Token导航 LogoToken导航TokenDH.com
研究检索可写文件github未标认证来源可访问许可证需确认审计通过

product-naming产品命名

Agent Skill

product-naming 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

235

周安装

10

GitHub Stars

1

下载量

82
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:product-naming(产品命名)
来源仓库:https://github.com/elliottrjacobs/bench-skills
仓库路径:skills/product-naming
安装命令:
npx skills add https://github.com/elliottrjacobs/bench-skills --skill product-naming
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/elliottrjacobs/bench-skills --skill product-naming

简介

product-naming 提供基于 David Placek 方法论的专业命名流程,适用于产品、功能或公司名称创作。

  • 通过结构化步骤识别品牌本质、生成候选名称并评估可用性,支持多轮迭代优化。
  • 使用时需提供产品描述、目标用户和核心属性,Agent 将引导完成完整命名流程。
  • 安装前建议确认是否具备网络访问权限以调用外部词库或商标数据库。
  • 注意:最终名称选择需人工审核商标可用性和法律合规性。

SKILL.md

/product-naming — Expert Naming Process

Structured naming process based on David Placek's methodology (Lexicon Branding — created names for Sonos, Pentium, Blackberry, Swiffer).

When to Use

  • User says "name this", "brainstorm names", "naming process"
  • Naming a new product, feature, company, or project
  • Evaluating existing name candidates

Process

Step 1: Identify — Define the Brand Essence

If $ARGUMENTS provides a product or feature description, use it as the starting point. Ask the user to define (or help them articulate):

  • What is it? (1 sentence describing the thing to be named)
  • Core attributes (3-5 adjectives that describe the ideal brand feeling)
  • Target audience (who will use/hear this name most)
  • Competitive context (what other names exist in this space)
  • Constraints (domain availability needed? character limit? language considerations?)

Step 2: Invent — Generate Name Candidates

Generate 50+ name candidates across these categories:

Descriptive — Names that say what it is

  • Functional descriptors (YouTube, Netflix, Dropbox)
  • Compound words (Facebook, WordPress, Snapchat)

Metaphorical — Names that evoke a feeling or concept

  • Nature metaphors (Amazon, Apple, Sierra)
  • Action metaphors (Sprint, Dash, Vercel)
  • Quality metaphors (Zendesk, Clarity, Notion)

Abstract — Names that are evocative but not literal

  • Sound-symbolic (Sonos, Zoom, Slack)
  • Portmanteaus (Pinterest = Pin + Interest, Spotify)
  • Modified words (Lyft, Flickr, Tumblr)

Invented — Completely new words

  • Phonetic constructions (Kodak, Xerox, Hulu)
  • Latin/Greek roots (Astra, Vero, Luma)
  • Generated strings (ASML, Nvidia)

Present candidates organized by category. Aim for quantity — curation comes next.

Step 3: Evaluate — Score and Rank

Score the top 15-20 candidates on these criteria (1-5 scale):

CriterionWeightDescription
MemorabilityHighEasy to recall after hearing once
PronounceabilityHighObvious pronunciation, works spoken aloud
DistinctivenessHighStands out from competitors
Meaning/EvocationMediumConveys the right feeling or concept
Domain/HandleMedium.com or reasonable alternative available
ScalabilityLowWon't constrain future product expansion

Use AskUserQuestion to have the user react to the top candidates:

  • Which names do you gravitate toward?
  • Which feel wrong? Why?
  • Any you'd like to combine or riff on?

Step 4: Present — Final Recommendation

Present top 5-10 names with:

  • The name
  • Category (descriptive/metaphorical/abstract/invented)
  • Why it works (connects back to brand essence)
  • Potential concerns
  • Domain availability (check via WebSearch if requested)

See references/placek-methodology.md for deeper methodology notes.

Output

Present recommendations inline in conversation. Optionally save to a file if the user requests.

Next Steps

  • Happy with the name? Document it in the PRD
  • Need to formalize the product? → /product-prd

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.44%
按下载量换算32

Claude

29.48%
按下载量换算24

Cursor

20.52%
按下载量换算17

Gemini CLI

9.39%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

可写文件

该 Skill 可能写入或修改本地文件,使用前需要确认目标目录和修改范围。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills