Loading...
Loading...
Found 6 Skills
Set up and run Ralph Wiggum loop - autonomous AI coding with clean slate iterations, PRD-driven features, and CI quality gates. Use for long-running autonomous coding tasks.
Bootstrap a Memory Bank for a new or existing repository, then route into PRD-driven or brownfield workflows.
Phased software engineering execution for large refactors, migrations, feature work, testing efforts, and modularization. Executes through strict planning, workspace setup, dependency analysis, PRD-driven parallel implementation, and merge phases. Each subagent runs in an isolated Ralph workspace (CLAUDE.md + prd.json + progress.txt) and executes the Ralph agent loop autonomously. Use when a task needs isolated workspaces, atomic commits, parallel branches, and controlled merge sequencing.
Genera el Technical Design Document + ADRs (formato MADR) + criterios de aceptación de un proyecto, entrevistando al usuario decisión por decisión a partir de su PRD (y opcionalmente su Design.md o un repo existente). Use when the user asks to generate, draft, or create a technical design document, system architecture, or architecture decision records (ADRs) for a project, greenfield or brownfield.
AI-powered task management for structured, specification-driven development. Use this skill when you need to manage complex projects with PRDs, break down tasks into subtasks, track dependencies, and maintain organized development workflows across features and branches.
Use when you need to execute R3 (Prototype Generation) in the product requirement Spec process of sdlc-dev, generate requirements/prototype.md based on requirements/prd.md (including task flow + page structure + ASCII wireframe + AC mapping + walkthrough script), and avoid proceeding with generation without context/PRD, using Open Questions instead of verification checklists, or using non-ASCII formats that make the prototype untraceable and unreviewable.