정보
이 Claude Skill은 브랜드 창조의 초기 개념 단계를 지원하여 포지셔닝, 네이밍, 무드, 내러티브 방향을 생성하고 다듬는 데 도움을 줍니다. 사용자가 아이디어를 브레인스토밍하거나 다양한 옵션을 탐색하거나, 여러 개의 미완성 아이디어를 일관된 브랜드 개념으로 수렴해야 할 때 활성화됩니다. 시각적 아이덴티티 개발에 들어가기 전, 상류 개념 작업에 활용하세요.
빠른 설치
Claude Code
추천npx skills add rampstackco/claude-skills -a claude-code/plugin add https://github.com/rampstackco/claude-skillsgit clone https://github.com/rampstackco/claude-skills.git ~/.claude/skills/brand-ideationClaude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요
문서
Brand Ideation
Generate and converge on brand directions before committing to identity work. This is upstream of brand-identity (the visual system) and brand-style-guide (the documentation). It is the divergent-then-convergent thinking phase where ideas are cheap and direction matters more than polish.
When to use
- Generating naming options for a new brand or product
- Exploring positioning territories before committing
- Building moodboards and visual direction options
- Drafting narrative or origin-story angles
- Helping the user converge from many half-ideas to one direction
- Stress-testing an existing brand idea before investing in identity work
When NOT to use
- The brand direction is already locked, the user wants logo and identity work (use
brand-identity) - Documenting an existing brand system (use
brand-style-guide) - Defining voice for an existing brand (use
brand-voice) - Initial discovery and audience research (use
brand-discovery)
Required inputs
- The category or product type
- The audience (at least roughly)
- The reason this brand exists (the problem it solves or the gap it fills)
- Constraints (existing brand assumptions, parent brand, regulatory limits)
- Number of directions desired (typically 3 to 5)
If the audience is unclear, run brand-discovery first.
The framework: 4 stages
Brand ideation moves through four stages. Each stage diverges (generate options) then converges (pick a direction).
Stage 1: Positioning territories
A positioning territory is the strategic space the brand occupies. It is not a tagline. It is the answer to "what does this brand stand for that competitors do not?"
Generate 3 to 5 territories using these angles:
- Functional benefit. "The fastest way to X." (Risk: easy to copy.)
- Emotional benefit. "The brand that makes you feel Y." (Risk: vague if not earned.)
- Identity. "For people who are Z." (Risk: alienates non-Z customers.)
- Antagonist. "The opposite of [incumbent]." (Risk: defines you by them.)
- Originator. "The first or only one to do W." (Risk: must be defensible.)
- Worldview. "We believe V." (Risk: must be lived, not just stated.)
For each territory, write:
- Statement (one sentence)
- Why this is true (the proof point)
- What this rejects (the territory we are NOT going to)
- Risk (what makes this fragile)
Stage 2: Naming directions
Names cluster by approach. Generate names across multiple approaches, not just one.
| Approach | Description | Examples |
|---|---|---|
| Descriptive | Says what it is | "General Electric," "American Airlines" |
| Evocative | Suggests a feeling or quality | "Patagonia," "Oasis," "Stripe" |
| Founder | Person's name | "Disney," "Ford," "Tesla" |
| Acronym | Letters from longer phrase | "IBM," "BMW," "AWS" |
| Coined | Made-up word | "Kodak," "Häagen-Dazs," "Asana" |
| Metaphor | Borrowed concept | "Apple," "Amazon," "Twitch" |
| Compound | Two words combined | "Facebook," "PayPal," "Spotify" |
| Suggestive | Hints at function without describing | "Tide," "Slack," "Sprint" (historical; absorbed into T-Mobile in 2020) |
Generate 8 to 15 candidates per direction. Apply naming filters before short-listing:
- Pronounceable in target languages
- Spellable without confusion
- Available as a domain (.com or relevant TLD), social handles, and trademark
- Distinctive in the category (search the name + category, see what comes up)
- Stretchable (does the name still work if the company expands?)
- Free of negative associations (run it past native speakers of any major target market)
A short-listable name passes all six. Most names fail at least one. The bar is necessarily high.
Stage 3: Mood and visual direction
Generate visual directions BEFORE designing anything. Each direction should be distinct enough that a designer would produce visibly different work for each.
For each mood direction (typically 2 to 4):
- Mood adjectives (3 to 5 words)
- Color territory (warm/cool, saturated/muted, light/dark - not specific hex yet)
- Type territory (serif/sans, modern/classical, geometric/humanist)
- Imagery direction (photography style, illustration style, iconography)
- Reference brands or sites (3 to 5 that exemplify the direction)
- What this rejects (the visual territory we are NOT going to)
A mood direction is "Editorial sophistication: Warm cream paper backgrounds, classical serifs, archival photography. Think: The New York Times Magazine meets a literary journal."
A bad mood direction is "Modern and clean."
Stage 4: Narrative and origin
Every brand has a story. The narrative answers: how do we tell people why this exists?
Common narrative shapes:
- Founder story. A real person solved a real problem they had.
- Mission story. A bigger purpose drives every decision.
- Discovery story. We found something the world did not know.
- Heritage story. This has always been done a certain way; we honor or refresh it.
- Frustration story. The category was broken; we built the alternative.
- Vision story. Here is the future we are pulling toward.
For each candidate narrative:
- One-sentence summary
- The opening line (how the story starts when told for the first time)
- The proof points (what makes it true and not marketing puff)
- The hero (who the audience identifies with - the founder, the customer, the world)
Workflow
- Confirm the inputs. Category, audience, reason for being, constraints.
