Brand
Eight-phase brand identity process that starts with an emotive narrative
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Aug 7, 2026
- Environment
- Claude Code 2.x (agent harness)
Ran Phase 0 and Phase 1 twice on the same invented product — a kiln-firing monitor for ceramics studios — once cold and once following the workflow files. The cold version described the brand as 'reliable, calm, approachable' and suggested an ember-orange accent; the skill version forced a choice among three named metaphors, landed on the potter's witness cone, named the aesthetic 'Kiln Log', and produced a rule the cold run never reached — one saturated colour, spent only on live temperature and drift, so a green 'all good' tile is banned by construction. It also emitted four literal do-say/don't-say strings instead of adjectives. The cost is real: 1,387 words against 309, and roughly 800 lines of workflow read to get there. Phase 3's render-verify loop works with rsvg-convert (vtracer and potrace were absent on the test machine and the documented browser fallbacks stand in); Phase 2's reference images need your own image-generation API key. The README is unusually candid, opening with a first-person confession that the model cannot judge its own divergence and that your selections are the actual design work.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Brand does
A markdown-only brand development system that runs identity work in eight gated phases: emotive narrative, discovery, visual direction, mark, wordmark, design system, composition and packaging, ending in a single DESIGN.md. Triggers when you ask for a brand identity, a logo and visual system, brand guidelines, or a design system spanning web and iOS. Ships nine workflow files, five document templates and a worked example brand kit.
How to install Brand
git clone https://github.com/b1rdmania/claude-brand-skills.git
mkdir -p ~/.claude/skills
cd claude-brand-skills && cp -r brand-skill ~/.claude/skills/brand
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Brand
-
/brandEight-phase brand identity process that starts with an emotive narrative
It also activates on plain-language prompts like these:
-
Build a brand identity for our startup, starting with the narrative -
Design a logo, wordmark and visual system for our new product -
Write brand guidelines spanning both web and iOS for our app
Frequently asked questions
- Is the Brand skill free?
- Yes. The skill itself is free from b1rdmania/claude-brand-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Brand work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Aug 7, 2026. Verdict: Tested · Works. Ran Phase 0 and Phase 1 twice on the same invented product — a kiln-firing monitor for ceramics studios — once cold and once following the workflow files. The cold version described the brand as 'reliable, calm, approachable' and suggested an ember-orange accent; the skill version forced a choice among three named metaphors, landed on the potter's witness cone, named the aesthetic 'Kiln Log', and produced a rule the cold run never reached — one saturated colour, spent only on live temperature and drift, so a green 'all good' tile is banned by construction. It also emitted four literal do-say/don't-say strings instead of adjectives. The cost is real: 1,387 words against 309, and roughly 800 lines of workflow read to get there. Phase 3's render-verify loop works with rsvg-convert (vtracer and potrace were absent on the test machine and the documented browser fallbacks stand in); Phase 2's reference images need your own image-generation API key. The README is unusually candid, opening with a first-person confession that the model cannot judge its own divergence and that your selections are the actual design work.
- What is the Brand SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Brand?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Brand with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.