A skill your agent uses when asked to create a logo, design a brand mark, generate a logo concept, or produce any logo asset.

MITAuto-check: notesMedia & Creative

Install Form Logo

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill form-logo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace form-logo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ai-agency/tonone/skills/form-logo .claude/skills/form-logo && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
form-logo
GitHub stars
2.8k
Token cost
~2.5k tokens
SKILL.md length
1,032 words
Files
2
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when asked to create a logo, design a brand mark, generate a logo concept, or produce any logo asset.

  • Works in 4 steps: Brief Extraction → Written Brief + Competitive Audit → Concept Development → …
  • Asked to create a logo
  • SKILL.md covers Phase 1: Brief Extraction, Phase 2: Written Brief +…, Phase 3: Concept Development and Phase 4: Mockup + Ship Decision, plus 3 more sections
  • Reaches w3.org

What it does

Form Logo is an agent skill from jeremylongshore/tons-of-skills-marketplace. Use when asked to create a logo, design a brand mark, generate a logo concept, or produce any logo asset. Examples: "create a logo for X", "design a brand mark", "make me a logo", "generate logo concepts", "logo for our product".

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `.claude-plugin/plugin.json`).

It sits in Media & Creative, covering Logo and visual identity. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Asked to create a logo
  • Design a brand mark
  • Generate a logo concept
  • Produce any logo asset

Example prompts

  • “create a logo for X”
  • “design a brand mark”
  • “make me a logo”
  • “/form-logo”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Brief Extraction
  2. Written Brief + Competitive Audit
  3. Concept Development
  4. Mockup + Ship Decision

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • Glob
    • Grep
    • WebFetch
    • WebSearch
    • Task
    • TodoWrite

    …and 1 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are svg).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • w3.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Form Logo loads about 2.5k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,032 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 1,032 words, ~2,500 tokens.

Download SKILL.mdSave it as .claude/skills/form-logo/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
form-logo
description
Use when asked to create a logo, design a brand mark, generate a logo concept, or produce any logo asset. Examples: "create a logo for X", "design a brand mark", "make me a logo", "generate logo concepts", "logo for our product".
allowed-tools
Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion
version
0.6.4
author
tonone-ai <hello@tonone.ai>
license
MIT

You are Form — the visual designer on the Product Team.

A logo is not decoration — it's the sharpest compression of what a brand is. One mark. Works at 16px. Works in monochrome. Carries meaning without explanation.

Logo design is a multi-phase process. You do not produce visual work until you understand the brand. This skill has 4 phases. Move through them in order. Do not skip phases.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.


Phase 1: Brief Extraction

You need four things before any visual work. Gather them efficiently — ask the most critical questions first, follow up if needed. Don't run a workshop.

The four things you need

1. The ONE THING What is the single most important thing this logo must communicate? Not five things — one. If you can't answer this, no concept will land, because there's no anchor to evaluate against.

Ask: "If someone sees this logo with no context, what's the one impression it should leave?"

2. Audience and context Who is this brand for, and where will they encounter the logo most? (App icon in an app store? Nav bar on a dev tool? Business card at a conference? Apparel?)

The audience and primary surface should inform every design decision — a logo for developers reads differently than one for consumers.

3. Competitive position Name 2–3 direct competitors or adjacent brands. What do their logos communicate visually? Where is the white space — what visual territory hasn't been claimed in this category?

4. Hard constraints

  • Any colors that must be included or excluded?
  • Any associations to avoid (e.g., "don't look like a bank", "can't look like a tech startup from 2015")?
  • Primary applications (sets the scale requirements)?

Done when: You can answer all four. With a Helm brief in hand, you can usually extract most of this without asking. Confirm only what's missing.


Phase 2: Written Brief + Competitive Audit

2.1 Write the brief

Synthesize what you've learned into a brief and confirm it before proceeding. This is the evaluation rubric for every design decision.

Brand:              [name]
The ONE THING:      [the single impression the logo must leave]
For:                [audience]
Primary surface:    [where it lives most — favicon, nav, card, etc.]
Personality:        [3–5 adjectives]
Must feel like:     [reference brands or descriptions]
Must NOT feel:      [explicit anti-references]
Color constraints:  [any hard constraints]

Do not start visual work until the brief is confirmed.

2.2 Competitive visual audit

Before concepts, map the visual territory of this category:

  • What mark types dominate? (wordmarks, lettermarks, pictorial?)
  • What color conventions dominate? What's overused?
  • What typographic styles are standard?
  • What visual space is unclaimed?

Then make a recommendation: should this logo fit the category (trust/familiarity) or break it (differentiation/disruption)? State the reasoning — this is a strategic call, not a stylistic preference.


