Agent skill

Logo Designer

by luongnv89 in luongnv89/skills

Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page.

MITAuto-check passedMedia & Creative

Install Logo Designer

skills CLI
$ npx skills add luongnv89/skills --skill logo-designer -a claude-code

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

GitHub CLI
$ gh skill install luongnv89/skills logo-designer --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/luongnv89/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/logo-designer .claude/skills/logo-designer && 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
logo-designer
GitHub stars
131
Token cost
~3k tokens
SKILL.md length
1,182 words
Files
11 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page.

  • Works in 4 steps: Project Analysis → Logo Design → Deliverables → …
  • Raster-only logos
  • SKILL.md covers Environment Check, Subagent Architecture, Repo Sync Before Edits… and Workflow, plus 6 more sections
  • Calls git

What it does

Logo Designer is an agent skill from luongnv89/skills. Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page. Use for product marks, wordmarks, icons, and favicons. Don't use for raster-only logos, illustrations, or full brand guidelines.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `agents/brand-researcher.md`, `agents/svg-generator.md` and `agents/svg-reviewer.md`).

It sits in Media & Creative, covering Logo and visual identity and Brand strategy and identity. The repository describes itself as: Supercharge your AI agents/bots with reusable skills. The licence is MIT.

When your agent uses it

  • Raster-only logos
  • Full brand guidelines

Example prompts

  • “/logo-designer”

Workflow steps

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

  1. Project Analysis
  2. Logo Design
  3. Deliverables
  4. 5: Documentation & Brand Showcase

What it can do on your machine

Read from SKILL.md and the folder at commit 891c720. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Logo Designer loads about 3k tokens when it runs, and up to ~7.9k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 1,182 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
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.9k

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 passed

The automated check found no risky patterns in SKILL.md.

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 luongnv89/skills at commit 891c720, republished under its MIT licence (© luongnv89). 1,182 words, ~2,973 tokens.

Download SKILL.mdSave it as .claude/skills/logo-designer/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
logo-designer
description
Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page. Use for product marks, wordmarks, icons, and favicons. Don't use for raster-only logos, illustrations, or full brand guidelines.
license
MIT
effort
medium
metadata.version
1.4.0
metadata.author
Luong NGUYEN <luongnv89@gmail.com>

Logo Designer

Design modern, professional logos by analyzing project context and generating SVG-based brand assets.

Environment Check

Before running this skill, verify:

  • You're in a project directory with a README or package.json
  • You have write access to create /assets/logo/ directory
  • The project directory is a git repository (optional, but recommended)

If any check fails, the skill will stop and ask for clarification.

Subagent Architecture

This skill uses an Explorer+Executor (A) + Review Loop (C) architecture:

Phase 1: Brand Research
  ↓ (brand-researcher agent)
  ↓
Phase 2: Interactive Style Selection
  ↓ Main agent: confirm style selection with user
  ↓
Phase 3: Generate All 7 SVGs
  ↓ (svg-generator agent)
  ↓
Phase 4: SVG Validation
  ↓ (svg-reviewer agent)
  ↓
Final Output: 7 SVG files in /assets/logo/ + brand-showcase.html + Design Rationale

Agents:

  1. agents/brand-researcher.md — Reads project files, produces structured brand brief
  2. agents/svg-generator.md — Generates all 7 SVG files (mark, wordmark, full, icon, favicon, white, black)
  3. agents/svg-reviewer.md — Validates SVG structure (viewBox, no rasters, all files present, correct names)

Key Insight: 7 SVG files generated inline is the single biggest context cost. Brand research across multiple project files adds to the burden. The reviewer acts as a quality gate to catch SVG structure issues before files are committed.

Repo Sync Before Edits (mandatory)

Before creating/updating/deleting files in an existing repository, sync the current branch with remote. If the working tree is not clean, stash first, sync, then restore:

bash
branch="$(git rev-parse --abbrev-ref HEAD)"
dirty=0
if [ -n "$(git status --porcelain)" ]; then
  git stash push -u -m "pre-sync"
  dirty=1
fi
git fetch origin
git pull --rebase origin "$branch"
if [ "$dirty" -eq 1 ]; then
  git stash pop
fi

If origin is missing, pull is unavailable, or rebase/stash conflicts occur, stop and ask the user before continuing.

