Agent Skills Hub

quality-fixer

Automatically apply safe quality fixes including formatting (Black, isort), linting (Ruff auto-fixes), and resolving formatter conflicts to maintain Python code quality.

convoy

Manage batch work tracking and dispatch with Gas Town's convoy system for multi-agent orchestration.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.

postgresql-table-design

A comprehensive guide for designing high-performance, maintainable PostgreSQL database schemas, covering best practices, data types, indexing, and advanced features.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

nestjs-best-practices

NestJS 11+ expert assistant for enterprise Node.js development, including dependency injection, DTO validation, authentication, ORMs, testing, microservices, and architectural best practices.

cosense

A comprehensive automation skill for Cosense (formerly Scrapbox) enabling page reading, searching, creating, and safe editing via API.

skill-repo

Standardize, validate, and manage Netresearch AI agent skill repositories with automated structure enforcement, distribution workflows, and licensing compliance tools.

ops-devops-platform

DevOps and platform engineering patterns: Kubernetes, Terraform, GitOps, CI/CD, observability, incident response, and cloud-native ops.

litestream

Expert technical support for the Litestream disaster recovery tool, covering WAL monitoring, LTX replication, cloud storage backends, and SQLite page management.

project-manager

Agile project management expert for sprint planning, risk mitigation, and stakeholder alignment in software engineering teams.

dod

Definition of Done (DoD) verification workflow that triggers automatically upon implementation completion to ensure quality, document evidence, and standardize reporting.