Skip to content
anyai.fyi

monitor-ai-quality

Skill from amplitude/mcp-marketplace

Agents & Workflows No risky patterns found curated llmanalyticsagentsmcp

Install

npx skills add amplitude/mcp-marketplace --skill monitor-ai-quality

Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.

As a Claude Code plugin

/plugin marketplace add anthropics/claude-plugins-official /plugin install amplitude@amplitude

This skill is part of the plugin “amplitude”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.

What does the monitor-ai-quality skill do?

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.

Description from the SKILL.md in the source repository.

Works with Amplitude

Questions about monitor-ai-quality

What does the monitor-ai-quality skill do?

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.

How do I install monitor-ai-quality?

In a terminal: npx skills add amplitude/mcp-marketplace --skill monitor-ai-quality. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.

Which agents can use monitor-ai-quality?

Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.

Is monitor-ai-quality safe to use?

Our automatic check found no risky patterns (piped shell scripts, hidden characters, secret access, prompt overrides). It is not a full audit – read the SKILL.md and any scripts before installing.

Which tool is monitor-ai-quality for?

monitor-ai-quality comes from the makers of Amplitude and helps your agent work with it.

More skills from amplitude/mcp-marketplace

instrument-events
amplitude/mcp-marketplace

Given event_candidates YAML (output from discover-event-surfaces), generates a concrete instrumentation plan for priority-3 (critical) events.

Data & Databases curated
No risky patterns found
monitor-experiments-consolidated
amplitude/mcp-marketplace

Monitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones.

Development curated
No risky patterns found
manage-amp-context
amplitude/mcp-marketplace

Lists projects for an employee-accessible organization or writes organization/project AI context with `manage_amp_context`; use `get_amplitude_context` for reads.

Other curated
No risky patterns found
live-data-forensics
amplitude/mcp-marketplace

Investigates live product issues against Amplitude data — "is X firing today", "did the release break Y", "which users are affected by Z".

Data & Databases curated
No risky patterns found
investigate-ai-session
amplitude/mcp-marketplace

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.

Agents & Workflows curated
No risky patterns found
discover-opportunities
amplitude/mcp-marketplace

Discovers product opportunities by analyzing Amplitude analytics, experiments, session replays, and customer feedback. Synthesizes evidence into prioritized, actionable opportunities with RICE scoring.

Data & Databases curated
No risky patterns found
discover-analytics-patterns
amplitude/mcp-marketplace

Discovers how analytics tracking calls are actually written in this codebase — the concrete SDK calls, function signatures, and import patterns used to send events.

Data & Databases curated
No risky patterns found
discover-event-surfaces
amplitude/mcp-marketplace

Given a change_brief YAML (output from diff-intake), generates an exhaustive list of candidate analytics events to instrument.

Data & Databases curated
No risky patterns found

Related skills in Agents & Workflows