Workflow

Phase 1: Project Analysis

Automatically analyze the current project to understand brand context:

  1. Detect product identity - Check these files in order:

    • README.md - Product name, description, tagline
    • package.json - Name, description, keywords
    • pyproject.toml - Project name and description
    • Cargo.toml - Package name and description
    • go.mod - Module name
  2. Find existing brand assets - Search for:

    • /docs/brand_kit.md, /.docs/brand_kit.md, brand_kit.md
    • /docs/prd.md, prd.md - Product requirements with brand info
    • /assets/logo/, /public/logo, /static/logo - Existing logos
    • Tailwind config for existing color palette
  3. Identify project type from codebase structure:

    • Developer/CLI/Open Source - .github/, CLI entry points, MIT license
    • SaaS/Productivity - Web app structure, auth, dashboard patterns
    • Startup - Lean structure, MVP patterns
    • Enterprise/B2B - Complex architecture, integrations
    • Consumer/Mobile - React Native, Flutter, mobile-first patterns
  4. Summarize findings before proceeding:

    Product: [name]
    Type: [Developer Tool / SaaS / Startup / Enterprise / Consumer]
    Purpose: [1-sentence description]
    Audience: [target users]
    Existing colors: [hex codes if found, or "None detected"]
    Assets found: [list or "None"]
Phase 2: Logo Design

Pick a style based on the detected project type (Developer/SaaS/Startup/Enterprise/Consumer), then design a minimalist, geometric mark that reads at every size from 16px favicon to hero banner. Use detected brand colors when present, else apply the Default Style Guide (dark base + neon-green highlights only — never as a fill). Confirm with the user how the product name should be cased in the wordmark before generating any text-bearing SVG.

See references/design-principles.md for the style table, full visual/color/typography rules, and the Default Style Guide palette with system status colors.

Default Quality Bar

All 7 SVGs and brand-showcase.html must be professional, production-ready, elegant, and premium, even unasked. The chosen style sets direction; this bar sets the finish (craft and restraint, not ornament): optical balance, consistent strokes, clean minimal paths legible at 16px, refined wordmark kerning, and a polished showcase with no placeholders. Pass this bar to svg-generator.

Phase 3: Deliverables

Generate the canonical mark first, then derive 6 sibling variants from its exact path data so every file shares the same geometry. The svg-generator agent must receive the literal d="" strings — do not paraphrase shapes.

Output structure:

/assets/logo/
├── logo-mark.svg          # Canonical 64×64 mark (source of truth)
├── logo-full.svg          # 320×72 mark + wordmark
├── logo-wordmark.svg      # 180×40 text only
├── logo-icon.svg          # 512×512 app icon (centered, padded)
├── favicon.svg            # 16×16 simplified 2-layer mark
├── logo-white.svg         # 320×72 white (for dark backgrounds)
├── logo-black.svg         # 320×72 black (for light backgrounds)
└── brand-showcase.html    # Self-contained brand identity page

After writing all 7 files, read back mark, full, icon, white, and black variants and verify d="" strings are identical (or correctly scaled via transform). Fix divergences before continuing.

See references/svg-deliverables.md for full variant specifications, scale calculations, favicon simplification rules, and SVG requirements.

Phase 4–5: Documentation & Brand Showcase

After SVGs are written, output the design rationale (symbol meaning, color choices, typography reasoning), a hex-code color specification, and a Tailwind config snippet. Then generate /assets/logo/brand-showcase.html — a self-contained presentation page (hero, design concept, variant grid, palette, typography, dev reference, footer) and open it in the browser.

See references/brand-showcase.md for the full HTML page structure, design guidelines, and the documentation template.

Expected Output

For a CLI tool called "fastbuild", the skill produces:

/assets/logo/
├── logo-mark.svg          — 64×64 abstract "F" mark (canonical geometry)
├── logo-full.svg          — 320×72 mark + "FASTBUILD" wordmark
├── logo-wordmark.svg      — 180×40 text-only wordmark
├── logo-icon.svg          — 512×512 mark centered in rounded square
├── favicon.svg            — 16×16 simplified 2-layer mark
├── logo-white.svg         — 320×72 full logo in white (for dark backgrounds)
├── logo-black.svg         — 320×72 full logo in black (for light backgrounds)
└── brand-showcase.html    — self-contained brand identity presentation page

Design rationale summary presented to the user:

Product: fastbuild
Type: Developer/CLI Tool
Symbol: Abstract "F" from stacked horizontal speed bars
Colors: #0A0A0A base, #00FF41 neon green accent (borders and highlights only)
Typography: Inter Bold for wordmark

