Data & Analytics

synthetic-sciences Bundle

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

synthetic-sciences Bundle

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

synthetic-sciences Bundle

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

synthetic-sciences Bundle

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

wyre-ai Bundle

Autotask time entry structure: approval status codes and workflow, the time entry field schema, the billing rate hierarchy, budget and contract-limit validation, utilization analytics, and the MSP business rules for rounding and minimum billing increments.

wyre-ai Skill

PagerDuty Analytics: MTTA/MTTR/MTTE/MTTS definitions, incident and interruption counts, aggregation levels (account, service, team, escalation policy), time-range constraints, and benchmark tables for interpreting the numbers.

ryan-brosas Bundle

Use when porting docmost's realtime collaboration kernel: Redis-synced multi-instance Yjs routing, WS auth ladders, debounced CRDT-to-SQL persistence, and page-tree permissions.

ryan-brosas Bundle

Use when building GEO/AI-visibility tooling: site audits scored 0-100, llms.txt generation, citation checks against answer engines, anti-SSRF fetching, plugin registries, or AI-crawler analytics — port the mined GeoReady (geo-optimizer-skill) contracts.

ryan-brosas Bundle

Use when porting Apache Superset's chart-data acquisition kernel (per-query cache-key composition under security context, cache fault-tolerance ladders, contribution-totals two-phase sync, annotation-data co-caching, cache-timeout precedence, grouping-sets emulation), its chart-data HTTP entry plane (sync/async job gate with identity-carrying submission, opaque-key cache replay with novel-SQL skip, annotation-layer permission gating, override-before-reauthorization, authorize-before-render ordering), or its Alerts & Reports execution plane (crontab-keyed state machine, WORKING concurrency guard, audit-log row promotion, retry/backoff ladder with window anchors, error-notification grace dedup, webhook SSRF peer validation and response containment). Source code and direct tests are ground truth; references carry decisive excerpts and graph retrieval.

ryan-brosas Bundle

Use when porting or debugging privacy-analytics engine internals — ClickHouse query planning with table partitioning and subquery joins, session metric sign arithmetic, timeSlots smearing, goal array-index joins, filter-to-SQL compilation, batched RowBinary ingestion, per-user serialization, comparison-period arithmetic, or tracker engagement protocol.

ryan-brosas Bundle

Use when porting AliasVault's E2E-encrypted vault patterns — SRP wire-format auth, LWW merge-to-SQL core, append-only vault revisions, and zero-knowledge client planes.

ryan-brosas Bundle

Use when building a multi-tenant application or CRM with dynamic schema — upgrade-aware repository proxies and cursor-driven metadata adapters, RLS predicate rewriting, normalized Postgres error taxonomies with duplicate-key diagnostics, workspace DDL managers, SQL identifier escaping, generation-stamped promise memoizers, integer-gap record ordering, metadata-driven upsert engine, tool-facing CRUD validation envelopes, ORM update-event fidelity contracts (id-keyed pairing, authoritative timestamps, snapshot clone discipline), timeline activity routing/coalescing kernel (hash-keyed routing plans, dual-emission junction repoints, sorted advisory-lock funnels), the GraphQL record-filter compiler (bracket-composition walker, where/andWhere first-entry semantics, permission-gated field parsing, depth-capped join-based MANY_TO_ONE sub-filters, composite sub-field flattening, ~18-operator parameterized SQL ladder with randomized param namespacing, null-equivalent widening vs strict eqStrict/isStrictly…

ryan-brosas Bundle

Use when porting Nexus Repository infrastructure contracts: freeze-aware task scheduling over Quartz, thread-scoped transactions with retry/backoff semantics, the capability lifecycle framework for plugin objects, blob-store location/soft-delete/S3 multipart mechanics, JWT-cookie sessions, double-submit CSRF, sandboxed JEXL/CSEL content selectors with parameterized SQL push-down, the repository view handler chain, and the plugin/boot/UI-extension system (descriptors, lifecycle phases, edition selection, script gating, state polling).

ryan-brosas Bundle

Use when building lead-generation/funnel engines: GP-active-learning qualification, count-based query-frontier walks, paid-lookup waterfalls with uncapped backoff, bounded CLI jobs with typed stop reasons, give-to-get data cooperatives, or importer-exact CSV contracts — port the mined OpenOutreach contracts.

ryan-brosas Skill

Use when authoring or reviewing SQL, snake_case naming, uppercase keywords, river-aligned layout, portable DDL types, suffix conventions, and parameterized queries.

