Install
$ agentstack add skill-etr-groundwork-groundwork-help ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Groundwork Help
Lists all available skills and agents provided by the Groundwork plugin. Every Groundwork capability is a skill, invoked either as /groundwork: or automatically by the model.
Workflow
Step 1: Gather Component Information
Read the plugin manifest and scan directories:
- Read
${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.jsonfor overview - Scan
${CLAUDE_PLUGIN_ROOT}/skills/for available skills (each/SKILL.md) - Scan
${CLAUDE_PLUGIN_ROOT}/agents/for available verification/research agents
Step 2: Extract Descriptions
For 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)- neither → dual (user slash + model auto)
Step 3: Group and Present
Present the skills grouped by purpose. Hide user-invocable: false library skills from the user-facing list (they are internal). Example grouping:
User-invocable skills (/groundwork:)
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 tasks
Task 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 task
Quick Development:
/groundwork:build-unplanned [description]- Build a feature from description with worktree isolation and TDD
Sync & 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 format
Plugin Management:
/groundwork:groundwork-check- Validate plugin health/groundwork:groundwork-help- Show this help/groundwork:skills- List available skills
Debugging:
/groundwork:debug [description]- Systematic root-cause debugging/groundwork:swarm-debug [description]- Parallel adversarial hypothesis investigation
Design & UX:
/groundwork:ux-design- Establish a design system
Hidden library skills
Some 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.
Step 4: Usage Examples
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
Step 5: Additional Resources
Point users to:
README.mdin the plugin root for full documentation- GitHub issues for support
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: etr
- Source: etr/groundwork
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.