Skip to main content
skill CX Codex

exploring-mcp-tool-original-user-motive — Claude Code skill

The exploring-mcp-tool-original-user-motive Claude Code skill builds a taxonomy of the goals users had before reaching an MCP tool. It groups session openings and publishes the categories in a PostHog notebook.

no license 148 installs ★ 101 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add PostHog/ai-plugin --skill exploring-mcp-tool-original-user-motive -a claude-code
Open on GitHub

What exploring-mcp-tool-original-user-motive does

The skill infers why a user started an MCP session from its opening tool calls. It groups similar goals into categories, with counts, shares, and facet breakdowns, then publishes the results as a PostHog notebook.

The agent labels goals by reading sessions in sequence. scripts/extract_facets.py handles mechanical facets, but can reduce a goal to a description of the actions taken. The skill is intended for PostHog staff reviewing their own telemetry; customer-agent access or unattended runs require a real control.

What it helps with

  • identify the goal behind sessions that reach an MCP tool
  • group session-start goals into named categories
  • publish an MCP usage taxonomy in a PostHog notebook

Example prompts for the agent

  • Find out why users start sessions with the workflow MCP tool and publish the categories in a PostHog notebook.
  • Group sessions that call the search MCP tool by their starting goal, and show each category's size and share.
  • Build a taxonomy of starting goals for the analytics MCP tool over the last 90 days.

How to install exploring-mcp-tool-original-user-motive

1Skills CLI (Vercel)

npx skills add PostHog/ai-plugin --skill exploring-mcp-tool-original-user-motive -a claude-code

2Manually: put the files in place

~/.claude/skills/exploring-mcp-tool-original-user-motive/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/exploring-mcp-tool-original-user-motive/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about exploring-mcp-tool-original-user-motive

How do I install exploring-mcp-tool-original-user-motive in Claude Code?

Run npx skills add PostHog/ai-plugin --skill exploring-mcp-tool-original-user-motive -a claude-code. The skill file is at ~/.claude/skills/exploring-mcp-tool-original-user-motive/SKILL.md.

What does exploring-mcp-tool-original-user-motive do?

It infers the goal behind each session from its opening MCP calls, groups those goals, and publishes the taxonomy in a PostHog notebook.

What does exploring-mcp-tool-original-user-motive require?

It queries MCP telemetry in PostHog and is intended for PostHog staff to run with human oversight. It is not intended for customer agents or unattended runs.

Similar skills

SKILL.md skills catalog →

From the same set82

The whole set →
building-canvases The building-canvases Claude Code skill creates and edits standalone PostHog canvas apps. It activates for requests to build, update, or fix one of these apps. CX Codex +1 149installs adding-warehouse-person-properties The adding-warehouse-person-properties Claude Code skill maps columns from a synced warehouse table to PostHog person or group properties. It activates for requests to add warehouse data to profiles or manage an existing mapping. CX Codex +1 148installs scanning-experiments-with-replay-vision The scanning-experiments-with-replay-vision skill for Claude Code sets up a PostHog Replay Vision scanner targeted at an experiment. It watches exposed user recordings and analyzes differences across test variants with an LLM. CX Codex +1 148installs creating-box-plot-insights The creating-box-plot-insights Claude Code skill builds box plot insights in PostHog from product analytics or SQL. It runs on requests to chart a numeric distribution, compare medians, or save an insight. CX Codex +1 148installs context-layer-consolidation The context-layer-consolidation Claude Code skill keeps a context wiki coherent by working through a deterministic lint report queue. It handles the queue before dream publisher creates its branch and commit. CX Codex +1 148installs building-react-quill-canvases building-react-quill-canvases — a Claude Code skill for building PostHog canvases with React and Quill. It activates when building-canvases routes a dashboard, form, or tool request to a React implementation. CX Codex +1 148installs context-layer-dreaming The context-layer-dreaming Claude Code skill turns recent organizational activity into lasting context wiki updates. It runs for nightly or incremental refreshes based on completed work and other activity. CX Codex +1 148installs validating-and-publishing-canvases The validating-and-publishing-canvases skill for Claude Code checks PostHog Canvas source projects and publishes them with version guards. It verifies declared capabilities and handles merge conflicts without data loss. CX Codex +1 148installs

Project sponsors

Companies that keep this analytics open