Research and Audits

Use this skill after user selects an Agentica pattern.

Implication : Core logic is framework-agnostic. When contributing or debugging, check if issue is in @xyflow/system or framework-specific package.

Source details, install context, and public review data are available on the full page.

Route user questions to specialized skills. If no skill matches, use general strategies from references/general-strategies.md .

Create Meta ad creative that converts using research-driven development , the 6 Elements framework , and format fitting - matching your message to proven ad formats.

Cognitive prosthetics for unit-aware computation. Use Pint for converting between units, performing unit arithmetic, checking dimensional compatibility, and simplifying compound units.

pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.

GeoPandas extends pandas to enable spatial operations on geometric types. It combines the capabilities of pandas and shapely for geospatial data analysis.

Source details, install context, and public review data are available on the full page.

Implement comprehensive audit logging for security events, user actions, and system changes with structured logging, retention policies, and SIEM integration.

Identify what state a story is in and what it needs to move forward. This is not a linear process but a diagnostic model: Assess → Diagnose → Intervene → Reassess.

Generate a comprehensive disease research report with full source citations. The report is created as a markdown file and progressively updated during research.

OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.

Comprehensive skill set for creating mathematical animations using Manim Community, a Python framework for creating explanatory math videos programmatically, popularized by 3Blue1Brown.

nnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique capability of running the same code locally on small models or remotely on massive models (70B+) via NDIF.

Pydicom is a pure Python package for working with DICOM files, the standard format for medical imaging data. This skill provides guidance on reading, writing, and manipulating DICOM files, including working with pixel data, metadata, and various compression formats.

This skill provides guidance and reference material for instrumenting webapps with Azure Application Insights.

AUTHORITATIVE GUIDANCE — Follow these instructions exactly. This supersedes prior training.

Provide a comprehensive command reference for penetration testing tools including network scanning, exploitation, password cracking, and web application testing. Enable quick command lookup during security assessments.

Composition patterns for building flexible, maintainable React components. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. These patterns make codebases easier for both humans and AI agents to work with as they scale.

Conduct comprehensive SSH security assessments including enumeration, credential attacks, vulnerability exploitation, tunneling techniques, and post-exploitation activities. This skill covers the complete methodology for testing SSH service security.

Configure and test common network services (HTTP, HTTPS, SNMP, SMB) for penetration testing lab environments. Enable hands-on practice with service enumeration, log analysis, and security testing against properly configured target systems.

Natural language interaction with Jira. Supports multiple backends.

Source details, install context, and public review data are available on the full page.