- Stage 1: Generate 3 to 5 positioning territories. Use the 6 angles above. Name what each rejects.
- Pick 1 to 2 territories. Move forward with the strongest.
- Stage 2: Generate 30 to 50 naming candidates across at least 4 approaches. Filter to 8 to 12 that pass the six-criteria check.
- Stage 3: Generate 2 to 4 mood directions. Each must be distinguishable enough to brief a designer.
- Stage 4: Generate 2 to 3 narrative shapes. Pick the one that fits the founders, the audience, and the proof points.
- Converge. Present the user with: 1 positioning, 8 to 12 naming finalists, 2 to 4 mood directions, 2 to 3 narrative shapes. Help them pick.
- Output. Use the template in
references/ideation-output-template.md.
Failure patterns
- Generating one option and calling it "the answer." The point of ideation is divergence. Without options, there is no real choice.
- Skipping the rejection step. A territory that does not name what it rejects is not a territory. Same for moods.
- Naming before positioning. Names without positioning end up arbitrary. Position first.
- Falling in love with one name too early. Run the full filter on every candidate. The clever name that fails the trademark check is not a candidate.
- "Modern, clean, minimal" mood direction. Means nothing. Always require specific reference brands.
- Skipping pronunciation tests. Especially for international brands. A name that confuses non-English speakers loses search volume forever.
- Mistaking ideation for execution. The output of this stage is direction, not finished assets. Resist the urge to design logos here.
Output format
Default output is a markdown brief at brand-ideation.md in the project root. Includes:
- The chosen positioning territory (with what it rejects)
- Naming finalists (8 to 12) with notes on each
- Mood directions (2 to 4) with reference URLs
- Narrative shape (chosen) with opening line and proof points
- Open questions and decisions still needed before identity work begins
Optional: a separate naming-explorations.md with the full list of 30 to 50 candidates (the "kill file") in case the chosen finalists fail later checks.
If required data is unavailable
This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.
Reference files
references/ideation-output-template.md- Fillable template for the ideation deliverable.references/naming-evaluation-rubric.md- The 6-criteria filter applied with examples.
GitHub 저장소
자주 묻는 질문
brand-ideation Skill이란 무엇인가요?
brand-ideation은(는) rampstackco이(가) 만든 Claude Skill입니다. Skill은 Claude가 필요할 때 불러오는 지침과 리소스를 묶어 추가 프롬프트 없이 brand-ideation 관련 작업을 수행할 수 있게 합니다.
brand-ideation은(는) 어떻게 설치하나요?
이 페이지의 설치 명령을 사용하세요. brand-ideation을(를) Claude Code 플러그인으로 추가하거나 저장소를 skills 디렉터리에 복제한 다음 Claude를 다시 시작해 Skill을 불러옵니다.
brand-ideation은(는) 어떤 카테고리에 속하나요?
brand-ideation은(는) 메타 카테고리에 속합니다.
brand-ideation은(는) 무료로 사용할 수 있나요?
네. brand-ideation은(는) AIMCP에 등록되어 있으며 무료로 설치할 수 있습니다.
연관 스킬
이 스킬은 콘텐츠 콜렉션(Content Collections)을 위한 프로덕션 검증된 설정을 제공합니다. 콘텐츠 콜렉션은 Markdown/MDX 파일을 Zod 검증이 포함된 타입 안전한 데이터 콜렉션으로 변환해주는 TypeScript 최우선 도구입니다. 블로그, 문서 사이트 또는 콘텐츠 중심의 Vite + React 애플리케이션을 구축할 때 타입 안전성과 자동 콘텐츠 검증을 보장하기 위해 사용하세요. Vite 플러그인 구성과 MDX 컴파일부터 배포 최적화 및 스키마 검증에 이르기까지 모든 것을 다룹니다.
이 스킬은 개발자들이 Polymarket 예측 시장 플랫폼을 활용한 애플리케이션을 구축할 수 있도록 지원하며, 거래 및 시장 데이터를 위한 API 통합 기능을 포함합니다. 또한 WebSocket을 통한 실시간 데이터 스트리밍을 제공하여 실시간 거래와 시장 활동을 모니터링할 수 있습니다. 이를 통해 거래 전략을 구현하거나 실시간 시장 업데이트를 처리하는 도구를 생성하는 데 활용할 수 있습니다.
이 스킬은 개발자들이 명령어, 파일, LSP 작업 등 25개 이상의 이벤트 유형에 연결되는 OpenCode 플러그인을 만들 수 있도록 돕습니다. JavaScript/TypeScript 모듈을 위한 플러그인 구조, 이벤트 API 명세, 구현 패턴을 제공합니다. OpenCode AI 어시스턴트의 라이프사이클을 사용자 정의 이벤트 기반 로직으로 가로채거나, 모니터링하거나, 확장해야 할 때 사용하세요.
SGLang은 RadixAttention 프리픽스 캐싱을 활용하여 JSON, 정규식, 에이전트 워크플로우를 위한 고속 구조화 생성에 특화된 고성능 LLM 서빙 프레임워크입니다. 특히 반복되는 프리픽스가 있는 작업에서 상당히 빠른 추론 속도를 제공하여 복잡한 구조화 출력 및 다중 턴 대화에 이상적입니다. 제약 디코딩이 필요하거나 광범위한 프리픽스 공유가 있는 애플리케이션을 구축할 때는 vLLM과 같은 대안보다 SGLang을 선택하십시오.