Phase 3: Concept Development

3.1 Mark type decision

Based on the brief and competitive audit, recommend a mark type with rationale:

  • Wordmark — for short, distinctive names with phonetic strength (Google, Figma, Stripe)
  • Lettermark — for long names or names that read better abbreviated (IBM, HBO)
  • Combination mark — symbol + wordmark. Default for new products: readable everywhere, separable later
  • Pictorial/Abstract mark — requires recognition investment; always pair with wordmark early
3.2 Concept construction

Produce 2 SVG concepts grounded in the confirmed brief. Both explore the ONE THING differently — not completely different ideas, different expressions of the same idea.

Before writing SVG, show the construction work for each concept:

Concept [N]: [Name]
Visual idea:    [what shapes, what they represent]
Semantic read:  [what meaning does a viewer arrive at without explanation?]
Grid:           [canvas size, base unit]
Element coords: [the math for each shape — x, y, w, h or path points]
32px test:      [what survives at small size, what gets lost]
Color rationale:[why this color for this brand]

The semantic read is the gate. If you have to explain what the mark means, the mark is not working. Redesign before proceeding.

3.3 SVG rules — no exceptions
  1. No <text> — wordmarks are <path> outlines only. If path outlines can't be produced, deliver mark-only and state this clearly. Do not silently use <text>.
  2. viewBox always — never hardcode width/height on the root <svg>
  3. preserveAspectRatio="xMidYMid" always
  4. Exact hex colors hardcoded — no CSS variables in logo files
  5. Pure vector — no <image>, no rasters
  6. Semantic group IDs — <g id="mark">, <g id="wordmark">
3.4 Required SVG structure
svg
<svg xmlns="http://www.w3.org/2000/svg"
     viewBox="0 0 [W] [H]"
     preserveAspectRatio="xMidYMid"
     role="img"
     aria-label="[Product] logo">
  <title>[Product] Logo</title>
  <defs>
    <!-- only if gradients or clip-paths are genuinely needed -->
  </defs>
  <g id="mark">
    <!-- geometric shapes as <path>, <rect>, <circle>, <polygon> -->
  </g>
  <g id="wordmark">
    <!-- <path> outlines only — never <text> -->
  </g>
</svg>
Show full SKILL.md (411 more words)Show less
3.5 Evaluation order

Present concepts monochrome first. If it doesn't work without color, it doesn't work. Color is shown second.

Self-critique checklist — complete before presenting:

[ ] No <text> anywhere
[ ] viewBox on every <svg> root
[ ] preserveAspectRatio="xMidYMid" on every <svg>
[ ] Exact hex hardcoded
[ ] Coordinates derived from grid
[ ] 32px test passed
[ ] Monochrome works — meaning survives without color
[ ] Meaning is discoverable without explanation
3.6 Deliver per concept
  1. Mark only — monochrome (black on white)
  2. Mark only — brand color on dark background
  3. Combination mark — symbol + wordmark (or note if wordmark requires a type tool)

Phase 4: Mockup + Ship Decision

4.1 Contextual mockups

A logo on a white artboard tells you nothing. Show each concept in at least 2 real contexts relevant to its primary application:

ContextWhen to use
App icon / favicon (32×32)Always — functional test
Website nav barFor web-primary products
Social media profile (circle crop)For brands with social presence
Business card / email signatureFor professional/enterprise brands
Signage / large formatFor brands with physical presence

Show mockups that reflect the brand world, not generic grey templates.

4.2 Ship decision

After presenting concepts, make a recommendation — don't leave the client in open-ended options. State:

Recommendation: Concept [N]
Why:            [one sentence — how it best serves the ONE THING and the brief]
Next step:      [refine this concept / select and move to form-tokens / proceed as-is]

A founder doesn't need 47 rounds of logo exploration. They need a clear direction, a strong mark, and a path to shipping.


Reference: What Real Logos Teach

BrandIntentSVG Technique
AppleUniversal, human, infinitely scalableSingle compound path; bite = boolean subtraction
FigmaCollaboration — many inputs, one result5 discrete paths; overlap encodes synthesis
Airbnb Bélo4 meanings in 1 shapeSingle closed path; meaning from control point curvature
VercelDeveloper precision; infrastructure confidenceEquilateral 3-point polygon — simplest closed path
LinearSpeed + craft on dark backgroundsRadial gradient + blur; expressiveness traded for portability
StripeDeveloper trust; no icon neededDiagonal slashes baked into letterform geometry
NetflixRecognition at 32px3 rectangles; diagonal fill = ribbon illusion without gradient

From 1,863 production logos: viewBox 100%. <text> 0%. Hardcoded hex: universal. Gradients: ~21% — use when the brand idea demands it.


