Agent Skills Hub

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).

executing-plans

Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.

customer-feedback-analyzer

A framework for collecting, analyzing, and prioritizing user feedback across multiple channels to drive product strategy and feature development.

parallel-agents

Orchestrate complex workflows by coordinating multiple specialized AI agents for multi-perspective code analysis, feature implementation, and system-wide reviews.

documentation-creation

Automated generation of project documentation from codebase analysis, ensuring accuracy, consistency, and alignment with VilnaCRM architecture patterns.

using-superpowers

The foundational skill for the Superpowers methodology. Ensures agents correctly identify and invoke required development skills before starting any task or conversation.

holistic-testing-pact

Apply Holistic Testing with PACT (Proactive, Autonomous, Collaborative, Targeted) principles to build quality into team culture and test strategies for modern software systems.

web-search

Autonomous research specialist for verified information gathering, source evaluation, and structured synthesis.

rust-ownership

Expert Rust analysis for ownership, borrowing, and lifetime errors, including E0382, E0597, and memory safety patterns.

implement-feature

Guide for implementing features using architecture-first design, TDD, rich domain models, and Swift 6.2 patterns, ensuring a clean separation between Domain, Infrastructure, and App layers.

changelog

Automated runtime observability changelog for Claude Code development sessions, tracking file changes, test results, and git commits.

session-intelligence-harvester

Captures session learnings into Reusable Intelligence Infrastructure (RII). Converts one-time bug fixes and pattern discoveries into permanent agent-executable knowledge to prevent recurrence and accelerate future development.