Agent Skills Hub

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

speckit-workflow

A constitution-driven, spec-first development workflow for Claude Code and Codex, automating feature planning, implementation, and quality assurance through structured agentic loops.

pattern-detection

Analyze and identify codebase patterns (naming, architecture, testing) to maintain consistency and enforce standards during development.

spawn-decision

A specialized decision-making agent for complex architectural choices, task planning, and error resolution within the orchestration system.

sql-queries

Generate optimized SQL queries from natural language. Supports BigQuery, PostgreSQL, MySQL, and Snowflake. Analyze database schemas, interpret business requirements, and output ready-to-run queries with explanations.

scope-options

Plan mode on steroids. Push engineers to think with a product mindset before building with structured intake and concrete technical options.

looped-builder

Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.

lsp-code-analysis

Compiler-accurate semantic code analysis via LSP. Navigate definitions, references, and implementations, perform workspace-wide renames, and get file outlines for Python, Rust, Go, TypeScript/JS, and Java.

orchestrate

Multi-phase feature development workflow for complex tasks using research, planning, implementation, and review gates.

dashboard-design

A structured design and planning tool for Vizro dashboards, enforcing a 3-step workflow (requirements, layout, visualization) to ensure production-ready dashboard development.

getting-started-guide

A structured guide for novelists to navigate the seven-step writing process, from constitution and specification to planning, tasking, drafting, and quality analysis.

requesting-code-review

Enforces code quality by dispatching a dedicated subagent to review work against project plans, requirements, and git commit history before tasks are completed or merged.