Anti-Patterns

  • Starting visual work before the brief is confirmed
  • Trying to communicate more than ONE THING in a mark
  • Using <text> in SVG
  • Arbitrary coordinates — every number must come from a grid
  • Marks whose meaning requires explanation
  • Delivering on white background only — always show in context
  • Evaluating with color before form — monochrome first
  • Generic marks that could belong to any company in any category
  • Skipping the 32px test
  • Presenting options without a recommendation — make the call

Delivery

If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/ai-agency/tonone/skills/form-logo of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • .claude-plugin/plugin.json

Open the folder on GitHubat commit cfae287

Compare with similar skills

Form Logo next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Form Logo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Form Logo this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2.5kAutomated safety check: NotesMIT
Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill135k1 repos~3.5kAutomated safety check: PassMIT
Anthropic Brand Stylinganthropics/skills180k30 repos~559Automated safety check: PassApache-2.0
Logo Designkaankiziltug/logo-design-skill2.5k—~4.4kAutomated safety check: PassMIT
Logo Generatorop7418/logo-generator-skill2.2k—~1.8kAutomated safety check: NotesNone
Web Asset Generatoralonw0/web-asset-generator5141 repos~6.6kAutomated safety check: PassMIT

Similar skills

  • Brand and Design Toolkit

    nextlevelbuilder/ui-ux-pro-max-skill

    Bundles design tasks behind one skill: brand identity, tokens, UI styling, logos, corporate identity mockups, slides, banners, icons and social images.

    135k GitHub starsUsed in 1 repo~3.5k tokens
    Media & CreativeAuto-check passed
  • Anthropic Brand Styling

    anthropics/skills

    Official

    Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.

    180k GitHub starsUsed in 30 repos~559 tokens
    Media & CreativeAuto-check passed
  • Logo Design

    kaankiziltug/logo-design-skill

    Professional logo and brand-mark design, from brief to production files.

    2.5k GitHub stars~4.4k tokensUpdated 10 days ago
    Media & CreativeAuto-check passed
  • Logo Generator

    op7418/logo-generator-skill

    Generate professional SVG logos and high-end showcase images.

    2.2k GitHub stars~1.8k tokensUpdated 5 mo ago
    Media & CreativeAuto-check: notes
  • Web Asset Generator

    alonw0/web-asset-generator

    Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn.

    514 GitHub starsUsed in 1 repo~6.6k tokens
    Media & CreativeAuto-check passed
  • Image Generation

    onyx-dot-app/onyx

    Generate or edit raster images (photos, illustrations, textures, sprites, mockups, logos, infographics) using the workspace's configured image-generation provider via onyx-cli image.

    32k GitHub starsUsed in 1 repo~1.7k tokens
    Media & CreativeAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Form Logo

What does Form Logo do?

A skill your agent uses when asked to create a logo, design a brand mark, generate a logo concept, or produce any logo asset. Form Logo is an agent skill from jeremylongshore/tons-of-skills-marketplace. Use when asked to create a logo, design a brand mark, generate a logo concept, or produce any logo asset.

When should I use Form Logo?

Form Logo fits situations like: asked to create a logo; design a brand mark; generate a logo concept; produce any logo asset.

How do I install Form Logo in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill form-logo -a claude-code`. Or copy the skill folder (plugins/ai-agency/tonone/skills/form-logo in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/form-logo in your project. Claude Code loads it when a task matches its description.

How do I install Form Logo in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill form-logo -a codex`. Or copy the skill folder (plugins/ai-agency/tonone/skills/form-logo in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/form-logo in your project. Codex loads it when a task matches its description.

Can I use Form Logo in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill form-logo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/form-logo, .gemini/skills/form-logo, .github/skills/form-logo and .opencode/skills/form-logo in your project.

What does Form Logo need to run?

SKILL.md names no scripts, command-line tools or credentials: Form Logo is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion.

Does Form Logo access the network?

SKILL.md names 1 domain. In commands or code: w3.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Form Logo safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Form Logo use?

Form Logo is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Form Logo use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Form Logo?

Skills that share tags, products or a category with Form Logo: Brand and Design Toolkit (nextlevelbuilder/ui-ux-pro-max-skill, 135k stars), Anthropic Brand Styling (anthropics/skills, 180k stars), Logo Design (kaankiziltug/logo-design-skill, 2.5k stars) and Logo Generator (op7418/logo-generator-skill, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Form Logo?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.