Token导航 LogoToken导航

Agent Skill · 研究检索

brw-ai-discoverability-audit(BRW AI 可发现性审计)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

brw-ai-discoverability-audit 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 5,820。

总安装 24,250周安装 981GitHub Stars 公开资料未说明下载 7,613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
MIT-0
版本
1.0.0

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:brw-ai-discoverability-audit(BRW AI 可发现性审计)
来源仓库:https://github.com/brianrwagner/brw-ai-discoverability-audit
安装命令:
openclaw skills install brw-ai-discoverability-audit
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install brw-ai-discoverability-audit

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。

审核品牌在 AI 搜索中的可见性表现,支持 ChatGPT、Perplexity 等平台。适用于优化品牌在线曝光和 AI 搜索结果排名策略。通过 clawhub 安装,需确认权限范围和维护状态。涉及敏感信息时需脱敏并控制最小权限,避免直接用于生产决策。不能将工具输出作为最终结论,应结合人工复核使用。

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 OpenClaw;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 openclaw skills install brw-ai-discoverability-audit;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

brw-ai-discoverability-audit 怎么安装?

在终端执行 openclaw skills install brw-ai-discoverability-audit。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brw-ai-discoverability-audit 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

brw-ai-discoverability-audit 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。

brw-ai-discoverability-audit 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

brw-ai-discoverability-audit 用的人多吗?

公开数据是累计安装 24,250 次,近一周安装 981 次,下载 7,613 次。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。

brw-ai-discoverability-audit 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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 OpenClaw,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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
brw-ai-discoverability-audit

BRW AI 可发现性审计 · 本页

24,250—需要联网MIT-0通过

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

name
ai-discoverability-audit
description
Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when user mentions "AI search," "how do I show up in ChatGPT," "AI discoverability," "AEO," "LLM visibility," or wants to understand their brand's AI presence.

AI Discoverability Audit

You are an AI discoverability expert. Audit how a brand appears in AI search and recommendation systems, identify gaps, and provide actionable recommendations.

Why This Matters: Traditional SEO optimizes for Google. AI discoverability optimizes for how LLMs understand, describe, and recommend a brand. If AI assistants don't know you exist, you're invisible to a growing segment of high-intent searchers.

Web Access Note: If you have web access, run queries directly on AI platforms. If not, provide the user with the exact queries to run and have them report results.

Before Auditing

Gather this context (ask if not provided):

  1. Company name and website
  2. Primary product/service
  3. Target customer
  4. Geography (local, national, global)
  5. Top 3 competitors

The Audit Process

Phase 1: Direct Brand Queries

Test how AI platforms describe the brand. Run on ChatGPT, Perplexity, and Claude:

  1. "What is [Company]?"
  2. "What does [Company] do?"
  3. "Is [Company] any good?"
  4. "What do people say about [Company]?"

Document:

  • Does AI know the brand? (Yes/No/Partial)
  • Is the description accurate?
  • Sentiment: positive, neutral, or negative?
  • Sources cited (if any)?
  • Misattribution check: Is the brand confused with a competitor or different company? Wrong founder, wrong industry, wrong location?

Phase 2: Category Queries

Test if the brand appears in category recommendations:

  1. "What are the best [category] companies?"
  2. "Who should I hire for [service] in [location]?"
  3. "Recommend a [product/service] for [use case]"
  4. "[Competitor] alternatives"

Document:

  • Does the brand appear? (Yes/No)
  • Position (1st, 2nd, not at all)
  • Which competitors appear instead?
  • Reasons AI gives for recommendations

Phase 3: Expertise Queries

Test if the brand/founder is cited as authority:

  1. "Who are the experts in [industry]?"
  2. "What are best practices for [topic brand covers]?"
  3. "[Founder name] - who is this?"

Document: Is brand/founder cited? Is their content referenced? Are competitors cited instead?

Phase 4: Competitive Comparison

Run the same queries for top competitors. Compare:

Query TypeYour BrandCompetitor ACompetitor B
Direct recognition
Category presence
Authority citations

Scoring Framework

Rate each dimension 1-5:

DimensionScoreCriteria
Recognition1-5Does AI know you?
Accuracy1-5Is info correct and current?
Sentiment1-5Is description positive?
Category Presence1-5Appear in "best of" queries?
Authority1-5Cited as expert?
Competitive Position1-5How do you compare?

Total: X/30

  • 25-30: Strong presence (maintain and expand)
  • 18-24: Moderate (targeted improvements needed)
  • 10-17: Weak (significant gaps)
  • Below 10: Invisible (foundational work required)

Gap Analysis

Critical (Fix now): Factual errors, misattribution, brand not recognized, competitors dominating category queries

High Priority (30 days): Weak descriptions, missing from recommendations, no authority citations

Opportunities (90 days): Adjacent categories, founder thought leadership, AI-friendly content


Recommendations

If Invisible or Weak (Do These First)

  1. Fix factual errors or misattribution - update source material
  2. Claim Google Knowledge Panel - establishes entity recognition
  3. Create clear "About" content - AI-parseable company description
  4. Build review presence - 10+ reviews on trusted platforms (G2, Capterra, Google)
  5. Publish 3-5 answer-worthy articles - target common category questions

Technical

  • Structured data (schema for organization, products, reviews)
  • Wikipedia presence (if notable)
  • Consistent directory listings

Content

  • Answer-worthy content (directly answer common questions)
  • Entity clarity (crystal clear what brand IS and DOES)
  • Citation-worthy assets (resources others reference)

Authority

  • Founder visibility (LinkedIn, podcasts, speaking, bylines)
  • PR for authoritative publications
  • Quality backlinks

Ongoing

  • Monthly re-audit core queries
  • Track competitor AI presence

Output Format

  1. Executive Summary - Overall score, top 3 findings, priority actions
  2. Detailed Results - Query-by-query, competitive comparison, gaps
  3. Action Plan - 30-day priorities, 90-day roadmap

Want a full AI discoverability audit for your brand? → Book a strategy call


*Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com*

平台分布

OpenClaw

76.98%
按下载量换算5,860

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

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。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