Skip to main content
skill CX Codex

exploring-mcp-intent-clusters — Claude Code skill: install & guide

exploring-mcp-intent-clusters analyzes PostHog MCP agent intent clusters to reveal what agents attempt to do, tool failure patterns, and semantic routing competition.

no license 202 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-intent-clusters -a claude-code
Open on GitHub

What exploring-mcp-intent-clusters does

This skill inspects agent actions by grouping free-text $mcp_intent values into semantic goal clusters. Unlike standard call counts, it groups tasks via vector embeddings to highlight the actual objectives behind calls. Because embedding-based grouping cannot run in basic SQL, the skill retrieves precomputed snapshots via posthog:mcp-analytics-intent-clusters-retrieve.

Each cluster entry reveals error percentages, call volumes, and routing entropy. High entropy marks scenarios where agents search aimlessly across multiple tools for a single goal. The tool pivot additionally tracks description fit and tool overlap, pinpointing where vague documentation causes agents to pick competing tools.

When cluster metrics are missing or outdated, posthog:mcp-analytics-intent-clusters-recompute triggers an asynchronous background update. Session summaries are intentionally bypassed during grouping to keep call attribution precise.

What it helps with

  • group agent goals into semantic clusters using vector embeddings
  • locate goal clusters suffering from elevated failure rates
  • detect overlapping tools that agents confuse during execution
  • evaluate whether tool descriptions match agent queries

Example prompts for the agent

  • Group recent agent intents and show which goals fail most often
  • Inspect tool overlap and discoverability using posthog:mcp-analytics-intent-clusters-retrieve
  • Trigger an async clustering snapshot refresh with posthog:mcp-analytics-intent-clusters-recompute

How to install exploring-mcp-intent-clusters

1Skills CLI (Vercel)

npx skills add PostHog/ai-plugin --skill exploring-mcp-intent-clusters -a claude-code

2Manually: put the files in place

~/.claude/skills/exploring-mcp-intent-clusters/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/exploring-mcp-intent-clusters/

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

Questions about exploring-mcp-intent-clusters

How do I install exploring-mcp-intent-clusters in Claude Code?

Run npx skills add PostHog/ai-plugin --skill exploring-mcp-intent-clusters -a claude-code. The skill file is placed at ~/.claude/skills/exploring-mcp-intent-clusters/SKILL.md.

What is the exploring-mcp-intent-clusters skill used for?

It analyzes PostHog MCP telemetry to show what agents are trying to accomplish. You can inspect cluster error rates, discoverability issues, and identify tools that compete for identical user goals.

Why does this analysis rely on stored snapshots instead of SQL queries?

Clustering requires embedding calculations across $mcp_intent values, which cannot be handled in standard SQL. PostHog stores these results as snapshots, which can be regenerated asynchronously when needed.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set82

The whole set →
exploring-replay-vision-observations The exploring-replay-vision-observations skill guides an agent through Replay Vision scanner results, from recurring patterns to individual session recordings. Use it to review findings and decide what to investigate next. CX Codex +1 203installs signals-scout-customer-analytics The signals-scout-customer-analytics skill tracks account-level engagement in PostHog and spots churn-risk or expansion patterns. Use it for recurring customer-health checks. CX Codex +1 203installs exploring-mcp-sessions exploring-mcp-sessions investigates PostHog MCP sessions to inspect tool call sequences, agent intent, and run failures. CX Codex +1 202installs exploring-mcp-tool-quality exploring-mcp-tool-quality reads PostHog MCP analytics to rank tools by failure share, latency and reach, then drills into the ones that break. CX Codex +1 202installs managing-reminders managing-reminders is a Claude Code skill that creates and manages private PostHog reminders with one-time or repeating schedules. It can nudge you about a task or resource. CX Codex +1 202installs signals-scout-apm signals-scout-apm watches OpenTelemetry traces in PostHog for error-rate and latency shifts per service, new error signatures and traffic drops, and files a report only on a confirmed change. CX Codex +1 202installs exploring-mcp-tool-usage exploring-mcp-tool-usage — a routing skill for PostHog MCP analytics: it offers a menu of questions about tool calls, then hands you to the query that answers it. CX Codex +1 200installs checking-deploy-timing checking-deploy-timing tells you when a commit or PR reached prod-us or prod-eu by reading PostHog's hidden deploy annotations and matching them against the merge commit on GitHub. CX Codex +1 200installs

Project sponsors

Companies that keep this analytics open