Browse Skills

Implement user stories with a test-driven development methodology. The agent writes failing tests for acceptance criteria, implements code to pass them, and refactors while maintaining test coverage.

A Scrum master AI agent (Bob) that plans implementation sprints by selecting stories from an epic backlog, defining sprint goals, ordering tasks by dependency, and identifying blockers. Use for structured sprint planning in agent-driven development workflows.

A workflow for solo developers that transforms a project description into a technical specification, implements it in multiple stories with tests, and provides a multi-dimensional code review.

Automates API and end-to-end test generation, regression testing, and quality gate assessment for software projects.

Generates comprehensive project documentation including source tree analysis, onboarding guides, component deep-dives, and Mermaid architecture diagrams. Ideal for quickly creating or maintaining project docs.

Creates comprehensive product briefs by orchestrating market, domain, and technical research using an AI analyst agent. Ideal for product managers and strategists needing structured briefs from research.

Generates comprehensive Product Requirements Documents using Job-to-be-Done framework, includes feature specs, user stories, prioritization, MVP scope, and validation.

Performs multi-dimensional code reviews covering correctness, security, performance, maintainability, and test coverage. Use it during code review phases to identify technical debt and generate actionable recommendations.

Designs comprehensive system architecture, selects technology stacks with justification, creates data models, API contracts, and Architecture Decision Records (ADRs) to validate implementation readiness.

Manage git worktree lifecycle for safe, isolated parallel development. Creates worktrees on feature branches, installs dependencies, merges or cleans up, and preserves failed worktrees.

Automate test suite execution with Vitest and Playwright. Collect pass/fail counts, extract failure details, measure coverage, and identify flaky tests to accelerate debugging and quality assurance.

Formats and emits real-time progress events with timestamps, stage information, and completion percentages for streaming UI consumption. Useful for tracking agentic workflow execution stages.