Install
$ agentstack add skill-etr-groundwork-skills ✓ 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
Skills Discovery
Dynamically discovers and displays all available Groundwork skills.
What to Do
- Discover all skills by reading SKILL.md files from the plugin's skills directory
- Extract metadata (name, description) from each skill's YAML frontmatter
- Categorize skills based on their names and descriptions
- Display organized output with skill names and descriptions
Discovery Process
Step 1: Find All Skills
Use Glob to find all SKILL.md files:
skills/*/SKILL.md
Step 2: Extract Frontmatter
For each SKILL.md file, extract the name and description fields from the YAML frontmatter at the top of the file.
Step 3: Categorize Skills
Group skills into categories based on keywords in their names/descriptions:
| Category | Keywords | |----------|----------| | Planning & Design | plan, design, product, architecture, task | | Testing & Verification | test, verify, validation, tdd | | Maintenance & Sync | sync, alignment, check, verify | | Meta | using |
If a skill doesn't match any category, place it in "Other".
Step 4: Display Output
Format the output as:
# Groundwork Skills
## [Category Name]
| Skill | Description |
|-------|-------------|
| `skill-name` | First sentence of description |
[Repeat for each category with skills]
---
**Total:** X skills available
## Usage
Invoke a skill using the Skill tool or slash command:
- `Skill: skill-name`
- `/groundwork:skill-name` (unless the skill is `user-invocable: false`)
## Discovery
Run `/help` to see all available slash commands.
Example Output
# Groundwork Skills
## Planning & Design
| Skill | Description |
|-------|-------------|
| `design-product` | Use when defining product requirements |
| `design-architecture` | Use when designing technical approach |
| `create-tasks` | Use when generating implementation tasks |
## Testing & Debugging
| Skill | Description |
|-------|-------------|
| `test-driven-development` | Use when implementing any feature |
---
**Total:** 32 skills available
## Discovery
Run `/help` to see all available slash commands.
Notes
- Skills are discovered dynamically - new skills appear automatically
- Descriptions are truncated to the first sentence for readability
- Personal skills from
~/.claude/skills/are also discovered if present
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.