Data & Analytics for Claude Code

CodexResearcher Agent Context

Multi-perspective researcher using Google Gemini. Called BY Research skill workflows only. Breaks complex queries into 3-10 variations, launches parallel investigations for comprehensive coverage.

GeminiResearcher Agent Context

Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.

GrokResearcher Agent Context

Ava - Investigative analyst using Perplexity API for web research. Called BY Research skill workflows only. Triple-checks sources, connects disparate information, delivers evidence-based findings with journalistic rigor.

PerplexityResearcher Agent Context

所有专家稿落盘后再启动事实核查员,让它看到完整的专家输出做比对。

Analyzes data flow from source to vulnerability sink, mapping trust boundaries, API contracts, environment protections, and cross-references. Spawned by fp-check during Phase 1 verification.

Post-hoc Analyzer Agent

Post-hoc Analyzer Agent

Post-hoc Analyzer Agent

Post-hoc Analyzer Agent

Use when working on business intelligence, data visualization, and statistical analysis, including SQL, Python, and BI tools to transform raw data into actionable insights, with emphasis on stakeholder communication and business impact.

Use when building scalable data pipelines, ETL/ELT processes, and data infrastructure, including big data technologies and cloud platforms, with emphasis on reliable, efficient, and cost-optimized data platforms.

Use when discovering, collecting, and analyzing diverse data sources, including data mining, statistical analysis, and pattern recognition, with emphasis on extracting meaningful insights from complex datasets to support evidence-based decisions.

Use when working on statistical analysis, machine learning, and business insights, including exploratory data analysis, predictive modeling, and data storytelling, with emphasis on delivering actionable insights that drive business value.

Use when working on high-availability systems, performance optimization, and disaster recovery, including PostgreSQL, MySQL, MongoDB, and Redis, with emphasis on reliability, scalability, and operational excellence.

Use when working on query optimization, performance tuning, and scalability across multiple database systems, including execution plan analysis, index strategies, and system-level optimizations, with emphasis on achieving peak database performance.

Use when working on financial modeling, algorithmic trading, and risk analytics, including statistical methods, derivatives pricing, and high-frequency trading, with emphasis on mathematical rigor, performance optimization, and profitable strategy development.

Use when working on comprehensive information gathering, synthesis, and insight generation, including research methodologies, data analysis, and report creation, with emphasis on delivering actionable intelligence that drives informed decision-making.

Use when working on advanced information retrieval, query optimization, and knowledge discovery, including finding needle-in-haystack information across diverse sources, with emphasis on precision, comprehensiveness, and efficiency.

Use when identifying emerging patterns, forecasting future developments, and strategic foresight, including trend detection, impact analysis, and scenario planning, with emphasis on helping organizations anticipate and adapt to change.

> Analyze and strengthen the knowledge graph in the Obsidian vault by finding missing connections between notes. Use when the user asks about links, relationships, or the vault's knowledge network. Triggers: "connect the notes", "find connections", "link analysis", "improve the graph", "what connections are missing", "network analysis", "strengthen links", "serendipity", "constellation", "bridge notes", "people network", "graph health", "collega le note", "trova connessioni", "migliora il grafo"

> Analyze and strengthen the knowledge graph in the Obsidian vault by finding missing connections between notes. Use when the user asks about links, relationships, or the vault's knowledge network. Triggers: "connect the notes", "find connections", "link analysis", "improve the graph", "what connections are missing", "network analysis", "strengthen links", "serendipity", "constellation", "bridge notes", "people network", "graph health", "collega le note", "trova connessioni", "migliora il grafo"

Specialist for isolated follow-up analyses inside an analysis campaign.

Baseline specialist for attach/import/reproduce/repair work.

Quantitative report auditor. Use PROACTIVELY whenever a Markdown report contains probability claims, EV calculations, pass-rate estimates, MC results, or backtest summaries. Catches probability stacking (1−(1−p)^N vs N×p), conditional-vs-marginal pass-rate confusion, percentage-vs-percentage-points mixups, bootstrap-with-replacement implications, EV-per-eval × N misuse, best-of-N selection bias, and sample-size red flags. Returns a structured P1/P2/P3 severity table.

Researches a single gray area decision and returns a structured comparison table with rationale. Spawned by discuss-phase advisor mode.

Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels and evidence. Spawned by profile orchestration workflows.

Bias-isolated agent that evaluates hypothesis state based on linked evidence across interview analysis files (and future evidence sources). Given a list of hypothesis slugs (or "all"), greps for [[slug]] backlinks, reads the linked statements in context, and recommends status changes. For each hypothesis it also reports what changed since the last assessment and the smallest observable next validation action, and flags one cross-hypothesis top pick. Also synthesizes candidate new hypotheses from

Bias-isolated agent that reads a customer discovery interview transcript (or recollection) and produces a structured interview analysis file — extracted statements with hypothesis backlinks, plus technique feedback. Dispatched by the interviews skill. Does not evaluate hypothesis state or write to hypothesis files.

Use when the user asks about biological pathways, gene functions, metabolic networks, drug targets, enzyme reactions, disease mechanisms, or any KEGG database query. Specializes in pathway enrichment, cross-species comparison, and drug-target investigation.

Cross-platform ad budget optimization — reads Meta + Google Ads data, computes blended ROAS for top-line health plus segmented (brand/non-brand, prospecting/retargeting) ROAS, and recommends specific budget shifts.

Research synthesist specialist for multi-source deep dives -- web search, GitHub, prior art -- synthesized into structured briefings with citations. Use when a task requires wide-net research plus synthesis. Part of the operator-kit five-agent starter kit.

The Rookie of the product team. Junior PM energy. Asks about metrics, users, and the underlying "why" behind every feature. Not contesting, just making the decision explainable.

The Watcher of the product team. Data-minded thinker who sees second-order effects, weird user behaviors, and the metric gaming everyone else missed.

Revenue, billing, and credits analysis agent. Pulls real revenue data from Stripe (SaaS) and RevenueCat (mobile subs), queries AWS Cost Explorer for spend, and cross-references project revenue stages. Returns structured financial snapshot.

General-purpose web research agent. Dispatched by the main agent to research a specific topic — competitor discovery, market analysis, source validation, or any information-gathering task. Returns a structured, source-cited summary. Use when the main agent needs to delegate a focused research task to avoid context bloat.