Skill UI

A mechanism for spawning hierarchical, nested sub-agents up to five levels deep, designed specifically for deep task delegation while managing context limitations. Instead of parallel execution, this ensures that each layer of decomposition receives a fresh context window, preventing the parent agent's context budget from being overwhelmed by complex, multi-step workflows. Ideal for research, verification, and synthesis processes.

This comprehensive API provides a robust solution for automated document workflows. Users can perform format conversions (PDF, DOCX, XLSX, etc.), extract structured data (text, tables), perform OCR on scanned documents, redact sensitive information (PII), add watermarks, and apply digital signatures. Suitable for building automated, secure document processing pipelines.

This tool collects distributed trace spans to build a comprehensive, visual trace tree of an agent's task execution. It allows users to understand the exact flow, timing, and coordination between multiple agents involved in a task. Use it to identify performance bottlenecks, analyze the critical path, and synthesize a detailed narrative summary of complex multi-step workflows.

This tool is designed to manage the process of altering an existing, functional feature to meet a new desired specification. It ensures a structured workflow: first, update the existing test cases to reflect the new behavior; second, modify the underlying implementation to pass these updated tests; finally, complete through review and gated commit. Use this when the feature works but its behavior needs adjustment.

This tool orchestrates the complete workflow for addressing defects, ensuring a robust fix process. It guides the user through reproducing a bug as a failing regression test, applying the necessary fix until the test passes (goes green), and managing the subsequent code review and gated commit phases. Ideal for systems where existing functionality is broken, incorrect, or exhibiting regression.

This engine serves as a shared, comprehensive orchestration layer for the entire development lifecycle (orch-* skills). It defines a rigorous, gated pipeline—including Research, Plan, TDD Implementation, Review, and Commit—ensuring consistency regardless of the specific operation (e.g., feature addition, defect fixing). It also includes a size classifier to accurately scope the required effort and gates for mandatory human review.

This optimizer guides the acceleration of complex, multi-stage processes, such as CI/CD pipelines, large-scale refactoring, or data validation. It instructs users to decompose large tasks into independent execution lanes, build a dependency graph, batch read/check operations, and manage writes with strict isolation to maximize speed without sacrificing correctness. Ideal for optimizing development workflows and testing cycles.

This skill is designed for orchestrating complex, multi-step processes. It helps manage workflows, coordinate different components, and ensure systematic execution of tasks from planning to completion. Ideal for complex automation scenarios and structured project management.

This skill runs a single, simulated tick of a defined business pod (Sales). It is designed for dry-run testing, allowing users to validate inputs, resolve agents, and reserve budgeted resources without invoking real LLM workers. It handles template loading, schema validation, budget management, and emits structured status reports for subsequent workflow consumption.

This skill transforms you into an expert design system guideline author, specializing in creating structured, implementation-ready documentation for the Power brand. It provides a comprehensive workflow covering style foundations (color, typography, spacing), component anatomy, accessibility standards (keyboard-first, high contrast), and quality gates. Use it to ensure all digital products maintain superior aesthetic consistency, usability, and accessibility.

This skill reviews prediction market, basket, oracle, and trading-agent workflows to ensure compliance, safety, data quality, and privacy. It must be run before any workflow handles user portfolio data, venue authentication, API keys, or trade planning to mitigate execution and regulatory risks across multiple domains.

This guide provides a comprehensive workflow for searching and retrieving biomedical literature from PubMed and NCBI. It covers advanced query construction using MeSH terms and specific field tags, advanced filtering (date, publication type), and a repeatable programmatic workflow using NCBI E-utilities (esearch, efetch). Essential for researchers conducting systematic reviews and literature monitoring.