Data & Analytics

aibot88 Bundle

Automates REST API security testing using the OWASP ZAP Python SDK. Runs active scans, SQL injection probes, and XSS tests against OpenAPI specs with structured vulnerability reports.

aibot88 Bundle

usql is a universal command-line interface for SQL databases including PostgreSQL, MySQL, SQLite, Oracle, SQL Server, and dozens more. It provides a consistent psql-like experience with syntax highlighting, tab completion, and cross-database copying.

aibot88 Bundle

Take a suspected injectable request, replay it on an authorized target, confirm the finding, and enumerate reachable database actions before manual follow-up.

aibot88 Bundle

Compare checked-in SQL against live MySQL, PostgreSQL, SQLite, or SQL Server schemas and generate a reviewable apply plan before agents touch production databases.

aibot88 Bundle

Move data into PostgreSQL with declarative load files, built-in type conversion, and repeatable migration runs before one-off import scripts become cutover risk.

aibot88 Bundle

Use dogsheep/github-to-sqlite when an agent needs a local, queryable snapshot of GitHub activity instead of bouncing through the web UI or ad hoc API calls. The agent authenticates once, pulls the exact GitHub objects it needs, and leaves behind a SQLite database that can be inspected, joined, diffed, or handed to downstream tools.

frank-luongt Bundle

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

frank-luongt Bundle

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

frank-luongt Skill

<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->

frank-luongt Bundle

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

frank-luongt Bundle

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

frank-luongt Skill

<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->

j4flmao Bundle

Use this skill when building or operating data lakes with Delta Lake, Apache Iceberg, or Apache Hudi. This skill enforces: table format selection, ACID transactions on object storage, time travel, schema evolution, compaction and vacuum, Z-order/Hilbert clustering, incremental queries, CDC with merge-on-read vs copy-on-write. Do NOT use for: legacy Hive-style external tables (no ACID), raw file ingestion without table format, or data warehouse design.

j4flmao Bundle

Use this skill when asked about streaming, Kafka, Flink, Kinesis, stream processing, event stream, real-time, CDC, change data capture, message queue, or stream architecture. This skill enforces: Kafka topic design with partitioning strategy, Flink/ksqlDB stream processing with exactly-once semantics, Schema Registry with Avro/Protobuf, CDC integration with Debezium, and reliability guarantees. Do NOT use for: batch ETL pipelines, API design, or standard message queues (RabbitMQ task queues).

j4flmao Bundle

Use this skill when asked about reverse ETL, Census, Hightouch, Grouparoo, operational analytics, syncing data from warehouse to SaaS, warehosue-to-SaaS, operational data activation, data warehouse as source, sync configs, idempotent syncs, audience export, or data activation. This skill enforces: warehouse-first sync architecture with idempotent writes, incremental and full-refresh sync modes, API rate-limit aware scheduling, and destination-specific deduplication strategies. Do NOT use for: traditional ETL (warehouse as target), streaming CDC, or data ingestion pipelines.

j4flmao Bundle

Use this skill when asked about Apache Arrow, Parquet, Avro, ORC, Arrow Flight, columnar storage, row-oriented storage, compression, schema evolution, data file format, columnar vs row-oriented, file format comparison, or data serialization. This skill enforces: columnar format selection based on access patterns, Parquet row group sizing and encoding optimization, Arrow in-memory format for analytical workloads, Arrow Flight for high-performance data transport, compression codec selection, and schema evolution compatibility. Do NOT use for: streaming data formats (Avro for Kafka), data modeling, or database storage engine design.

j4flmao Bundle

Use this skill when working with Drizzle ORM — schema definition, SQL-like queries, migrations, relations, and edge deployment. This skill enforces: schema-first design, explicit SQL patterns, drizzle-kit for migrations, relational query builder, and connection management. Requires drizzle-orm and drizzle-kit. Do NOT use for: Prisma, TypeORM, Mongoose, or non-Drizzle ORM frameworks.

j4flmao Bundle

Use this skill when analyzing customer journeys: journey mapping, service blueprinting, journey analytics, and journey optimization. This skill enforces: lifecycle stage mapping, touchpoint identification, service blueprint creation, funnel analysis methodology. Do NOT use for: persona development, user research interviews, usability testing, feature prioritization.