Edge Cases

  • No project context found: Ask the user for product name, product type, and one-sentence purpose before generating anything.
  • Existing brand colors detected: Use them instead of the default dark/neon-green palette; confirm with the user before proceeding.
  • User does not specify wordmark casing: Ask explicitly before proceeding (see references/design-principles.md for the casing rule and examples).
  • SVG geometry diverges across variants: Re-run the Phase 3 verification step (read back and diff d="" strings) and fix before finishing.
  • No git repository: Skip the branch and sync steps; write directly to the current directory and note this in the summary.
  • favicon.svg complexity: At 16×16 the full mark is unreadable — always simplify to 2 layers (outer + inner) and drop the middle detail layer; preserve proportional geometry.
  • User rejects the proposed style: Iterate on Phase 2 (style selection) until the user approves before generating any SVG files.
Show full SKILL.md (413 more words)Show less

Final Report

End every run, stops included, with this compact text block. Status is COMPLETE (all 7 SVGs and brand-showcase.html written, geometry verification passed), PARTIAL (files written, a check still fails), or BLOCKED (no files written). A question that awaits the user's answer does not end the run; if the user ends the run without answering, the status is BLOCKED. Fill rules, PARTIAL and BLOCKED examples, and reader checks: references/final-report.md. Example:

text
Result: COMPLETE. Wrote 7 SVGs and brand-showcase.html to /assets/logo/.
Evidence: Read back mark, full, icon, white and black variants: d="" strings identical. svg-reviewer: all viewBox attributes correct, no embedded rasters. Default Quality Bar passed. sync: skipped (not a git repo)
Uncertainty: Assumed a developer-tool audience from the CLI entry point; the user did not say.
Decision: No approval needed. Export PNG sizes from logo-icon.svg if you need raster assets.

Acceptance Criteria

  • All 7 SVG files are written to /assets/logo/ with the correct filenames
  • logo-mark.svg is created first and its d="" path strings are used verbatim in all derived variants
  • Every SVG has a correct viewBox attribute and contains no embedded rasters
  • Monochrome variants (logo-white.svg, logo-black.svg) differ from logo-full.svg only in color, not geometry
  • favicon.svg is a simplified 2-layer version of the mark at 16×16
  • brand-showcase.html is written and opens correctly in a browser
  • Design rationale (symbol meaning, color choices, typography) is documented in the response
  • Color specification includes hex codes for all palette roles
  • Wordmark casing is confirmed with the user before any SVG containing text is generated
  • Every SVG and the showcase page meet the Default Quality Bar (professional, production-ready, elegant, premium) without the user asking
  • The Final Report opens with Result: and its status, and has Evidence:, Uncertainty:, and Decision: lines. Evidence: cites only checks that ran
  • The Final Report passes the four reader checks in references/final-report.md (result findable, facts and assumptions separated, claims traceable, next decision clear). Without a human reviewer's answer, human understanding is unconfirmed

Step Completion Reports

After each phase, emit a ◆ [Phase] (step N of 4) status block listing per-check pass/fail and a final Result: line (PASS | FAIL | PARTIAL). Keep the agent's context budget tight by reusing the template — do not re-paraphrase it per phase.

See references/step-reports.md for the full report template, per-phase check lists, and a worked Analysis Summary example.

Notes

  • Always show logo previews on both light (#FAFAFA) and dark (#0A0A0A) backgrounds
  • Confirm wordmark casing before generating (see Phase 2 and Edge Cases)
  • If no project context is found, ask the user for: product name, type, and purpose
  • Prefer simplicity — a logo should be recognizable at 16x16 pixels
  • Consistency is non-negotiable: every variant must be visually recognizable as the same logo. The mark shape, number of layers, and accent elements must match across all files. The only things that change between variants are: color (monochrome), scale (favicon, icon), and presence of wordmark. If you cannot verify that paths match, the deliverable is incomplete.

© luongnv89, 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 10 other files (references) in skills/logo-designer of luongnv89/skills.

  • SKILL.md
  • agents/brand-researcher.md
  • agents/svg-generator.md
  • agents/svg-reviewer.md
  • docs/README.md
  • evals/evals.json
  • references/brand-showcase.md
  • references/design-principles.md
  • references/final-report.md
  • references/step-reports.md
  • references/svg-deliverables.md

Open the folder on GitHubat commit 891c720

Compare with similar skills

Logo Designer 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.

