菜单
When the user wants to monitor brand mentions, detect trademark infringement, or set up brand monitoring. Also use when the user mentions "brand monitoring," "brand watch," "trademark watch," "brand mentions," "impersonation detection," "counterfeit detection," or "brand abuse monitoring."
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/gengirish/social-media-agency --skill brand-monitoring命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Integrate AgentMail (agentmail.to) for AI-powered email in the Social Media Agency. Use when sending client reports, approval notifications, outreach emails, managing per-org inboxes, handling email replies via webhooks/websockets, or attaching reports. Based on the official AgentMail skill (skills.sh/agentmail-to/agentmail-skills/agentmail).
Orchestrate LLM-powered content generation including post creation, caption writing, hashtag suggestions, content repurposing, image prompts, and performance insights. Use when working with AI content logic, OpenAI/Claude integration, or prompt templates.
Build and maintain the Social Media Agency FastAPI backend with production best practices. Use when creating API endpoints, services, middleware, Pydantic schemas, or backend configuration.
| name | brand-monitoring |
| description | When the user wants to monitor brand mentions, detect trademark infringement, or set up brand monitoring. Also use when the user mentions "brand monitoring," "brand watch," "trademark watch," "brand mentions," "impersonation detection," "counterfeit detection," or "brand abuse monitoring." |
| metadata | {"version":"1.0.0"} |
Guides ongoing brand monitoring—detecting impersonation, trademark infringement, counterfeit products, and brand abuse before they cause harm. Complements brand-protection (reactive: report, takedown); this skill covers proactive monitoring setup and tool selection.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read for brand name, official domain, and key assets.
Identify:
| Channel | Threats |
|---|---|
| Domains | Typosquatting, brand+ai, brand+app, impersonation sites |
| Social media | Fake accounts, impersonation, unauthorized use |
| Marketplaces | Counterfeit products, unauthorized sellers (Amazon, eBay, Temu) |
| Paid search | Competitors bidding on brand terms; impersonator ads |
| App stores | Fake apps, trademark misuse |
| Web | Phishing sites, spoofed pages |
| Method | Frequency |
|---|---|
| Search | Brand name + variants (brand+ai, brand+app, brand+official) |
| Google Alerts | Brand name, product names |
| Social search | X, LinkedIn, Instagram for brand mentions |
| Marketplace search | Amazon, eBay for counterfeit listings |
Tip: Document findings; escalate to brand-protection for takedown when infringement is confirmed.
| Capability | Description |
|---|---|
| AI detection | Machine learning, image recognition, NLP to detect abuse across channels |
| Multi-channel | Domains, social, marketplaces, paid search, dark web |
| Enforcement | Case management, takedown workflows, platform integrations |
| Trademark watch | USPTO, trademark office monitoring; litigation insights |
Vendor types: BrandShield, Tracer Protect, CompuMark, CounterFind—evaluate by coverage, enforcement rate, and budget.
| Level | Cadence | Use |
|---|---|---|
| Basic | Weekly search; Google Alerts | Low-risk; preventive |
| Standard | Daily alerts; monthly marketplace check | Moderate risk |
| Enterprise | Real-time monitoring; dedicated vendor | High-value brand; prior incidents |