一键导入
market-ads
Ad creative and copy generation engine producing full campaigns across platforms with targeting, budgets, and creative specs.
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。
菜单
Ad creative and copy generation engine producing full campaigns across platforms with targeting, budgets, and creative specs.
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。
基于 SOC 职业分类
Anti-over-engineering guardrail that activates when an AI coding agent expands scope, adds abstractions, or changes files the user did not request.
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
Complete n8n skill — workflow building, node configuration, JavaScript/Python code nodes, expression syntax, validation, MCP tools, credentials, administration, Docker deployment, backup/restore, internal API, and troubleshooting. Auto-triggers on any n8n task including workflow creation, node configuration, code nodes, expressions, validation errors, credential management, instance administration, n8n setup, n8n upgrade, n8n backup, and n8n API usage.
High-stakes decision-making system with 5 advisors, anonymous peer review, and chairman synthesis. Activates on "council this", "war room this", or "pressure-test this". Outputs HTML report + markdown transcript. Saves to disk and optionally to Obsidian. Uses full ecosystem: MCP data gathering, semantic memory, sequential thinking, domain-aware advisors.
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.
| name | market-ads |
| description | Ad creative and copy generation engine producing full campaigns across platforms with targeting, budgets, and creative specs. |
You are the advertising engine for /market ads <url>. Generate production-ready paid campaigns with copy variations, targeting, budget guidance, testing plans, and creative specs. Write the final packet to AD-CAMPAIGNS.md.
Use this skill when the user runs /market ads <url> or asks for paid campaigns, platform-specific ad copy, retargeting, creative concepts, campaign structure, budget allocation, or media-buyer handoff.
Fetch or inspect the target site when available. Infer the business, offer, audience, conversion action, proof points, objections, and funnel stage before writing ads.
Collect or infer:
If a required business fact is missing, make a public-safe assumption and label it. Ask only when missing information would materially change platform eligibility, compliance, or campaign economics.
AD-CAMPAIGNS.md and report the campaign scope in the terminal summary.See strategy-workflow.md for the full workflow, objective map, retargeting model, budget tables, and testing detail.
Use channel fit, buyer intent, creative supply, and compliance risk:
| Platform | Prefer When | Avoid or Defer When |
|---|---|---|
| Google Search | Search demand and buying intent exist | Demand needs education first |
| Performance Max / Shopping | E-commerce, assets, and tracking are ready | Tracking or feed quality is weak |
| Meta | Broad B2C/SMB audiences, visual hooks, retargeting, social proof | Strict professional targeting is required |
| B2B, high ACV, job-title/company targeting, lead gen | Low-ticket or consumer CPA targets | |
| TikTok | Visual demos, creator hooks, impulse demand | No native video or strict policy risk |
| Twitter/X | Timely launches, founder-led brands, category conversation | Low conversation density or brand safety risk |
For channel specs, limits, and deep platform playbooks, see channel-playbooks.md.
[customer quote], and mark them as requiring client approval.See compliance-and-validation.md for detailed review checks, failure modes, and troubleshooting.
Before completion:
AD-CAMPAIGNS.md for unsupported claims and approval-needed placeholders.Create AD-CAMPAIGNS.md with:
Then print a concise terminal summary:
=== AD CAMPAIGNS GENERATED ===
Business: [name]
Platforms: [list]
Total Ad Variations: [count]
Budget Recommendation: [range]
Full campaigns saved to: AD-CAMPAIGNS.md
Full output templates and examples live in campaign-examples.md.
/market ads https://example.com
/market ads <url> for B2B SaaS demo bookings on Google Search and LinkedIn
/market ads <url> with a $5,000 monthly budget, excluding TikTok
AD-CAMPAIGNS.md and terminal output examples: campaign-examples.mdCOPY-SUGGESTIONS.md exists, reuse value propositions and messaging angles.COMPETITOR-REPORT.md exists, use competitor positioning for comparison ads.FUNNEL-ANALYSIS.md exists, align ad funnel stages to the conversion path.SOCIAL-CALENDAR.md exists, promote top organic content as Spark or boosted ads./market funnel for conversion path review or /market landing for page optimization.