Data Science

Orchestrates comprehensive dependency updates by delegating research, impact analysis, code changes, and validation to specialized agents. Invoked when users request package updates, dependency updates, version bumps, or mention 'ncu' or npm-check-updates.

Expert CISO coaching and mentorship for security leaders in training. Use when the user asks for CISO coach guidance, executive communication advice, security leadership strategies, or needs help translating technical security issues for non-technical audiences. Also activates for discussions about current security events, threat landscape analysis, board-level security topics, risk communication, or security program development from a CISO perspective.

Analyzes dbt model dependencies, traces upstream sources and downstream consumers, identifies circular dependencies, and visualizes data lineage. Use when user asks about model dependencies, wants to understand data flow, needs impact analysis, or wants to trace where data comes from or goes to.

Expert data analyst that explores datasets, performs statistical analysis, identifies patterns, and generates insights from CSV, JSON, and other structured data formats

Autonomous prior art search and analysis agent. Searches multiple databases, analyzes references, creates claim charts, and assesses patentability impact.

Proactively investigates Go SSO codebase to understand authentication flows, trace gRPC request paths, analyze clean architecture patterns, and provide comprehensive backend code insights. Use when users ask about SSO implementation, service structure, database queries, or need to understand how authentication/authorization works.

Psychrometric Analysis Agent

TLA+ formal verification for modeling and verifying concurrent algorithms and distributed systems.Use when asked about: TLA+, formal verification, model checking, verify algorithm, verify spec,check invariants, race condition analysis, concurrency model, TLC, Apalache, formal spec,temporal logic, prove correctness, state machine verification, model concurrent, TOCTOU,double-check locking, create TLA spec, run TLC, explain counterexample, verify safety,liveness property, deadlock detection, formal methods.Capabilities: Create specs from templates, run TLC/Apalache, generate CI pipelines,check code-spec drift, explain counterexamples, generate tests from invariants.

Lightning-fast DataFrame library written in Rust for high-performance data manipulation and analysis. Use when user wants blazing fast data transformations, working with large datasets, lazy evaluation pipelines, or needs better performance than pandas. Ideal for ETL, data wrangling, aggregations, joins, and reading/writing CSV, Parquet, JSON files.

This skill should be used when the user asks to "analyze DBF files", "read DBF data", "query DBF database", "convert DBF to Parquet", "analyze Thai accounting data", "explore legacy database", "run DuckDB queries on DBF", or mentions DBF, Parquet conversion, or Thai legacy accounting systems. Provides comprehensive guidance for reading, converting, and analyzing Thai legacy DBF accounting databases.

Comprehensive skill for CellPhoneDB - Database of cell type markers and cell-cell communication analysis for single-cell data. Use for cell type annotation, ligand-receptor analysis, cell-cell interaction inference, and communication network visualization.

Power spectrum analysis for frequency domain insights and periodicity detection

Configure activity grid heatmaps in drizzle-cube dashboards for GitHub-style contribution visualizations. Use when creating activity grids, heatmaps, contribution calendars, or daily activity patterns.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Analyzes network traffic and exploits protocols. Use when working with PCAP files, Wireshark captures, packet analysis, protocol exploitation, traffic forensics, or data exfiltration detection.

Use when completing implementation, before escalating to human review, or when human checkpoint is reached - performs AI-assisted code review covering security, AI-specific issues, logic errors, and architecture to ensure humans see fresh analysis

Use when building, deploying, or setting up notebooks. Covers Makefile targets (make build, make data, make etl), GitHub Actions workflows, CI/CD, and creating new notebook repositories.

Perform comprehensive risk assessments on OSCAL systems including threat modeling, vulnerability analysis, risk scoring, and POA&M generation. Use this skill to evaluate security posture and prioritize remediation efforts.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Activated when users work with .xlsx, .xlsm, .csv files for spreadsheet operations or data analysis.

Security risk assessment from specifications, manuals, and design documents. Threat modeling (STRIDE/DREAD), asset identification, risk matrix generation, and CRA pre-compliance evaluation. Use for upstream security analysis before implementation. Triggers on: risk assessment, threat modeling, security review, design review, specification analysis, STRIDE, DREAD, attack tree, security requirements, pre-implementation security.