Analytics and metrics agents

randlee/claude-history

Agent Claude Code

Analyze agent execution traces to identify prompt issues, CLI bugs, and missing features with deterministic root cause classification.

ChenChen913/healthfit

Agent

An AI health-data analyst role that examines exercise, nutrition, and health information over time. It produces reports, identifies trends and unusual patterns, tracks milestones, and sends users to medical care when specified warning signs appear.

kimmy-sil/empirical-paper-cc

Agent Claude Code

A read-only data auditor that produces a separate audit report. It performs descriptive statistics and looks for unusual values before data cleaning, or when the user runs /audit.

AndreVianna/aid-methodology

Agent Claude Code

Reads and analyzes code, docs, logs, APIs, and external web sources to produce structured Knowledge Base documents and analysis reports — covering existing-state cataloguing, dependency/integration/convention mapping, telemetry interpretation, security analysis, performance profiling, and web-sourced prior art. Web…

lucafusarbassini/research-automation

Agent

Analyzes experimental results, generates figures and reports.

lucafusarbassini/research-automation

Agent

Runs training experiments, collects metrics, and reports results.

GixGosu/gdd-review-kit

Agent Claude Code

Extracts structured data from review files into a JSON format for visualization. Use in Round 5 before the viz-designer and html-builder.

GixGosu/gdd-review-kit

Agent Claude Code

Reads review data and designs a visualization spec for the interactive HTML report. Use in Round 5 after the data-extractor.

cosdt/PyTorchInsight

Agent

Deep analysis subagent — performs impact assessment, optional code-level analysis, and generates action recommendations for high-value community items.

cosdt/PyTorchInsight

Agent

Primary orchestration agent — parses user input, loads configs, dispatches parallel collectors, fuses data, triggers deep analysis, launches composer, runs quality gate.

Zayne-sprague/Dr-Claude-Code

Agent Claude Code

Post-run output auditor for experiments. Dispatched by harvest-and-report command. Reads the Red Team Brief's validation criteria and a sample of raw outputs. Checks for data quality issues, degenerate outputs, and reward hacking. Returns CLEAN/ANOMALIESFOUND with specific examples.

steven-jzt/MCM-AI-Assistant

Agent Claude Code

A read-only quality check for the modeling stage before delivery. It checks whether the conclusions match the model, the evidence is traceable, the number of models is appropriate, and data exploration is complete.

lehidalgo/codi

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

mikailustuner/OmniRule

Agent

Analytics engineering specialist. Event tracking strategy, PostHog/Mixpanel/Amplitude patterns, data layer design, funnel analysis, A/B test measurement.

lizTheDeveloper/solarpunk_utopia_project

Agent Claude Code

You are an expert-level Business Analyst Agent whose job is to analyze feature specifications and systematically map them to an organization’s value chain and strategic impact.

lehuutrung1412/dotfiles

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

LoganYangBo/rh-trading-agent

Agent Claude Code

Equity fundamental analyst on the trading desk. Use to assess valuation, earnings quality, growth, and balance-sheet health for one or more tickers before a trade decision. Returns a structured fundamental verdict — it does NOT decide trades or place orders.

LoganYangBo/rh-trading-agent

Agent Claude Code

Technical/price-action analyst on the trading desk. Use to read trend, momentum, support/resistance, volatility, and to surface candidates via saved scans. Returns a structured technical verdict with suggested entry/stop reference levels — it does NOT decide trades or place orders.

zm1990s/kb-agent

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

zm1990s/kb-agent

Agent

Evaluate expectations against an execution transcript and outputs.

JansenAnalytics/claudex

Agent

Diagnose production incidents from logs, metrics, and symptom reports. Trace root cause, propose a fix, and write a short post-mortem. Use when a service is broken, throwing errors, or behaving unexpectedly.

zoekdestep/pm-studio

Agent Claude Code

Suggests KPIs, guardrails, and measurement approaches.

taxueseek/skill-optimizer

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

gadenbuie/ds-lab-agent-skills

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.