j4flmao Bundle

Enforce report generation patterns including PDF generation (Puppeteer, wkhtmltopdf), Excel/CSV export, async generation with queues, report scheduling, large dataset handling, template rendering, and report API design. NOT for real-time dashboards or live charting.

j4flmao Bundle

Use this skill when the user says 'analytics', 'event tracking', 'Firebase Analytics', 'Mixpanel', 'Amplitude', 'app analytics', 'event logging', 'user properties', 'screen tracking', 'funnel analytics', 'user behavior', 'telemetry'. Track events, screen views, and user properties in mobile apps with privacy compliance. Do NOT use for: server-side analytics or web analytics.

j4flmao Bundle

Expertise in product analytics tools (Mixpanel/Amplitude) and User Retention metrics.

j4flmao Skill

Best practices for ETL pipelines using Apache Airflow and dbt.

j4flmao Bundle

Use this skill when planning UX research, user research, usability testing, user interviews, personas, user journeys, information architecture, or card sorting. This skill enforces: method selection (generative vs evaluative), structured interview protocols, usability test plans, persona templates, journey mapping, and synthesis frameworks. Do NOT use for: visual design critiques, A/B test design, or analytics/quantitative analysis.

j4flmao Bundle

Use this skill when designing batch processing with Hive, Spark SQL, Pig, or HQL. This skill enforces: Hive metastore management, Spark SQL Catalyst optimization, file format selection (Parquet, ORC, Avro), partitioning and bucketing strategies, query tuning with statistics and dynamic partition pruning. Do NOT use for: real-time streaming, CDC pipelines, distributed compute framework selection (see data-distributed-compute), or lake table format design.

j4flmao Skill

Best practices for sharding algorithms (Consistent Hashing) and scaling SQL databases.

itsual Skill

Create well-structured, usable Excel spreadsheets (.xlsx) with clear data layout, formulas, formatting, and analysis-ready tables. Use when the user asks for a spreadsheet, Excel file, tracker, model, dashboard data, or .xlsx. Prefer clean data tables over purely visual formatting.

itsual Skill

Establish data governance — ownership, policies, decision rights, and accountability — so data is trusted, compliant, and usable across the organization. Use when designing governance operating models, assigning data owners, or fixing chronic trust and access problems.

j4flmao Bundle

Use this skill when asked about analytics engineering, dbt, data modeling, metrics layer, semantic layer, Cube.js, MetricFlow, dbt metrics, SQL analytics, window functions, CTEs, pivot/unpivot, data modeling for analytics, OBT, dimensional modeling, medallion architecture, bronze/silver/gold, or analytical SQL. This skill enforces: dbt Core (models in SQL/Python, materializations, Jinja/macros, ref/source, tests, docs), metrics layer (dbt Metrics, MetricFlow, Cube.js, semantic layer design, metric definitions, dimensions, filters, time granularity), data modeling for analytics (marts approach, OBT, dimensional modeling, medallion architecture), and SQL for analytics (window functions, CTEs, pivot/unpivot, statistical functions, time series SQL, performance optimization, UDFs). Do NOT use for: general data engineering (use data-engineering skills), statistical analysis (use statistical-analysis skill), or experiment design (use experimentation skill).

itsual Skill

Use people analytics to answer workforce questions with data — turnover, hiring funnel, span of control, engagement drivers — responsibly. Use when building HR metrics, diagnosing people problems, or supporting leadership with workforce insight.

itsual Skill

Design dashboards that help users monitor status, spot exceptions, and take action — not just display charts. Use when creating operational, analytics, or executive dashboard experiences.

itsual Skill

Design clear, usable spreadsheet dashboards that surface key metrics, trends, and status without overwhelming the reader. Use when building KPI trackers, operational dashboards, or executive summary sheets inside Excel / Google Sheets.

ecnu-icalk Skill

使用Python处理包含SNP基因型和表型数据的CSV文件，筛选纯合基因型，计算表型均值并找出每个位点表现最好的基因型。

ecnu-icalk Skill

Генерация SQL-кода для создания таблицы истории и триггеров (INSERT, UPDATE, DELETE), которые фиксируют изменения в таблице подготовки к рейсу, включая время, самолет, тип работ и ответственных лиц.

masharratt Bundle

Pattern Extraction Skill

masharratt Bundle

Retrospective Report Generator Skill

masharratt Bundle

Improvement Recommender Skill