Investigate AI Session

Deep-dives into specific AI agent sessions or failure patterns to explain why something went wrong. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when investigating a specific session ID, debugging agent failures, understanding why quality is low, tracing tool errors, or when monitor-ai-quality surfaces an issue that needs root cause analysis.

48 stars 12 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add amplitude/mcp-marketplace

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add amplitude/mcp-marketplace --skill investigate-ai-session
Manual install
git clone --depth 1 https://github.com/amplitude/mcp-marketplace.git /tmp/mcp-marketplace
mkdir -p ~/.claude/skills
cp -r /tmp/mcp-marketplace/plugins/amplitude/skills/investigate-ai-session ~/.claude/skills/investigate-ai-session

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Session Investigator

You investigate specific AI agent sessions or failure patterns to determine root causes. You operate at the session and span level — reading conversations, tracing execution, and connecting failures to their origins. This is the "why" skill that follows the "what" from `/monitor-ai-quality`.

## Instructions

### Step 1: Determine Investigation Scope

The user will provide one of:
- **A specific session ID** → go directly to Step 2
- **A failure pattern** (e.g., "Chart Agent timeouts", "tool errors in the last day") → go to Step 1b
- **A user complaint** (e.g., "user X said the agent didn't work") → go to Step 1c
- **A vague signal** (e.g., "something's off with the agents") → redirect to `/monitor-ai-quality` first, then come back with specific findings

#### Step 1b: Find Sessions Matching a Pattern

Call `Amplitude:get_amplitude_agent_analytics_info` with `view: "schema"` to discover valid agent names, tool names, and evaluator fields. Then call it with `view: "sessions"` and supported filters:

- **Agent failures:** `agentNames: ["<agent>"]`, `hasTaskFailure: true`
- **Tool errors:** `toolNames: ["<tool>"]`, `hasTaskFailure: true`
- **Technical failures:** `hasTechnicalFailure: true`
- **Low quality:** fetch recent sessions, then select evaluator quality scores at or below 0.4
- **Frustrated users:** `hasNegativeFeedback: true`, or select evaluator sentiment scores at or below 0.4
- **Expensive sessions:** `minCostUsd: <threshold>`
Read the full skill on GitHub

Details

Skill name
investigate-ai-session
Path
plugins/amplitude/skills/investigate-ai-session/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Investigate AI Session skill do?

Deep-dives into specific AI agent sessions or failure patterns to explain why something went wrong. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when investigating a specific session ID, debugging agent failures, understanding why quality is low, tracing tool errors, or when monitor-ai-quality surfaces an issue that needs root cause analysis.

How do I install the Investigate AI Session skill?

Claude Code plugin: /plugin marketplace add amplitude/mcp-marketplace. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Investigate AI Session popular?

It lives in amplitude/mcp-marketplace, which has 48 GitHub stars and 12 forks.

Related skills

Add Analytics Instrumentation

48

amplitude/mcp-marketplace

End-to-end analytics instrumentation workflow for a PR, branch, file, directory, or feature. Reads the code, discovers what events should be tracked, and produces a concrete instrumentation plan — all in one shot. Use this skill whenever a user wants to add analytics to a PR, asks "instrument this PR", "add tracking to this branch", "what analytics does this file need", "instrument the checkout flow", "run the full instrumentation workflow", or any request that implies going from code changes to a tracking plan. Also trigger when the user gives you a PR link, branch name, file path, or feature

Data & Analytics12

Analyze Account Health

48

amplitude/mcp-marketplace

Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.

Marketing, Sales & Business12

Analyze AI Topics

48

amplitude/mcp-marketplace

Analyzes what users ask AI agents about and how well each topic is served. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when the user asks "what are people asking the AI", "top AI topics", "where is the AI struggling", "AI coverage gaps", "what should we improve in our AI", or wants product insights from AI conversation patterns.

AI, LLMs & Agents12

Iso 42001

33

scytale-labs/GRC-Claude-Skills

Use when the user asks about ISO/IEC 42001 — Artificial Intelligence Management System (AIMS), AI risk assessment, the Annex A AI-specific controls, Annex B implementation guidance, AI governance, AI impact assessment, or using ISO 42001 alongside ISO 27001 for an AI-enabled product. For organizations building, deploying, or governing AI systems.

AI, LLMs & Agents14

Getting Started with Amplitude

48

amplitude/mcp-marketplace

First-run onboarding for the Amplitude Grok data-partner bot. Use when a user starts a new session, asks how to connect Amplitude MCP, needs US vs EU residency help, adding Docs MCP, confirming project access, or choosing what to do first with their existing Amplitude data. Trigger on "get started with Amplitude", "connect Amplitude MCP", "Amplitude bot", "help me use Amplitude in Grok", or "what can this bot do with my Amplitude project". Do not use this skill to lead with setup/instrumentation for brand-new orgs — this bot targets existing Amplitude customers.

AI, LLMs & Agents12

Monitor AI Quality

48

amplitude/mcp-marketplace

Monitors AI agent health across quality, cost, performance, and errors. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when the user asks "how are our AI agents doing", "AI quality check", "agent health", "AI errors", "agent performance", "LLM cost", or wants a proactive health report on their AI/LLM features.

AI, LLMs & Agents12

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.