Analytics & Monitoring Agent Skills

Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output.

Map LLM visual observations or method-level event results into final video monitoring Event Candidate semantics.

Every Eventbrite organizer endpoint, plus a local SQLite mirror of your events, orders Trigger phrases: `sync my eventbrite events`…

Read-only EVM client: wallets, tokens, gas across 8 chains.

Every ExchangeRate-API endpoint, plus a local rate history, watchlists, drift alerts, and an MCP server no one else...

Use when an empirical analysis should be RUN and audited, not just advised — DiD, IV, RDD, synthetic control, DML, multiple-testing…

Guides developers through Exemplar Marshal (product; package still exemplar-harness-sdk) — AI gateway, prompts, skills, memory, Context…

Calculates probability-weighted averages of all possible outcomes to enable rational decisions under uncertainty.

Minimize the blocking surface of ML and scientific experiment gates.

Use when the credibility of an Experimental Economics (ExpEcon) manuscript rests on experimental control — incentive compatibility…

Use when designing or defending the field-experiment or modelling design of a Field Crops Research (FCR) manuscript — multi-environment…

Use when designing or stress-testing the experiments for a Journal of Consumer Psychology (JCP) manuscript — manipulations, controls and…

Designs, runs, and reads A/B tests and growth experiments — hypothesis, sample size, duration, and honest interpretation.

Audit battery/materials evidence, mechanisms, experimental comparisons, and manuscript claims.

Produce or audit the interpretability/explainability analysis of a medical-imaging model — Grad-CAM / Grad-CAM++ / attention-rollout /…

Extract text from PDFs for LLM consumption.

Use when preparing the accountability artifacts that accompany an ACM FAccT paper — datasheets for datasets, model cards, data statements…

Use when designing or auditing ACM FAccT empirical work — quantitative fairness audits with disaggregated metrics and fair baselines…

Use when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI…

Manage hybrid Famou experiments via famou-ctl: run local evaluators, submit config.yaml tasks, inspect status, manifests, leaderboards…

Use for training the FavCRM AI agent with URLs or pasted text, listing knowledge documents, checking ingestion status, and pruning…