Data & Analytics

Automatically logs every user prompt and AI output to datewise Notion pages. Use this skill to create a comprehensive archive of all AI interactions, track research progress, maintain conversation history, and build a searchable knowledge base. The skill creates one JSON file per day with all interactions and can export them to Notion in a structured format.

**Versão:** 1.0.0 **Data:** 06/02/2026 **Status:** Implementado e testado ---

Instant orientation skill for the Atlas 330 / atlas_core project. Use this skill at the start of ANY session involving Atlas development, research, scripting, graph work, dataset work, visualization, or philosophical/doctrinal writing. Also trigger when the user mentions: kernel.py, npu_engine, field_state, nakshatra, tithi, graha, devi, raga, corpus, relations, datasets, routes, S-layers, hexfield, toroidal field, Bandhu, sound, jyotisha, wave field, chladni, or any Atlas engine by name. Rea...

CLI para organizar PDFs y libros con metadata generada por IA, búsqueda full-text (SQLite FTS5) y backups a iCloud o S3. Úsala cuando el usuario pida buscar, mostrar, ingestar o respaldar libros/PDFs en su biblioteca wst — por ejemplo "pasame tal libro a mi iPad", "ingestá esta carpeta a mi biblioteca", "mostrame qué libros tengo de Sagan", "hacé backup a iCloud del libro 12".

Runs survival diagnostics and primary hypothesis tests for right-censored time-to-event outcome variables. Produces follow-up time summary, censoring rate assessment, Kaplan-Meier survival curves with number-at-risk tables, log-rank test for group comparison with median survival times and landmark survival rates, and hazard ratio preview from univariate Cox regression. Ends with a recommendation block listing additional analyses available via the full analysis pipeline. Outputs .R and .py scr...

Trajectory diagnostics and primary hypothesis tests for repeated measures / longitudinal designs with a continuous outcome. Produces spaghetti plots with group mean ribbons, ICC, descriptives per time point, attrition check, and one interpreted test: paired t-test for 2 time points, repeated measures ANOVA for 3+ time points in one group, or mixed ANOVA (time x group) for 3+ time points with 2+ groups, including Mauchly sphericity and Greenhouse-Geisser correction. Ends with a recommendation ...

Runs distribution diagnostics and primary hypothesis tests for ordinal outcome variables. Produces frequency tables, cumulative proportions, ordinal bar chart, and one fully interpreted nonparametric group comparison (Mann-Whitney U for 2 groups or Kruskal-Wallis for 3+ groups) with effect sizes (rank-biserial r or Cliff's delta) and Jonckheere-Terpstra trend test. Ends with a recommendation block listing additional analyses available. Outputs .R and .py scripts with 2 publication-quality plo...

Runs class distribution diagnostics and primary association tests for nominal (unordered multi-class) outcome variables. Produces class frequency table, proportions, rare-class warnings, bar chart of class distribution, and one fully interpreted association test (Chi-square/Cramer's V for categorical predictors, or ANOVA/Kruskal-Wallis for continuous predictors) with effect sizes. Ends with a recommendation block listing additional analyses available. Outputs .R and .py scripts with 2 publica...

Runs distribution diagnostics and primary hypothesis tests for count outcome variables (non-negative integers with no upper bound). Produces frequency table, overdispersion assessment, zero-inflation check, bar chart of count distribution with Poisson overlay, and one fully interpreted group comparison (Poisson/NB rate test for 2 groups or Poisson/NB regression with likelihood ratio test for 3+ groups) with incidence rate ratios and nonparametric confirmation. Detects whether data are raw eve...

Runs distribution diagnostics and primary hypothesis tests for continuous outcome variables. Produces Shapiro-Wilk normality check, skewness, kurtosis, Q-Q plot, and one fully interpreted group comparison (Welch's t for 2 groups or ANOVA with Tukey HSD for 3+ groups) with effect sizes and nonparametric confirmation. Ends with a recommendation block listing Outputs .R and .py scripts with 2 publication-quality plots. Triggered when user has a continuous/numeric outcome and says "analyze contin...