vril-labs Bundle

SQL Query Optimization

kernel8901 Bundle

Pinterest API v5 integration. Allows creating and reading pins, managing boards, retrieving profile data and analytics. Use this skill when the user needs to automate Pinterest tasks or access account data.

dojogenesis Skill

Startup CFO who builds models that survive contact with reality. Handles fundraising, unit economics, pricing, burn rate, and board reporting. Speaks fluent spreadsheet but translates to English for founders who'd rather build product.

ricneves-ai Skill

Use quando o usuário pedir para projetar schemas de banco de dados, planejar migrações de dados, otimizar queries, escolher entre SQL e NoSQL, ou modelar relacionamentos de dados.

ricneves-ai Skill

Use ao definir KPIs de produto, construir dashboards de métricas, executar análise de coorte ou retenção, ou interpretar tendências de adoção de funcionalidades em diferentes estágios de produto.

swan-gtm Bundle

Use this skill when a user uploads a CSV or spreadsheet of contacts and wants verified work emails, phone numbers, or professional fields appended at scale. Produces a cleaned input, confirmed field mapping, bounded enrichment run, non-destructive merge, quality report, and export that preserves every original row and value.

swan-gtm Skill

Use this skill to turn LinkedIn Ads engagement into prioritized, pre-drafted outbound. Runs daily to pull LinkedIn Ads analytics, find the companies clicking your ads above a CTR threshold, suppress customers/open-deals/recently-touched accounts, and draft outreach informed by whichever ad themes are landing right now — all saved as drafts for human review, never sent automatically.

mattakushi432 Skill

When to activate: PHP security, SQL injection, PDO prepared statements, mass assignment, CSRF, Blade XSS, password_hash, session fixation, unserialize object injection, file upload validation, Laravel security

mattakushi432 Skill

When to activate: Exposed ORM, Kotlin SQL, DSL query, DAO pattern, Exposed transactions, type-safe queries, database migrations

aeondave Bundle

Auth/lab ref: CLI-centric Windows Wi-Fi scanning tool exposing richer nearby-network data than built-in commands, including RSSI, security details, information elements, 6 GHz Reduced Neighbor Reports, JSON/CSV export.

aeondave Skill

Auth/lab ref: Saleae Logic 2 capture and export workflow: `.sal` traces, raw CSV export, analyzer-table export, and automation API control.

aeondave Bundle

Auth/lab ref: automated SQL injection detection and exploitation tool. For testing web applications for SQLi vulnerabilities to enumerate databases, extract data, read/write files, or escalate to OS shell.

h3y6e Bundle

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.

h3y6e Bundle

Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables, views), or perform basic data ingestion and analysis.

ricneves-ai Skill

Use quando o usuário pede para escrever queries SQL, otimizar desempenho de banco de dados, gerar migrações, explorar esquemas de banco de dados, ou trabalhar com ORMs como Prisma, Drizzle, TypeORM ou SQLAlchemy.

ricneves-ai Skill

Diagnóstico completo de churn para SaaS: identificação de causas, cohort analysis, health scoring de clientes, estratégias de retenção e playbooks de salvamento. Métricas e benchmarks do mercado brasileiro.

ricneves-ai Skill

Skill de cientista de dados sênior de nível mundial especializada em modelagem estatística, design de experimentos, inferência causal e analytics preditivo. Cobre teste A/B (dimensionamento de amostra, testes z de duas proporções, correção de Bonferroni), difference-in-differences, pipelines de feature engineering (Scikit-learn, XGBoost), avaliação de modelo com validação cruzada (AUC-ROC, AUC-PR, SHAP) e rastreamento de experimentos MLflow — usando Python (NumPy, Pandas, Scikit-learn), R e SQL. Use quando projetar ou analisar experimentos controlados, construir e avaliar modelos de classificação ou regressão, realizar análise causal em dados observacionais, fazer feature engineering para datasets tabulares estruturados ou traduzir achados estatísticos em decisões de negócio baseadas em dados.

ricneves-ai Skill

Use quando escrever SQL Snowflake, construir pipelines de dados com Dynamic Tables ou Streams/Tasks, usar funções Cortex AI, criar Cortex Agents, escrever Snowpark Python, configurar dbt para Snowflake ou solucionar problemas de erros Snowflake.

h3y6e Bundle

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

mattakushi432 Skill

When to activate: Rails security, strong parameters, CSRF protect_from_forgery, SQL injection ActiveRecord, XSS raw html_safe, Rails credentials, mass assignment, params.permit, Ruby security

mattakushi432 Skill

When to activate: analytics, GA4, event tracking, custom dimensions, conversion tracking, Plausible, attribution, privacy-first