fiatkongen/saurun-marketplace

Autonomously execute tasks from a markdown task list with dependency awareness, blocker detection, and retry logic. Use when the user asks to "work through tasks", "execute pending tasks", "run the task list", "continue with tasks", or wants automated task execution from a markdown file with sections (Pending, In Progress, Completed, Failed).

Use when user wants to ask Codex, get GPT's opinion, get a second opinion from OpenAI, compare perspectives, have Codex review code or docs, or let Codex fix/refactor/implement something.

Use when user wants to deploy/publish a skill to saurun-marketplace, says "deploy [skill] to marketplace", or asks to publish a skill to the plugin marketplace.

Use when a .NET implementation task is complete and needs quality-focused code review, especially test quality validation (behavioral tests, assertion counts, mock boundaries, anti-patterns like getter/setter tests)

Use when breaking a .NET implementation plan into tasks for subagent execution

Use when building .NET backend APIs with business logic, domain rules, invariants to enforce, or projects expanding beyond simple CRUD. Symptoms - anemic models with public setters, domain logic in controllers, AutoMapper bypassing validation, primitives instead of value objects

Use when implementing ASP.NET Core + EF Core features or bugfixes with xUnit tests, before writing implementation code.

Use when you have a spec or requirements for a multi-step .NET backend task, before touching code. Covers task decomposition, test design, and TDD-ready implementation plans.

Execute long-running implementation tasks autonomously. Use when user wants to implement a plan, run autonomous implementation, execute tasks with minimal checkpoints, or do long-run execution.

Use when a React implementation task is complete and needs quality-focused code review, especially test quality validation (behavioral tests, assertion counts, mock boundaries, anti-patterns like getter/className tests)

Use when dispatching a React frontend subagent from an implementation plan — covers TDD with Vitest/RTL/MSW, Zustand stores, and Tailwind v4 component tasks

Use when building React components with Tailwind CSS v4, shadcn/ui, or Radix primitives. Use when writing className strings, cva variants, or arbitrary CSS variable values in Tailwind. Critical for avoiding v3 syntax that silently breaks in v4.

Use when implementing React 19 + Vite + TypeScript features or bugfixes with Vitest + React Testing Library tests, before writing implementation code.

Use when testing marketplace deployment. Simple test skill for validating deploy workflow.

Use when user wants to explore or compare multiple design styles for a web page, or needs visual direction before implementation begins.