Spec-Flow

Execute multiple sprints in parallel based on dependency graph from sprint-plan.md

Build and validate locally for projects without remote deployment (prototypes, experiments, local-only dev)

Execute multi-sprint epic workflow from interactive scoping through deployment with parallel sprint execution and self-improvement

Execute feature development workflow from specification through production deployment with automated quality gates

Analyze workflow state and provide context-aware guidance with visual progress indicators and recommended next steps

Initialize project documentation, preferences, or design tokens

Implement small bug fixes and features (<100 LOC) without full workflow. Use for single-file changes, bug fixes, refactors, and minor enhancements that can be completed in under 30 minutes.

Enter deep craftsman mode - question everything, plan like Da Vinci, craft insanely great solutions, then materialize to roadmap

Display Vercel and Railway deployment quota usage with 24h rolling window analysis, quota reset predictions, and deployment strategy recommendations

Deploy feature through automated staging validation to production with rollback testing

Validate staging deployment before production through automated test review, rollback capability testing, guided manual validation, and optional gap capture for feedback loops

Audit workflow effectiveness and generate improvement recommendations after epic completion

Apply workflow improvements discovered during audit with approval workflow

Display workflow health dashboard with velocity trends, quality metrics, and improvement tracking

Post release announcement to X (Twitter) with GitHub link reply

Expert prompt engineer that creates optimized, XML-structured prompts with intelligent depth selection

Automate complete release workflow for Spec-Flow package (version bump, CHANGELOG, git tag, GitHub release, npm publish)

Initialize and manage parallel AI developer worktrees (Dev Studio). Creates persistent worktrees for concurrent Claude Code agents.

Manage workflow context (handoffs, todos, session status)

Generate project-specific skills, commands, or hooks based on detected patterns from workflow audits

Create Claude Code extensions (prompts, commands, agents, skills, hooks)

Delegate one or more prompts to fresh sub-task contexts with parallel or sequential execution

Diagnose and repair corrupted workflow state. Use when state.yaml is invalid, phases are stuck, or domain-memory.yaml has stale locks.