Data & Analytics for Claude Code

Detect data quality issues, stubs, orphan plugins, duplicate files, and score outliers in the freshie inventory SQLite database using a structured six-check sweep. Use when auditing inventory health after a discovery run or investigating anomalous compliance grades. Trigger with \"scan for anomalies\", \"detect inventory issues\".

Analyzes visitor cohorts, geographic distribution, device/platform mix, and new-vs-returning patterns to identify best audience segments and churn risk. Use when profiling who visits your sites or spotting engagement decline in key cohorts. Trigger with \"analyze my audience\", \"who are my best visitors\".

Use this agent when mapping bead dependencies — finding bottlenecks (open issues blocking the most other open work), detecting dependency cycles, or reasoning about the critical path through a bd Dolt database.

Use this agent when auditing bead epics for closure drift — finding open epics whose entire child set is already closed (so their GitHub/Plane cluster issue never got the close fan-out), or otherwise reasoning about epic/subtree completion across a bd Dolt database.

Monitor cross-chain bridge activity, analyze security models, detect exploits, and compare route fees across Wormhole, Stargate, Hop, and canonical L2 bridges. Use when tracking a pending bridge transfer, assessing TVL risk, or investigating unusual bridge behavior. Trigger with \"monitor bridge\", \"analyze bridge security\".

Parse, classify, redact PII, score reliability, and cluster bug candidates by family and signal layers. Use when processing raw X/Twitter posts into structured bug clusters.

Builds time series forecasting models for demand, revenue, and usage signals. Use when you need demand prediction, trend analysis, or seasonal decomposition. Trigger with \"forecast this time series\", \"build a demand model\".

Analyzes YouTube channels for competitive intelligence — engagement rates, content gaps, and steal-worthy patterns. Use when researching competitor channels or building a content strategy. Trigger with "analyze channels", "competitive channel research".

Designs data validation, cleaning, and quality-monitoring pipelines so models train on trustworthy data. Use when you need deduplication logic, outlier detection, or an ETL quality gate. Trigger with \"audit my data quality\", \"design a cleaning pipeline\".

Analyzes page-level traffic performance, classifies rising and declining content, identifies gaps, and recommends data-backed content strategy from Umami analytics. Use when evaluating which content drives results or deciding what to publish next. Trigger with \"analyze content performance\", \"what should I publish next\".

Analyzes conversion events, funnel stage drop-off rates, and goal completions to quantify where visitors abandon and what the business impact is. Use when diagnosing funnel health or measuring event-driven conversions across sites. Trigger with \"analyze conversion funnel\", \"where are people dropping off\".

Delivers on-chain metrics, tokenomics evaluation, and DeFi protocol analysis to produce ACCUMULATE/HOLD/REDUCE ratings with position sizing guidance. Use when researching a crypto asset or DeFi protocol. Trigger with "analyze this token", "crypto thesis for X".

Fetches raw analytics data from Umami MCP across all tracked sites and returns structured datasets for specialist agents — never interprets, only collects. Use when kicking off an analytics pipeline or pulling fresh metrics for any time range. Trigger with \"collect analytics data\", \"fetch site metrics\".

Use when reviewing data pipelines, numerical/ML code, model training/inference, or analytics correctness — verifies reproducibility and numerical correctness against the scientific and db persona standards.

Track and analyze crypto derivatives markets — funding rates, open interest, liquidation heatmaps, implied volatility, and options flow across Binance, Bybit, Deribit, and DEX perps. Use when researching perpetual positioning, basis-trade opportunities, or options sentiment. Trigger with \"analyze derivatives\", \"funding rates\".

Run a full freshie ecosystem discovery scan via rebuild-inventory.py and report plugin, skill, and pack delta against the previous run stored in the SQLite inventory database. Use when refreshing the inventory after adding plugins or tracking ecosystem growth over time. Trigger with \"run discovery scan\", \"scan the inventory\".

Detects and diagnoses ML model decay in production — data drift, concept drift, and silent degradation. Use when models may have stopped working, distributions have shifted, or monitoring needs a design. Trigger with \"audit my ML monitoring\", \"detect model drift\".

Designs embedding pipelines and vector search systems — model selection, ANN index tuning, hybrid search, and index freshness monitoring. Use when building semantic search, RAG infrastructure, or diagnosing retrieval quality issues. Trigger with \"design embedding pipeline\", \"optimize vector search\".

Produces institutional-quality equity research using fundamental analysis, DCF valuation, and technical analysis to issue Buy/Hold/Sell ratings with price targets. Use when analyzing a stock or building an investment thesis. Trigger with "analyze this stock", "equity research on X".

