AugmentClaude
MITAnalyticsDashboards

HitKeep Ecommerce Analyst

By PascaleBeier· PascaleBeier/hitkeep· 0

Analyze revenue, orders, and conversion trends from HitKeep ecommerce data.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.
    Install
    Sign up to copy
    Sign up free to reveal

    This copies the whole skill folder into ~/.claude/skills/hitkeep-ecommerce-analyst-pascalebeier/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
    Sign up free to reveal
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Analyze HitKeep ecommerce and conversion data through aggregate reports. Use when the user asks about revenue, orders, average order value, products, sources, ecommerce funnels, conversion changes, city/provider/ASN aggregates, UTM performance, or whether traffic quality changed in revenue terms. Use with HitKeep MCP when available and keep analysis aggregate-only.

What this skill does

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:

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.

Related skills

E

Experiment Designer

mohitagw15856

Design statistically rigorous A/B tests and interpret results with recommendations.

A

Attribution Health Audit

AgriciDaniel

Audit your cross-platform attribution setup for iOS, GA4, consent compliance, and conversion accuracy.

A

Ads Performance Analytics

rampstackco

Interpret paid media dashboards correctly to avoid costly scaling mistakes.

G

Google Ads Scraper

gooseworks-ai

Scrape competitor ads from Google by domain to analyze creatives and campaigns.