Token导航 LogoToken导航

Agent Skill · 研究检索

competitor-discovery(竞争对手发现)

competitor-discovery 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。

competitor-discovery 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 73,674 个 Skill 里排第 50,882。

总安装 605周安装 26GitHub Stars 35下载 212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:competitor-discovery(竞争对手发现)
来源仓库:https://github.com/superamped/ai-marketing-skills
仓库路径:skills/competitor-discovery
安装命令:
npx skills add https://github.com/superamped/ai-marketing-skills --skill competitor-discovery
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/superamped/ai-marketing-skills --skill competitor-discovery

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。

当缺乏明确竞品认知时启动探索模式,挖掘潜在替代方案与跨界玩家。运用多维度搜索语法组合突破单一信息源局限获取全景视野。输出带评分权重的候选名单及其差异化特征摘要便于后续筛选。必须清晰描述产品功能与目标人群特征才能有效构建检索表达式。

competitor-discovery 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/competitor-discovery

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/superamped/ai-marketing-skills --skill competi…;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

competitor-discovery 怎么安装?

在终端执行 npx skills add https://github.com/superamped/ai-marketing-skills --skill competitor-discov…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

competitor-discovery 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。

competitor-discovery 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。

competitor-discovery 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。

competitor-discovery 用的人多吗?

公开数据是累计安装 605 次,近一周安装 26 次,下载 212 次,GitHub 35 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。

competitor-discovery 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
competitor-discovery

竞争对手发现 · 本页

60535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

Competitor Discovery

Usage

Use when you don't know who your competitors are, when entering a new market, or when refreshing the competitor list after a pivot or market shift.

Process

Step 1: Gather Inputs

Ask the user for:

  1. Product description — what it does, what category it's in, key features
  2. Target audience — who buys or uses the product (role, industry, company size)
  3. Known competitors (optional) — names or URLs to include without searching
  4. Number to find (optional) — default: 5-7

Step 2: Build Search Queries

Construct 4-6 search queries mixing these angles:

  • Category: "[category] tools 2025 2026" or "[category] software"
  • Alternative: "[product name] alternatives" or "tools like [product name]"
  • Problem: "[primary use case] solution" or "[pain point] tool"
  • Audience: "best [category] for [target company type]" or "[category] for [target role]"
  • Comparison: "best [category] compared" or "top [category] platforms"
  • Review sites: "[category] G2" or "[category] Capterra" (to mine company names from lists)

Tailor queries to the product type. A B2B SaaS product needs different queries than a marketplace or agency service.

Step 3: Search and Collect

Run web searches for each query. For each result:

  • Extract company names and domains that appear across multiple results
  • Pull companies listed on review/comparison sites (G2, Capterra, etc.) — these are strong signals
  • Skip aggregator sites themselves, job boards, news articles about funding, and clearly unrelated results

Compile a candidate list of 8-12 companies. For each, note:

  • Name
  • URL (homepage)
  • How found — which search queries surfaced them

Rank candidates by frequency — companies appearing in 3+ different searches are almost certainly direct competitors.

Step 4: Quick Profile Each Candidate

For each candidate, fetch their homepage (and pricing page if easily accessible) and extract:

  • One-liner — what they say they do, in their own words
  • Target audience signals — who the site speaks to
  • Overlap — how directly they compete (direct / adjacent / tangential)

Classify each candidate:

  • Direct competitor — same problem, same audience, similar solution
  • Adjacent competitor — same audience but different approach, or same approach but different audience
  • Tangential — some overlap but fundamentally different product

Drop tangential candidates unless the list would be too short (fewer than 3 direct competitors).

Step 5: Present for Confirmation

Present the ranked list to the user:

I found these competitors for [product name]:

Direct competitors:
1. [Name] — [one-liner] — [url]
2. [Name] — [one-liner] — [url]
3. [Name] — [one-liner] — [url]

Adjacent competitors:
4. [Name] — [one-liner] — [url]
5. [Name] — [one-liner] — [url]

Should I save these? Any to add or remove?

Wait for user confirmation. They may know competitors that web search missed, or flag false positives.

Output Format

# Competitor Discovery: [Product Name]

**Date:** [current date]
**Competitors found:** [X]

## Competitors

| # | Name | URL | Type | One-Liner |
|---|------|-----|------|-----------|
| 1 | [name] | [url] | Direct | [what they do] |
| 2 | [name] | [url] | Direct | [what they do] |
| 3 | [name] | [url] | Adjacent | [what they do] |

## Search Queries Used
- [query 1] — [X results]
- [query 2] — [X results]

## Recommended Next Steps
- Run competitor-site-analysis on top competitors for full profiles (pricing, moats, GTM signals)
- Run competitor-landscape after 2+ analyses for cross-competitor comparison and positioning map

Rules

  • Never include a company without visiting their site — one-liners must come from their actual homepage.
  • Never guess at pricing — only note what's publicly visible on the homepage or pricing page.
  • Never include more than 7 competitors without user approval — keep the list focused.
  • If web search returns fewer than 3 relevant competitors, the category may be too niche — try broader search terms.
  • If the market appears very crowded (15+ candidates found), suggest focusing on direct competitors only.
  • Re-run every 6 months or after significant product/market changes.

平台分布

Codex

35.97%
按下载量换算76

Claude

27.61%
按下载量换算59

Cursor

17.16%
按下载量换算36

Gemini CLI

9.4%
按下载量换算20

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