By marcoskichel
Manage git worktree lifecycles for parallel feature development, batch clean stale worktrees, and generate standardized PR descriptions with structured sections (Why, What changed, Risk, Test plan).
Render the canonical PR description body. Use whenever drafting, writing, updating, refreshing, or regenerating a "PR description", "PR body", "pull request description", "pull request body", "PR summary", "PR template", "GitHub PR body", or any text destined for `gh pr create --body`, `gh pr create --body-file`, `gh pr edit --body`, `gh pr edit --body-file`, or a GitHub PR template. Triggers on phrases like "draft a PR", "write the PR", "summarize this branch for review", "regenerate PR body". MUST be invoked before any `gh pr create --body*` or `gh pr edit --body*` per the empire-git rules. Output is markdown ready to pipe to stdin.
Batch cleanup across MULTIPLE stale worktrees and orphaned branches. Use this when the user wants to tidy up accumulated worktrees, asks about old branches, mentions cleaning up their workspace, says "stale worktrees", "orphan branches", "prune worktrees", "clean up old branches", "purge stale worktrees", or "housekeeping". For finishing ONE specific worktree, use worktree-close instead. Also triggers for `/empire-git:worktree-cleanup [--dry-run] [--days N]`.
Finish work in a SINGLE worktree — push, remove the worktree, and optionally delete the branch. Use this when the user is done with a specific worktree, wants to wrap one up, push and move on, or no longer needs a parallel environment. Triggers on phrases like "close this worktree", "I'm done with this worktree", "wrap up this branch", "push and remove", "tear down this worktree". For batch cleanup of MULTIPLE stale worktrees, use worktree-cleanup instead. Also triggers for `/empire-git:worktree-close [branch] [--push] [--discard] [--force]`.
Answer questions about the worktree toolkit — VSCode integration, gitignore, port offsets, env files, dependency installs, workflow tips. Use when the user asks how worktrees work, "how do I open this in VSCode", "why is .env copied", "what about port collisions", "how do worktrees affect main repo", "worktree workflow", "show me the worktree FAQ", or any question about the setup. Also triggers for `/empire-git:worktree-help [question]`.
Read-only inventory of active worktrees with branch, status, sync state, and staleness info. Use this when the user asks what worktrees exist, "list worktrees", "show my worktrees", "what's in flight", "which branches have worktrees", "stale worktrees", "any forgotten worktrees", or wants a parallel-work overview. Reports state only — never deletes or modifies. For removal use worktree-close (single) or worktree-cleanup (batch). Also triggers for `/empire-git:worktree-list [--stale]`.
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.
Claude Code skills that staff your one-person company.
You're the CEO. You're also QA, support, and the intern who fetches coffee. The skills handle everyone else: a coder, a reviewer, a researcher, a PR scribe, a pitch writer, and a parallel-branch wrangler. Solo on paper. Crewed in practice.
Add the marketplace once:
/plugin marketplace add marcoskichel/empire
Install the full bundle:
/plugin install empire@empire
Or hire individual departments:
/plugin install empire-git@empire
/plugin install empire-dev@empire
/plugin install empire-research@empire
/plugin install empire-product@empire
[!NOTE]
/empire-rules:sync-rulespatches your globalCLAUDE.mdwith opionated instructions on how to work with agents in parallel.
| Plugin | What it does |
|---|---|
empire | Meta bundle. Installs empire-git, empire-dev, empire-research, and empire-product together. |
empire-git | Git workflow: parallel worktree lifecycle (open, close, merge, list, cleanup, help) and canonical pr-description templating. |
empire-dev | Code team-review, engineering diagnostics (shape, weigh, slice), plus 11 bundled dev subagents (generalist review, paradigms, domain experts). |
empire-research | Open-ended explore and closed compare skills with parallel agent dispatch and consolidated reports. |
empire-product | Product comms and intelligence: pitch, vet, recon, mint, distill, probe. Three bundled subagents. |
empire-rules | Utility: /empire-rules:sync-rules reconciles per-plugin routing snippets into the project's AGENTS.md. Auto-installed as a dependency. |
[!TIP] Each plugin README documents its skills and bundled agents in detail, with a per-skill flow diagram. Click any plugin name above for the breakdown.
Plugins that pair well with empire:
superpowers@claude-plugins-official — discipline skills (TDD, debugging, brainstorming, planning, requesting code review). Pairs with empire-git for the commit/PR loop and with empire-dev for review rigor.
/plugin install superpowers@claude-plugins-official
voltagent-lang@voltagent-subagents — language-specialist subagents (TypeScript, Python, Rust, Go, Swift, Kotlin, and more). empire-dev:team-review auto-discovers them and dispatches the right specialist per file when present.
/plugin marketplace add VoltAgent/awesome-claude-code-subagents
/plugin install voltagent-lang@voltagent-subagents
wshobson/agents — curated collection of language and domain specialist subagents. Same role as voltagent-lang; empire-dev:team-review auto-discovers whichever is installed.
/plugin marketplace add wshobson/agents
See CONTRIBUTING.md
MIT
npx claudepluginhub marcoskichel/empire --plugin empire-gitSync hand-authored skill-routing rules from installed empire-* plugins into a target rules file (project AGENTS.md or user-global ~/.claude/CLAUDE.md).
Development collaboration: parallel specialist code review (team-review) plus pre-implementation diagnostics — cognitive audit (probe), requirements (distill), system design (shape), architecture decisions (weigh), task decomposition (slice) — and 11 bundled dev subagents.
Research collaboration: open-ended exploration (explore), closed comparison (compare), hallucination checking (verify), and claim investigation (dissect), with parallel agent dispatch and consolidated reports. Bundles research-analyst as a fallback subagent.
Product intelligence: elevator pitches (pitch), idea pressure-testing (vet), competitor mapping (recon), deck generation (deck), and naming (mint). Bundles three fallback subagents.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.