Skill UI

This CLI alias executes a comprehensive teardown protocol for PUA agents, designed for development environments. It safely releases all active agent and loop states, ensuring a clean system reset. It automatically manages configuration files like ~/.pua/config.json, preserving unknown fields while providing reliable, evidence-based cleanup.

This skill provides comprehensive capabilities for working with Microsoft Word documents (.docx). It supports full document lifecycle management, including text extraction (via pandoc), raw XML manipulation, creating new documents, and complex editing. Specialized workflows are available for redlining, handling tracked changes, managing comments, and preserving intricate formatting, making it ideal for professional, academic, and business document processing.

This utility serves as a Command Line Interface (CLI) alias for specialized AI code models, specifically mapping to the Claude Code `/pua:yes` command structure. It facilitates structured code generation or interaction by adopting a specific 'yes skill' protocol. It ensures that while switching to an encouragement-first narration, the system maintains strict verification red lines and handles configuration file updates while preserving unknown fields. Ideal for developers needing consistent, protocol-driven AI code assistance.

This tool generates a comprehensive, structured, five-section academic paper outline (Abstract, Introduction, Method, Results, Discussion) based on a provided research topic, preference brief, and source references. It ensures the outline contains sufficient substance and integrates multiple citation keys, serving as a robust foundation for a full-length research paper.

This utility takes multiple independently drafted sections of a research paper (Introduction, Method, Results, Discussion) and revises them into a single, highly coherent LaTeX body. It enforces consistency in terminology, metrics, and style, ensuring the final output meets academic standards and required length parameters, all while preserving critical citations and figure placements.

This skill provides a structured, multi-step workflow for resolving conflicts encountered during in-progress Git merges or rebases. It guides users through analyzing conflict origins, preserving original development intents, resolving conflicting code hunks without introducing new behavior, and executing comprehensive automated checks (typechecking, testing, formatting) to ensure the resulting codebase is stable and functional.

This skill provides comprehensive code review capabilities for analyzing git diffs or specific file scopes. It goes beyond simple syntax checks, assessing code for reuse opportunities, quality issues (e.g., redundant state, leaky abstractions), efficiency bottlenecks, and adherence to standards. It utilizes multiple specialized sub-agents (Reuse, Quality, Efficiency, Clarity) to perform parallel, read-only audits. Optionally, it can apply high-confidence, behavior-preserving fixes upon user request.

Specialized skill to rewrite and humanize AI-generated natural language files (like notes or documentation). It removes common 'AI-isms' such as sycophantic openings, stock vocabulary, over-explaining, and excessive signposting. Users can choose between a fast, deterministic regex cleanup or a deep LLM rewrite (default mode) using Claude to enhance burstiness and match a natural human voice, all while strictly preserving code blocks, URLs, and headings.

This skill is designed to mitigate false-positive safety triggers from strict AI classifiers (e.g., cyber, bio/chem, reasoning). It operates by making minimal, surgical edits to sensitive phrases, abstracting away specific domains or actions while preserving the original benign intent and structure. It ensures the prompt remains policy-compliant without losing its core purpose, making it ideal for academic or defensive inquiries.

A comprehensive skill for safely restructuring existing Go codebases. It provides behavior-preserving transforms, such as renaming, extracting functions, moving packages, and applying design patterns, while maintaining a safety net via robust testing and structured, atomic commits. Ideal for large-scale maintenance and improving code structure.

Pattern for controlling LLM API costs while preserving quality. Combines complexity-based model routing, immutable budget tracking, retry logic limited to transient failures, and prompt caching. Use when building LLM API apps, processing batches with varying difficulty, or enforcing budget guardrails in production.

A comprehensive tool for aggregating and displaying system metrics (counters, gauges, histograms) from the observability namespace. It computes baselines and flags anomalies by detecting deviations exceeding standard deviations, providing a clear snapshot of system health, error rates, and performance degradation trends.