Explore skills

This skill covers 802.11 attack methodologies for red team engagements and wireless security assessments, including monitor-mode setup, WPA/WPA2-PSK/WPA3 attacks, WPA-Enterprise (EAP) attacks, evil twin attacks, captive-portal phishing, KRACK, FragAttacks, and WPS Pi.

This Wi-Fi reconnaissance methodology covers adapter selection, monitor mode and packet injection setup, regulatory domain handling, multi-band airspace mapping, hidden SSID discovery, network fingerprinting, client analysis, and structured data capture for downstream attacks.

Attack methodology for Zigbee, Thread, and Matter mesh protocols, covering IEEE 802.15.4 sniffing, KillerBee toolkit usage, Touchlink commissioning abuse, replay/injection attacks, Zigbee Cluster Library command exploitation, Thread network credential theft, Matter commissioning chain analysis, and 6LoWPAN/IPv6 routing.

Use this skill for creating database schemas or tables in Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. It helps improve the performance of insert-heavy tables.

This skill assists with general PostgreSQL table design, including creating and modifying tables, schemas, and data models. It helps choose data types, constraints, and indexes, and provides best practices for normalization.

This skill analyzes existing PostgreSQL databases to identify tables suitable for conversion to Timescale/TimescaleDB hypertables, helping to find time-series or event tables and evaluate conversion benefits.

This skill is for PostgreSQL database work, covering table design, indexing, data types, constraints, extensions (like pgvector), search, and migrations. It triggers for tasks such as designing tables, choosing data types, or working with pgvector embeddings and semantic search.

Queries video analytics data and metrics from Elasticsearch via the VA-MCP server (port 9901). This skill is used for questions about incidents, alerts, sensor data, object counts, speeds, occupancy, or any recorded events and metrics.

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

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.

Designs data systems, understanding storage engines, replication, partitioning, transactions, and consistency models. It is triggered when discussing database choice, replication lag, partitioning strategies, consistency vs availability, ACID transactions, or choosing between SQL and NoSQL and designing data pipelines.

Open the Token Optimizer dashboard. Collects latest session data, regenerates the dashboard, and opens it in your browser.