Designs statistically rigorous experiments — A/B tests, power analysis, variance reduction, and causal inference frameworks. Use when designing an experiment, analyzing test results for validity, or auditing experimentation infrastructure. Trigger with \"design A/B test\", \"review experiment methodology\".

Transforms raw data into model-ready features — leakage audits, encoding strategies, feature stores, and reproducible pipeline design. Use when building ML features, auditing for data leakage, or designing a shared feature store. Trigger with \"build feature pipeline\", \"audit features for leakage\".

Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with \"design training pipeline\", \"tune model hyperparameters\".

Simulate flash loan strategies across Aave, dYdX, and Balancer — model DEX arbitrage, liquidation, and collateral-swap transactions with full fee, gas, and slippage breakdowns. Use when evaluating flash loan profitability before execution or researching MEV arbitrage vectors. Trigger with \"simulate flash loan\", \"flash loan arbitrage\".

Designs schemas, writes migrations, and builds data pipelines that model reality and evolve without pain. Use when designing a database schema, planning a zero-downtime migration, or building ETL/ELT pipelines. Trigger with \"design database schema\", \"write zero-downtime migration\".

Verifies citations and data claims by checking URL accessibility, DOI resolution, source authority, and formatting style consistency across APA, MLA, and Chicago. Use when validating academic content or auditing reference accuracy. Trigger with "check citations", "verify data sources".

Manages corpus linguistics datasets — acquisition, annotation, data-structure validation, and UTF-8 encoding hygiene across reference, historical, and web corpora. Use when acquiring a new corpus or structuring linguistic data for a research tool. Trigger with "set up the corpus", "validate this linguistic dataset".

Designs linguistically-informed interfaces for corpus research tools — KWIC displays, concordance viewers, frequency charts, and genre filters following Swiss Design principles. Use when building or improving a UI for a corpus or NLP tool. Trigger with "design the concordance viewer", "improve the KWIC display".

Audits datasets across five quality dimensions — accuracy, completeness, consistency, timeliness, and schema validity — and flags stale or malformed records against authoritative sources. Use when updating a dataset or when data feels outdated. Trigger with "audit this dataset", "check data freshness".

Analyzes query plans, recommends indexes, and diagnoses N+1 patterns, lock contention, and missing pagination for SQLite and PostgreSQL databases. Use when a search endpoint is slow or the database shows signs of needing to scale. Trigger with "analyze slow queries", "optimize the database".

Coordinates swarm-style parallel data gathering across APIs, websites, and system sources, then aggregates findings into a structured research report. Use when pulling data from multiple sources or validating link collections. Trigger with \"gather data from these APIs\", \"research and synthesize this topic\".

Scores YouTube video ideas against search demand, competition level, trend direction, and audience fit to produce ranked opportunity assessments. Use when deciding which video ideas to prioritize. Trigger with "validate video ideas", "score content ideas".

Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with \"design a dashboard\", \"analyze our funnel\".

Owns the measurement layer — North Star definition, input metrics trees, A/B test specs, funnel and cohort analysis that drive product decisions. Use when defining what to track, diagnosing a funnel, or designing an experiment. Trigger with \"define our North Star metric\", \"design an A/B test\".

Maintains rolling 90-day analytics baselines, learned seasonal patterns, and anomaly history so specialist agents never start cold. Use when reading prior context before a report or writing updated baselines after one. Trigger with \"load analytics context\", \"update analytics baselines\".

Analyze blockchain mempools for MEV opportunities, sandwich attack patterns, pending large transfers, and gas price optimization across Ethereum, BSC, and Arbitrum. Use when detecting front-running risk, profiling pending transactions, or researching block builder behavior. Trigger with \"analyze mempool\", \"detect MEV\".

Design efficient NoSQL data models for MongoDB, DynamoDB, and Cassandra — applying embed-vs-reference, access-pattern-first, sharding key, and index strategies. Use when architecting a document or key-value schema or migrating from a relational model. Trigger with \"design NoSQL schema\", \"model for MongoDB\".

Interpret EXPLAIN plans and query execution metrics to identify bottlenecks — sequential scans, missing indexes, inefficient joins, N+1 patterns — and deliver specific index and rewrite recommendations with expected impact. Use when investigating slow queries or tuning a database under load. Trigger with \"analyze query performance\", \"review EXPLAIN plan\".

Phase 1 of the BigQuery schema optimization pipeline — parses schema export files to count tables and fields, detect naming patterns and type inconsistencies, flag duplicate or nullable issues, and write a markdown analysis report plus strict JSON for phase 2. Use when starting a BigQuery schema audit from raw exports. Trigger with \"run schema phase 1\", \"analyze BigQuery schema\".