From groundwork
Lists all available Groundwork skills and agents with descriptions, grouped by purpose, showing invocation methods (user slash vs model auto).
How this skill is triggered — by the user, by Claude, or both
Slash command
/groundwork:groundwork-helpThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Lists all available skills and agents provided by the Groundwork plugin. Every Groundwork
Lists all available skills and agents provided by the Groundwork plugin. Every Groundwork
capability is a skill, invoked either as /groundwork:<name> or automatically by the model.
Read the plugin manifest and scan directories:
${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json for overview${CLAUDE_PLUGIN_ROOT}/skills/ for available skills (each <name>/SKILL.md)${CLAUDE_PLUGIN_ROOT}/agents/ for available verification/research agentsFor each skill, extract the name and description from the SKILL.md YAML frontmatter. Note its
invocation tier from the frontmatter:
disable-model-invocation: true → user-only slash workflowuser-invocable: false → hidden library skill (model/other-skill use only)Present the skills grouped by purpose. Hide user-invocable: false library skills from the
user-facing list (they are internal). Example grouping:
/groundwork:<name>)List skills organized by purpose:
Spec-Driven Development:
/groundwork:design-product - Define product requirements/groundwork:design-architecture - Design technical approach/groundwork:create-tasks - Generate implementation tasksTask Execution:
/groundwork:work-on [N] - Work on a specific task by number/groundwork:work-on-next-task - Work on the next task/groundwork:plan-task [N or description] - Plan a task or feature without implementing/groundwork:implement-task [N or plan-path] - Implement a previously planned taskQuick Development:
/groundwork:build-unplanned [description] - Build a feature from description with worktree isolation and TDDSync & Alignment:
/groundwork:source-product-specs-from-code - Sync specs with code changes/groundwork:source-architecture-from-code - Update architecture docs/groundwork:check-specs-alignment - Verify spec alignment (full audit)/groundwork:split-specs - Convert single-file PRD into directory format/groundwork:split-architecture - Convert single-file architecture doc into directory formatPlugin Management:
/groundwork:groundwork-check - Validate plugin health/groundwork:groundwork-help - Show this help/groundwork:skills - List available skillsDebugging:
/groundwork:debug [description] - Systematic root-cause debugging/groundwork:swarm-debug [description] - Parallel adversarial hypothesis investigationDesign & UX:
/groundwork:ux-design - Establish a design systemSome skills (e.g. test-driven-development, understanding-feature-requests,
use-git-worktree, using-groundwork, task-validation-loop) are user-invocable: false:
they are not on the slash menu and are invoked only by other skills or by the model. Use
/groundwork:skills to see the full list of skills.
Provide usage examples:
/groundwork:design-product # Start defining a new product
/groundwork:design-architecture # Design the technical approach
/groundwork:create-tasks # Generate implementation tasks
/groundwork:work-on-next-task # Work on the next task
/groundwork:groundwork-check # Check plugin health
Point users to:
README.md in the plugin root for full documentationnpx claudepluginhub etr/groundworkDiscovers and lists all available Groundwork skills by reading SKILL.md files, extracting frontmatter metadata, and displaying them organized by category.
Lists all available skills in Director Mode Lite: core (code-reviewer, test-runner), workflow (/workflow, /test-first), utility (/project-init, /skill-check), templates (/skill-template), and custom creation guide. Use to discover invocable skills.
Loads skills efficiently using a 3-layer progressive disclosure system: lightweight index always loaded, summaries on demand, full skills only during execution to minimize token usage.