hitkeep-ecommerce-analyst
The hitkeep-ecommerce-analyst skill analyzes HitKeep ecommerce and conversion data through aggregate reports, answering questions about revenue, orders, average order value, products, traffic sources, UTM performance, and whether traffic quality changed in revenue terms. Use it when users need insights into conversion funnels, city/provider/ASN breakdowns, or whether traffic changes affected revenue, always maintaining aggregate-only analysis and avoiding customer-level or raw order data requests.
git clone --depth 1 https://github.com/PascaleBeier/hitkeep /tmp/hitkeep-ecommerce-analyst && cp -r /tmp/hitkeep-ecommerce-analyst/skills/hitkeep-ecommerce-analyst ~/.claude/skills/hitkeep-ecommerce-analystSKILL.md
# HitKeep Ecommerce Analyst Use this skill for revenue and conversion questions in HitKeep. ## Scope HitKeep ecommerce MCP output is for aggregate analysis. It can support questions about: - Revenue and order trends. - Product performance. - Source, channel, UTM, city, provider, and ASN aggregates where available. - Whether a traffic change affected revenue quality. - Checkout or conversion context alongside Web Vitals and events. Do not request raw order rows, customer identities, visitor IPs, or raw hit exports through MCP. ## MCP Call Pattern 1. `hitkeep_list_sites` if site scope is unclear. 2. `hitkeep_get_site_overview` for overall traffic and conversion context. 3. `hitkeep_get_ecommerce` for revenue, products, sources, and aggregate context. 4. `hitkeep_get_event_names` and `hitkeep_get_event_breakdown` when checkout, forms, or custom conversion events matter. 5. `hitkeep_get_web_vitals` when page performance could explain conversion movement. 6. `hitkeep_get_ai_visibility` when AI-referred traffic may be part of the acquisition story. 7. `hitkeep_get_mcp_help` when token setup, date range, filter syntax, or MCP privacy boundaries are unclear. Use current and comparison periods. Revenue without a baseline is usually just a number, not an insight. ## Analysis Checks - Split revenue movement into traffic volume, conversion rate, average order value, and product mix. - Check source mix before judging channel quality. - Check product mix before judging campaign quality. - If traffic rose and revenue fell, inspect low-intent sources, bot-like spikes, and product/page mix. - If revenue rose and orders did not, inspect AOV and product mix before claiming more buyers. - Treat city/provider/ASN aggregates as infrastructure and geographic context, not individual identity. ## Output Use: ```markdown Verdict: <what changed in revenue or conversion terms> Evidence: - <revenue/order/AOV comparison> - <source/product/UTM finding> - <traffic/event/performance context> Next: - <1-3 actions> Caveats: - <sample size, attribution limit, missing event, or aggregate-only caveat> ``` If the user asks for customer-level or order-level exports, route to takeout/open exports or the appropriate REST/export path instead of MCP.
Analyze HitKeep AI visibility data: AI crawler fetches, AI-referred visits, assistant names and families, citation yield, resource types, top paths, fetch failures, and Search Console correlation. Use when the user asks about GPTBot, ClaudeBot, ChatGPT, Claude, Perplexity, AI search, AI referrals, crawler access, LLM visibility, or whether AI assistants are discovering and sending traffic to a site.
Official parent skill for analyzing HitKeep data through HitKeep MCP and official docs. Use whenever the user asks an AI assistant to analyze HitKeep traffic, events, ecommerce, Web Vitals, AI visibility, Search Console, opportunities, tracking health, or "Ask AI" style questions; when setting up or validating HitKeep MCP access or help; or when deciding whether to use MCP, the dashboard, REST API, open exports, or takeout. Prefer this spine skill alongside narrower HitKeep analytics skills when they are installed.
Verify HitKeep tracking setup and automatic event collection. Use when the user asks whether HitKeep is installed, whether tracking is live, why pageviews or events are missing, how to validate WordPress or script installs, how automatic outbound click, file download, or form submit events should appear, or how to distinguish tracker setup problems from analytics interpretation problems.
Diagnose HitKeep traffic drops, spikes, source shifts, and suspicious changes. Use when the user asks why traffic changed, whether a deploy hurt traffic, whether organic/search/referral/direct traffic moved, whether a spike is real or bot-like, or what happened to sessions, visitors, pageviews, events, or conversions in HitKeep. Use with HitKeep MCP when available and follow the parent hitkeep-analytics skill when it is also loaded.