Skill UI

Guides a structured walkthrough for onboarding into unfamiliar codebases by covering quick overviews, stack detection, directory mapping, pattern spotting, workflow checks, and summary reporting so teams can answer "how does this work" with confidence.

Provides a comprehensive workflow for developing against Customer.io in local or staging environments. It implements environment isolation, dry-run clients, and service mocks to ensure development work does not affect production data, making unit and integration testing safe and reliable.

This skill simulates an expert software engineer and systems analyst. It is designed for deep, evidence-based understanding of complex codebases. Users can ask "how does X work" or request architectural reviews, ensuring every claim is grounded in actual code paths, data flows, and dependency chains, following a rigorous multi-iteration process.

Craft competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC by aligning narratives with agency review criteria, detailing budgets, personnel plans, and broader impacts, and incorporating required AI-generated schematics via the scientific-schematics skill.

Creates concise Architecture Decision Records (ADRs) that capture context, decision, and consequences whenever a significant technical choice has been finalized so future engineers understand why the architecture looks the way it does.

This skill implements a simplified version of the Signal Protocol, focusing on robust end-to-end encryption (E2EE) for messaging applications. It covers critical cryptographic components including X3DH key agreement, the Double Ratchet algorithm for continuous key management, and AES-256-GCM for message encryption. The implementation ensures forward secrecy, meaning that compromising a current key does not reveal past messages. Use this when designing, building, or evaluating the security architecture of a messaging service to guarantee that only communicating parties can read the messages.

A comprehensive guide detailing techniques for detecting and exploiting Blind Server-Side Request Forgery (SSRF). It uses advanced out-of-band (OOB) techniques, such as Burp Collaborator and timing analysis, to interact with internal services, scan private IP ranges, and extract cloud metadata (AWS, GCP, Azure) even when the application does not reflect the server response directly. Essential for web application penetration testing.

This skill is designed for running comprehensive evaluations of Hugging Face Hub models on local hardware. It supports multiple evaluation frameworks, including `inspect-ai` and `lighteval`, and provides flexibility in backend selection (e.g., `vllm`, Transformers, or `accelerate`) to optimize for performance and compatibility. Use this for local GPU benchmarking, smoke testing, and backend selection, but note that it does not handle remote job orchestration or result publishing.

This mode simulates a P9 Tech Lead role, specializing in strategic project management and complex task orchestration. It does not write code itself, but focuses on generating detailed, structured Task Prompts (six elements) and managing the entire workflow delivery from multiple specialized agents (P8 teams). Ideal for coordinating large, complex projects requiring strategic decomposition and coordination of three or more parallel agents.

Generates a concise, AI-optimized specification describing what an existing GitHub Actions workflow does, its triggers, requirements, inputs/outputs, and governance so teams can understand and maintain it without implementation details.

Transforms the AI into a highly personalized virtual tutor, adopting a defined persona, teaching style, and emotional relationship. This skill uses the Socratic method and advanced psychological principles (like Self-Determination Theory and memory scaffolding) to guide users through discovery learning. It doesn't just deliver answers; it fosters genuine engagement, maintains continuity across sessions, and motivates the user to learn by simulating the experience of a caring, challenging human mentor.

This skill is designed to translate vague, colloquial, or descriptive biological details (such as behaviors, appearances, or cultural uses) into precise scientific or common species names. It is essential for constructing effective search queries in biological databases when the question does not use formal taxonomic names. By accurately identifying candidate species names from descriptive clues, users can drastically improve search relevance and accuracy.