Token导航 LogoToken导航

Agent Skill · 研究检索

research-brand(研究品牌)

research-brand 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。

research-brand 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 66,285。

总安装 267周安装 11GitHub Stars 911下载 87核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:research-brand(研究品牌)
来源仓库:https://github.com/onvoyage-ai/gtm-engineer-skills
仓库路径:skills/research-brand
安装命令:
npx skills add https://github.com/onvoyage-ai/gtm-engineer-skills --skill research-brand
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/onvoyage-ai/gtm-engineer-skills --skill research-brand

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

research-brand 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。适用于品牌策略研究、竞品分析或市场定位调研的场景。

通过安装命令 npx skills add https://github.com/onvoyage-ai/gtm-engineer-skills --skill research-brand 添加到宿主环境。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后再使用。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/research-brand

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/onvoyage-ai/gtm-engineer-skills --skill resear…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

research-brand 怎么安装?

在终端执行 npx skills add https://github.com/onvoyage-ai/gtm-engineer-skills --skill research-brand。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

research-brand 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

research-brand 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

research-brand 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

research-brand 用的人多吗?

公开数据是累计安装 267 次,近一周安装 11 次,下载 87 次,GitHub 911 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

research-brand 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
research-brand

研究品牌 · 本页

267911需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Research Brand DNA

You are a brand intelligence researcher. Given a company URL, you produce a complete Brand DNA file — everything a marketer, content strategist, or GTM team needs to start working with this brand.

Input: A URL (and optionally a one-liner about the company). Output: A brand_dna.md file saved to the user's project directory.


Process

1. Crawl the website

Fetch and read these pages (skip any that 404):

  • Homepage
  • /about, /about-us
  • /pricing
  • /product, /features
  • /blog (first page)
  • /customers, /case-studies

Extract:

  • What the product does (in their words)
  • Tagline and key messaging
  • Features listed
  • Pricing tiers and model
  • Target audience signals (who the copy speaks to)
  • Tech stack signals (frameworks, integrations mentioned)
  • Social proof (customer logos, testimonials, metrics)

2. Search the web

Run these searches:

  • "[company name]" what is — product descriptions from third parties
  • "[company name]" site:crunchbase.com OR site:ycombinator.com OR site:pitchbook.com — funding, stage, team
  • "[company name]" site:linkedin.com/company — company page, employee count
  • "[company name]" site:apps.apple.com OR site:play.google.com — app store listing (if mobile)
  • "[company name]" review OR alternative — how users and reviewers describe it
  • "[company name]" vs — who they get compared to (reveals competitors)
  • [product category] tools 2026 — landscape context

Extract:

  • Funding stage and amount
  • Team / founder info
  • Third-party descriptions (often clearer than the company's own copy)
  • Competitors mentioned alongside them
  • User sentiment and language

3. Identify competitors

From steps 1-2, compile 3-5 direct competitors. For each, note:

  • Name and URL
  • One-line description
  • How they overlap with the brand
  • Key differentiator vs the brand

If competitors are unclear, search: [product category] alternatives and [product category] comparison.

4. Synthesize the Brand DNA

Write brand_dna.md using this exact structure:

# Brand DNA — [Company Name]

## Overview
- **Website:** [URL]
- **One-liner:** [What they do in one sentence — use third-party language, not marketing fluff]
- **Category:** [Product category]
- **Stage:** [Seed / Series A / Growth / Public / Unknown]
- **Funding:** [Amount if known, else "Not disclosed"]
- **Founded:** [Year if known]
- **Team:** [Founder names + backgrounds if found]

## What It Does
[2-3 sentences. Plain language. What problem does it solve, for whom, and how.]

## Key Features
1. **[Feature name]** — [one-line description]
2. **[Feature name]** — [one-line description]
[list all major features, max 8]

## Target Customer
- [Persona 1 — role + pain point]
- [Persona 2 — role + pain point]
- [Persona 3 if applicable]

## Pricing
[Tiers and pricing if found. "Free", "Freemium", "Not public" if unknown.]

## Competitors
| Competitor | What They Do | Overlap | Their Edge |
|-----------|-------------|---------|-----------|
| [Name] | [one-liner] | [where they compete] | [what they do better] |

## Differentiators
- [What makes this brand unique vs competitors — be specific]
- [Unique feature, approach, positioning, or credential]

## Brand Voice
- **Tone:** [Professional / Casual / Technical / Bold / etc.]
- **Language patterns:** [Key phrases, terminology they repeat]
- **Positioning:** [How they frame themselves — challenger, leader, specialist, etc.]

## Social Proof
- [Notable customers, logos, testimonials, metrics, awards]
- [App store ratings, review counts, G2/Capterra scores if found]

## Online Presence
- **LinkedIn:** [URL]
- **Twitter/X:** [URL]
- **App Store:** [URL if applicable]
- **Blog:** [URL if exists]
- **Other:** [GitHub, Discord, YouTube, TikTok, etc.]

## Content Gaps
- [What content is missing from their website that would help SEO/GEO]
- [Topics they should cover but don't]
- [Competitor content they're missing]

## Raw Notes
[Any additional context, quotes, or observations that don't fit above but might be useful later.]

5. Deliver

Save the file and tell the user:

  1. Where it was saved
  2. Top 3 most interesting findings (things the user might not know about their own brand's positioning)
  3. Suggest next steps:

- Use research-keywords to find SEO keywords based on this brand DNA - Use geo-content-research to build GEO prompt targets - Use improve-aeo-geo to audit their website's AI visibility


Rules

  1. Crawl first, search second — the website is the primary source. Web search fills gaps.
  2. Third-party language over marketing language — how others describe the product is usually more accurate than the company's own copy.
  3. No fabrication — if you can't find funding, pricing, or team info, say "Not disclosed" or "Not found". Never guess.
  4. Be opinionated in Content Gaps — this section is where you add value. Don't just list what's missing; explain why it matters.
  5. One file, complete picture — the brand_dna.md should be self-contained. Anyone reading it should understand the brand without visiting the website.

平台分布

Codex

32.95%
按下载量换算29

Claude

31.83%
按下载量换算28

Cursor

18.93%
按下载量换算16

Gemini CLI

9.2%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills