]
🔓

Public repository for Agent Skills

// skillsanthropics/⟨Python⟩★ 188,182[ claude ]
🔓

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…

// skillsGraphify-Labs/⟨Python⟩★ 149,064◷ MIT[ claude ]
🔓

💫 Toolkit to help you get started with Spec-Driven Development

// skillsgithub/⟨Python⟩★ 148,200◷ MIT[ claude ]
→ see how rob-janoff-design connects across the ecosystem