Runs class balance diagnostics and primary association tests for binary outcome variables (0/1, yes/no, survived/died, pass/fail). Produces proportion tables, class balance check with rare-event warning, descriptives by outcome level, chi-square test of independence with Cramer's V, Fisher's exact test when cell counts are small, odds ratio with 95% CI, and a mosaic or grouped bar chart. Outputs .R and .py scripts with 2 publication-quality plots. Triggered when user has a binary/dichotomous ...

Validate AI/ML models and datasets for bias, fairness, and ethical concerns. Use when auditing AI systems for ethical compliance, fairness assessment, or bias detection. Trigger with phrases like "evaluate model fairness", "check for bias", or "validate AI ethics".

Fires when the task adds a new data source or changes an existing one (xtb, gold, bond, manual, future: crypto/IKE). Use proactively when user mentions a source name or /source.

Query Google Search Console Search Analytics via the webmasters API. Use when the user asks about search queries, clicks, impressions, CTR, ranking positions, top pages, or month-over-month traffic on their site. Handles OAuth scope + quota project automatically, supports multiple sites via config, and can join page URLs with WordPress post titles for readability.

Detect significant price movements and unusual volume across crypto markets. Calculates significance scores combining price change, volume ratio, and market cap. Use when tracking market movers, finding gainers/losers, or detecting volume spikes. Trigger with phrases like "scan market movers", "top gainers", "biggest losers", "volume spikes", "what's moving", "find pumps", or "market scan".

Use when the user wants a review of currently staged git changes before committing. Triggers on phrases like "review staged", "посмотри что я застейджил", "review before commit", "проверь изменения перед коммитом". Returns a structured findings list focused on correctness, security, and conventions — not style nitpicks.

Query RegulomeDB v2 REST API to score variants for regulatory function and retrieve overlapping evidence (TF binding, histone marks, DNase peaks, eQTLs, motifs). Score single rsID/position, batch lists, region searches, and full annotations. Scores range 1a (strongest: eQTL+TF+DNase+motif) to 7 (none). Use for GWAS hit prioritization, regulatory variant annotation, cis-regulatory discovery. Use clinvar-database for pathogenicity; gwas-database for trait associations.

Audit public sector and government resource allocation systems for budget optimization algorithms (zero-based, incremental, performance-based), service demand forecasting (ARIMA, Prophet, regression), equity-based distribution scoring (CDC SVI, environmental justice indices, disparate impact analysis), GIS geographic coverage and service gap analysis, workload-based staffing models, grant drawdown compliance tracking, and transparency dashboard reporting for municipal, county, and state agenc...

Audit manufacturing predictive maintenance systems for OPC-UA/MQTT sensor data pipelines, time-series storage retention, ML model lifecycle (training-serving skew, drift detection, retraining triggers), MTBF/MTTF/MTTR reliability calculations, Weibull survival analysis, RUL prediction accuracy, alert threshold tuning and false positive management, CMMS/ERP integration, spare parts demand forecasting, and OT/IT security segmentation.

Audit investment portfolio management software for mean-variance optimization, Black-Litterman model, risk parity allocation, VaR/CVaR risk metrics, Brinson performance attribution, tax-loss harvesting rebalancing logic, Sharpe ratio calculations, efficient frontier accuracy, and GIPS-compliant reporting in wealth management and robo-advisor codebases.

Plausible Analytics is a lightweight, open-source, privacy-friendly alternative to Google Analytics. It requires no cookies, is fully GDPR/CCPA/PECR compliant, and provides a clean single-page dashboard with all essential website metrics and traffic insights.

Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies false vs true dependencies, provides sync-free alternatives. Triggers: sync-free, synchronization, .item(), .cpu(), host-device sync, eliminate syncs, CPU stall, non_blocking, set_sync_debug_mode, cudaStreamSynchronize, cudaEventSynchronize, remove syncs, async GPU.

Clinical research outcome extraction for meta-analysis. Use when users need to extract outcome measures (binary, continuous, or survival data) from clinical research papers for systematic review and meta-analysis. Handles both database lookup by PMID and real-time LLM extraction.

'Analyze git repositories to build a security ownership topology (people-to-file), compute