By etr
Orchestrate feature development with worktree isolation, TDD, and multi-agent validation; plan, implement, review, and deploy with structured workflows for architecture, design, testing, and observability.
Verifies implementation aligns with architecture decisions, component responsibilities, and technology choices. Use after task implementation.
Validates task list follows architecture decisions. Ensures tasks reference correct components, technologies, and patterns.
Validates task list coverage of PRD requirements. Ensures all EARS requirements are addressed by at least one task.
Reviews cloud infrastructure-as-code (Terraform, CloudFormation, CDK, Bicep, ARM, Pulumi, Kubernetes, Dockerfiles) for Well-Architected and provider-specific best practices. Use after task implementation.
Reviews code changes for quality, readability, elegance, and test coverage. Use after task implementation to verify code meets quality standards.
Build a feature from description with worktree isolation and TDD. Usage /groundwork:build-unplanned "Add user login"
Verify alignment between code and specs. Usage /groundwork:check-specs-alignment
Generate implementation tasks from architecture document. Usage /groundwork:create-tasks
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
This skill should be used when the user asks to design system architecture, make architectural decisions, or translate PRD into technical design
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A comprehensive skills library for Claude Code, consolidating proven techniques for planning, design, TDD, debugging, collaboration, and problem-solving.
First, add the Groundwork marketplace:
claude plugin marketplace add https://github.com/etr/groundwork-marketplace
Then install the plugin:
claude plugin install groundwork
claude plugin marketplace update groundwork-marketplace
claude plugin update groundwork
cd ~/.claude/plugins
git clone https://github.com/etr/groundwork.git
Or use the installer provided with the codebase.
Warning: Installation on platforms other than Claude Code is experimental. Skills and agents are automatically transformed to work without Claude Code's plugin system, but some features (hooks, slash commands, skill chaining) may not work identically. Use at your own risk.
Groundwork skills and agents can be installed into other AI coding tools using the included installer script. The installer transforms skill content to remove Claude Code-specific constructs and adapts the format for each target.
| Target | Flag | Description |
|---|---|---|
| Codex CLI | --codex | Agents are installed as native custom-agent TOML files with Codex model and reasoning settings |
| OpenCode | --opencode | Agents are installed as standalone agent files |
| Kiro | --kiro | Agents use JSON config + prompt file pairs |
| Pi | --pi | Agents install as review-prefixed skills, plus a pre-built TypeScript extension (pi-extension/) |
| Claude Code | --claude-code | Recommends the marketplace install (no transformation needed) |
Codex agents are written to .codex/agents/*.toml for project installs (or
~/.codex/agents/*.toml globally). Claude model metadata maps as follows:
| Claude agent model | Codex model override |
|---|---|
sonnet | gpt-5.6-terra |
opus[1m] | gpt-5.6-sol |
inherit or absent | No override; inherit the active Codex model |
Supported effort values (low, medium, high, and max) are preserved as
model_reasoning_effort; an absent effort is omitted. Unsupported model or
effort values stop the install with an explicit error so a silent fallback
cannot select an unintended model.
When installing Codex agents, the installer also removes the exact legacy
.codex/skills/review-<bundled-agent>/SKILL.md file for each bundled Groundwork
agent. It does not use a wildcard: unrelated review-* skills and any sidecar
files are preserved, and an empty legacy directory is removed.
Clone the repository and run the installer:
git clone https://github.com/etr/groundwork.git
cd groundwork
Install globally (available in all projects):
./install-skills.sh --codex --global
Install for the current project only:
./install-skills.sh --opencode --project
You can install to multiple targets at once:
./install-skills.sh --codex --opencode --kiro --global
| Option | Description |
|---|---|
--global | Install to user-level config directory |
--project | Install to current project directory |
--force | Overwrite existing files |
--dry-run | Preview actions without making changes |
--skills-only | Install only skills (skip agents) |
--source DIR | Groundwork source directory (default: auto-detect) |
groundwork- prefix. On OpenCode, skill dependencies are automatically inlined as appendix sections.SessionStart, PreCompact, PostToolUse) are not portable and must be configured manually for each toolRestart Claude Code or start a new session. You should see:
/groundwork:. It should show groundwork skills availablePlay notification sounds and voice announcements when Claude Code stops or needs attention
npx claudepluginhub etr/groundworkRyan's riff on obra/superpowers: strong guidance for Claude Code as a software development assistant
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules)
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses