Product Diagnostician — Data & AI agent for Claude Code
Diagnoses product health: builds a metric tree, flags anomalies, scores against stage benchmarks.
How to install Product Diagnostician
Installs to ~/.claude/agents/mariomile-builder-os-product-diagnostician.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mariomile/builder-os/HEAD/agents/product-diagnostician.md -o ~/.claude/agents/mariomile-builder-os-product-diagnostician.md Restart Claude Code, or start a new session, for it to be picked up.
What Product Diagnostician does
name: product-diagnostician description: "Diagnoses product health: builds a metric tree, flags anomalies, scores against stage benchmarks. Works with live analytics, recorded metrics, a codebase, or nothing but the user. Use when diagnosing product health, investigating a metric change, or building a metric tree." model: inherit
Product Diagnostician
You are a senior product analyst. Someone wants to know how the product is doing. Your job is to answer that with the best evidence ac
Alternatives in Data & AI
- Stack Auditor — Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses th 801 ★
- News Sentiment Analyst — Specialized agent for news sentiment analysis of B3 stocks 124 ★
- Book Evaluator — Independent evaluator for the book pipeline 114 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Funnel Diagnostician
Diagnostic inference engine that reads all data sources, builds AARRR funnel model, scores each stage, identif
Growth Architect
Diagnoses activation and retention, locates the bottleneck that matters, and designs ranked interventions agai
Usage Scout
Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage
Benchmark Specialist
Use for benchmark execution, monitoring, and data collection during evaluation runs. Invoked for running tier
Humanize Diagnostician
정밀(strict) 모드 1단계 진단 에이전트. 글 전체를 한 번에 보고 "가장 지배적인 AI 티 패턴 3~6개"를 taxonomy ID와 함께 진단한다. 불안정한 span 열거(0↔18개로 요동)
Advisor SEO Aeo
SEO/AEO expert for Altis — getting paywalled venture research cited by AI answer engines (ChatGPT, Perplexity,
Related Skills
Agentic QA Copilot
Automated call center QA analytics agent — scores every call against a weighted rubric (with emphasis on ident
Navin Engine
Rust-native MCP engine that breaks, diagnoses, repairs, benchmarks, and certifies software changes before they
Aeo Benchmark
Benchmarks AEO performance across multiple URLs or documentation sets. Compares scores, tracks improvements ov