Logo Designer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Logo Designer this skillluongnv89/skills131—~3kAutomated safety check: PassMIT
Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill134k1 repos~3.5kAutomated safety check: PassMIT
Anthropic Brand Stylinganthropics/skills180k30 repos~559Automated safety check: PassApache-2.0
Brand Design Skillziguishian/brand-design-skill152—~4.4kAutomated safety check: PassNone
Design Masterminhnv0807/ai-business-skills610—~4.6kAutomated safety check: PassMIT
Brand Setuphassancs91/claude-youtube-editor325—~2.3kAutomated 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.

    134k 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
  • Brand Design Skill

    ziguishian/brand-design-skill

    Drive a strict conversational, image-first and image-final brand identity design process.

    152 GitHub stars~4.4k tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed
  • Design Master

    minhnv0807/ai-business-skills

    Handles eight kinds of marketing visual requests, from logos and campaign key visuals to infographics and quote graphics, by generating images or writing paste-ready prompts.

    610 GitHub stars~4.6k tokensUpdated 27 days ago
    Media & CreativeAuto-check passed
  • Brand Setup

    hassancs91/claude-youtube-editor

    Makes this repo's videos look like YOUR channel instead of the house default — interviews you for palette, fonts, wordmark, motion energy, delivery specs and SFX taste, then rewrites brand.md +…

    325 GitHub stars~2.3k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Brand Style Guide

    rampstackco/claude-skills

    Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts.

    941 GitHub stars~2.1k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

More from luongnv89/skills

All 37 skills in this repo
  • Dont Make Me Think

    luongnv89/skills

    Review UI usability using Steve Krug's principles and produce a scannable report.

    131 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Herdr Agent

    luongnv89/skills

    Manage AI agent fleets in Herdr: tile root + sub-agents in one tab, start/prompt/wait/read/monitor via the herdr agent CLI, steer any pane; help lists every operation.

    131 GitHub stars~4.8k tokensUpdated today
    Auto-check passed
  • Ollama Optimizer

    luongnv89/skills

    Optimize Ollama configuration for the current machine's hardware.

    131 GitHub stars~4.1k tokensUpdated today
    Auto-check: notes
  • Security Setup

    luongnv89/skills

    Install local-first security hardening: pre-commit secret detection, offline dependency scans, static analysis, reports, and gated free CI.

    131 GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • SEO AI Optimizer

    luongnv89/skills

    Audit and optimize websites for technical SEO, content SEO, and AI bot accessibility.

    131 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Tasks Generator

    luongnv89/skills

    Generate sprint-based development tasks from a PRD. An agent skill from luongnv89/skills.

    131 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

Questions about Logo Designer

What does Logo Designer do?

Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page. Logo Designer is an agent skill from luongnv89/skills. Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page.

When should I use Logo Designer?

Logo Designer fits situations like: raster-only logos; full brand guidelines.

How do I install Logo Designer in Claude Code?

Run `npx skills add luongnv89/skills --skill logo-designer -a claude-code`. Or copy the skill folder (skills/logo-designer in luongnv89/skills) into .claude/skills/logo-designer in your project. Claude Code loads it when a task matches its description.

How do I install Logo Designer in Codex?

Run `npx skills add luongnv89/skills --skill logo-designer -a codex`. Or copy the skill folder (skills/logo-designer in luongnv89/skills) into .agents/skills/logo-designer in your project. Codex loads it when a task matches its description.

Can I use Logo Designer 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 luongnv89/skills --skill logo-designer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/logo-designer, .gemini/skills/logo-designer, .github/skills/logo-designer and .opencode/skills/logo-designer in your project.

What does Logo Designer need to run?

Going by SKILL.md and its folder, Logo Designer needs the command-line tools its instructions call (git).

Does Logo Designer access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Logo Designer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Logo Designer use?

Logo Designer 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 Logo Designer use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.9k tokens, read only when the agent opens those files.

What are the alternatives to Logo Designer?

Skills that share tags, products or a category with Logo Designer: Brand and Design Toolkit (nextlevelbuilder/ui-ux-pro-max-skill, 134k stars), Anthropic Brand Styling (anthropics/skills, 180k stars), Brand Design Skill (ziguishian/brand-design-skill, 152 stars) and Design Master (minhnv0807/ai-business-skills, 610 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Logo Designer?

luongnv89 (a GitHub user) maintains it in luongnv89/skills, which has 131 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 9, 2026.

Source: luongnv89/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.