SKILL·5CBDE8

brand-ideation

rampstackco
更新于 9 days ago
910
126
910
在 GitHub 上查看
元aidesign

关于

This Claude Skill assists with the early conceptual phase of brand creation, helping to generate and refine positioning, naming, mood, and narrative directions. It is triggered when users need to brainstorm, explore options, or converge multiple half-formed ideas into a coherent brand concept. Use it for upstream ideation work before moving into visual identity development.

快速安装

Claude Code

推荐
主要方式
npx skills add rampstackco/claude-skills -a claude-code
插件命令备选方式
/plugin add https://github.com/rampstackco/claude-skills
Git 克隆备选方式
git clone https://github.com/rampstackco/claude-skills.git ~/.claude/skills/brand-ideation

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

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.

ApproachDescriptionExamples
DescriptiveSays what it is"General Electric," "American Airlines"
EvocativeSuggests a feeling or quality"Patagonia," "Oasis," "Stripe"
FounderPerson's name"Disney," "Ford," "Tesla"
AcronymLetters from longer phrase"IBM," "BMW," "AWS"
CoinedMade-up word"Kodak," "Häagen-Dazs," "Asana"
MetaphorBorrowed concept"Apple," "Amazon," "Twitch"
CompoundTwo words combined"Facebook," "PayPal," "Spotify"
SuggestiveHints 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

  1. Confirm the inputs. Category, audience, reason for being, constraints.
  2. Stage 1: Generate 3 to 5 positioning territories. Use the 6 angles above. Name what each rejects.
  3. Pick 1 to 2 territories. Move forward with the strongest.
  4. Stage 2: Generate 30 to 50 naming candidates across at least 4 approaches. Filter to 8 to 12 that pass the six-criteria check.
  5. Stage 3: Generate 2 to 4 mood directions. Each must be distinguishable enough to brief a designer.
  6. Stage 4: Generate 2 to 3 narrative shapes. Pick the one that fits the founders, the audience, and the proof points.
  7. 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.
  8. 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:

  1. The chosen positioning territory (with what it rejects)
  2. Naming finalists (8 to 12) with notes on each
  3. Mood directions (2 to 4) with reference URLs
  4. Narrative shape (chosen) with opening line and proof points
  5. 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

GitHub 仓库

rampstackco/claude-skills
路径: dist/codex/.agents/skills/brand-ideation
0
agent-skillsai-agentsanthropicclaudeclaude-aiclaude-code
FAQ

常见问题

什么是 brand-ideation Skill?

brand-ideation 是一个 Claude Skill,作者为 rampstackco。Skill 将 Claude 按需加载的说明和资源打包,让 Claude 无需额外提示即可执行与 brand-ideation 相关的任务。

如何安装 brand-ideation?

使用本页的安装命令:将 brand-ideation 作为插件添加到 Claude Code,或将其仓库克隆到 skills 目录,然后重启 Claude 以加载该 Skill。

brand-ideation 属于哪个分类?

brand-ideation 属于元分类。

brand-ideation 可以免费使用吗?

可以。brand-ideation 已收录在 AIMCP,可免费安装。

相关推荐技能

content-collections
元

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能
polymarket
元

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能
creating-opencode-plugins
元

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能
sglang
元

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能