Groundwork Help
List all Groundwork skills with descriptions. Usage /groundwork:groundwork-help
Split Specs
This skill should be used when converting a single-file spec to directory-based format for better organization of large specifications
Ux Design
Create design system with foundations, brand identity, and UX patterns. Usage /groundwork:ux-design
Just Do It
Execute all remaining tasks in sequence until completion. Usage /groundwork:just-do-it
Domain Modeling
Use when designing a product or feature and the project lacks shared, agreed terminology - builds and maintains a pure domain glossary so agents speak one language
Design It Twice
Use before committing to a non-trivial module, service boundary, or public API - generate 2-3 divergent interface designs, compare them on depth/locality/seam, and recommend one
Source Architecture From Code
Synchronize architecture document with codebase changes. Usage /groundwork:source-architecture-from-code
Understanding Feature Requests
This skill should be used when clarifying feature requests, gathering requirements, or checking for contradictions in proposed changes
Swarm Debug
Start swarm debugging with parallel hypothesis investigation. Usage /groundwork:swarm-debug [bug description]
Handoff
Use when ending a session or passing work to another agent - produces a compact handoff document that transfers context, state, and next objective without copying source material
Skills
List all available Groundwork skills with descriptions. Usage /groundwork:skills
Swarm Design Architecture
Design architecture using parallel advocate agents for adversarial technology comparison. Usage /groundwork:swarm-design-architecture
Just Do It Swarming
Execute all remaining tasks using agent teams for context isolation. Each task runs in its own session. Usage /groundwork:just-do-it-swarming [--parallel]
Design Product
Create detailed product requirements document (PRD) for a feature. Usage /groundwork:design-product
Implement Task
Dispatches a planned task/feature to the task-executor agent for worktree-isolated TDD implementation
Build Unplanned
Build a feature from description with worktree isolation and TDD. Usage /groundwork:build-unplanned "Add user login
Setup Repo
This skill should be used when configuring a repository for groundwork - detects single-project or monorepo structure and creates .groundwork.yml
Source Ux Design From Code
Synchronize design system document with codebase changes. Usage /groundwork:source-ux-design-from-code
Instrument Observability
Instrument a change with structured logging, RED metrics, trace spans, and symptom-based alerts - use while building the change, not after an incident proves it was unobservable
Work On
skill to "execute a task", "work on task N", or "implement TASK-NNN" - orchestrates worktree isolation, TDD implementation, validation, and merge.
Using Groundwork
This skill should be used when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Source Product Specs From Code
Synchronize PRD with implemented codebase changes. Usage /groundwork:source-product-specs-from-code
Create Tasks
Generate implementation tasks from architecture document. Usage /groundwork:create-tasks
Test Driven Development
This skill should be used when implementing any feature or bugfix, before writing implementation code
Wonk
Structure-aware code search that cuts LLM token burn. Tree-sitter indexing, ranked results, grep-compatible output.
Design Architecture
This skill should be used when the user asks to design system architecture, make architectural decisions, or translate PRD into technical design
Task Validation Loop
This skill should be used when the task list is complete to run multi-agent verification ensuring tasks cover PRD, follow architecture, and respect design system
Check Specs Alignment
Verify alignment between code and specs. Usage /groundwork:check-specs-alignment
Use Git Worktree
This skill should be used when starting feature work that needs isolation from current workspace - creates isolated git worktrees with smart directory selection and safety verification
Ship
Ship a validated change to production - sequences observability and a staged rollout, then gates the outward-facing deploy behind a final go/no-go. Usage /groundwork:ship
Plan Task
Plans a task or feature - loads context, optionally clarifies requirements, spawns Plan agent, persists plan to .groundwork-plans/
Debug
This skill should be used when investigating bugs, unexpected behavior, test failures, or any code that does not work as expected - enforces systematic root cause analysis before any fix
Staged Rollout
Roll out a change in stages behind a feature flag with a monitoring window and a written rollback plan - use before shipping anything user-facing, instead of flipping it on for everyone at once
Vertical Slice
Use when building a feature large enough to span multiple layers - structure the work as thin, end-to-end, independently-shippable slices behind a feature flag instead of building layer-by-layer
Review Pr
Review a GitHub PR using multi-agent verification. Usage /groundwork:review-pr [PR number or URL]. Pass --no-interactive to skip all prompts and auto-publish.
Validate
This skill should be used when implementation is complete to run multi-agent verification with autonomous fix-and-retry until all agents approve
Select Project
This skill should be used when the user wants to switch between projects in a monorepo - lists projects from .groundwork.yml and sets the active project
Doubt Driven Development
Use when building a high-stakes or hard-to-reverse change - schema/data migrations, auth, payments, public API surface, destructive operations, or concurrency - to adversarially refute the chosen approach BEFORE committing to it
Split Architecture
This skill should be used when converting a single-file architecture doc to directory-based format for better organization of large architecture documents
Groundwork Check
Validate the Groundwork plugin for common issues. Usage /groundwork:groundwork-check
Work On Next Task
Execute next uncompleted task with full project context (PRD, architecture, tasks). Usage /groundwork:work-on-next-task