doing-a-simple-two-sta…
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic…
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
$ npx -y skills add ed3dai/ed3d-plugins --skill finishing-a-development-branch --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/finishing-a-development-branchContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
name: finishing-a-development-branch description: Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup user-invocable: false
Guide completion of development work by presenting clear options and handling chosen workflow.
**Core principle:** Verify tests → Present options → Execute choice → Update project context → Clean up.
**Announce at start:** "I'm using the finishing-a-development-branch skill to complete this work."
**Before presenting options, verify tests pass:**
# Run project's test suite npm test / cargo test / pytest / go test ./...
**If tests fail:**
Tests failing (<N> failures). Must fix before completing: [Show failures] Cannot proceed with merge/PR until tests pass.
Stop. Don't proceed to Step 2.
**If tests pass:** Continue to Step 2.
# Try common base branches git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null
Or ask: "This branch split from main - is that correct?"
Present exactly these 4 options in `AskUserQuestion`.
Implementation complete. What would you like to do? 1. Merge back to <base-branch> locally 2. Push and create a Pull Request 3. Keep the branch as-is (I'll handle it later, or I have more work to do) 4. Discard this work Which option?
**Don't add explanation** - keep options concise.
# Switch to base branch git checkout <base-branch> # Pull latest git pull # Merge feature branch git merge <feature-branch> # Verify tests on merged result <test command> # If tests pass git branch -d <feature-branch>
Then: Update project context (Step 5), then cleanup worktree (Step 6)
# Push branch git push -u origin <feature-branch> # Create PR gh pr create --title "<title>" --body "$(cat <<'EOF' ## Summary <2-3 bullets of what changed> ## Test Plan - [ ] <verification steps> EOF )"
Then: Update project context (Step 5), then cleanup worktree (Step 6)
Report: "Keeping branch <name>. Worktree preserved at <path>."
**Don't cleanup worktree.**
**Confirm first:**
This will permanently delete: - Branch <name> - All commits: <commit-list> - Worktree at <path> Type 'discard' to confirm.
Wait for exact confirmation.
If confirmed:
git checkout <base-branch> git branch -D <feature-branch>
Then: Cleanup worktree (Step 6)
Before merging or creating a PR, invoke `ed3d-extending-claude:project-claude-librarian` to update CLAUDE.md files if contracts or structure changed.
**Do not use nested subagents.** The librarian subagent must inspect the branch directly and must not dispatch additional subagents.
<invoke name="Task"> <parameter name="subagent_type">ed3d-extending-claude:project-claude-librarian</parameter> <parameter name="description">Updating project context for <branch-name></parameter> <parameter name="prompt"> Review what changed in this branch and update CLAUDE.md files if contracts or structure changed. Base branch: <base-branch> Feature branch: <feature-branch> Working directory: <directory> Follow the ed3d-extending-claude:maintaining-project-context skill to: 1. Diff against base branch to see what changed 2. Identify contract/API/structure changes 3. Update affected CLAUDE.md files 4. Commit documentation updates with message: "docs: update project context for <branch-name>" 5. Do not dispatch or invoke any subagents. Report back with what was updated (or that no updates were needed). </parameter> </invoke>
**If librarian commits updates:** Include those commits in the merge/PR. **If librarian reports no updates needed:** Proceed with chosen option. **If librarian subagent is not available:** skip this step, saying aloud that you're skipping it because the `ed3d-extending-claude` plugin is not available.
**Skip this step for Option 4 (Discard).**
**For Options 1, 2, 4:**
Check if in worktree:
git worktree list | grep $(git branch --show-current)
If yes:
git worktree remove <worktree-path>
**For Option 3:** Keep worktree.
**For Options 1, 2, and 3:**
If a human test plan was generated (check `docs/test-plans/`), remind the user:
Human test plan available at: docs/test-plans/<plan-name>.md This documents: - What automated tests cover - What requires human verification - End-to-end scenarios to manually test Review before considering this work fully complete.
**Skip for Option 4 (Discard).**
| Option | Merge | Push | Update Context | Keep Worktree | Cleanup Branch | Test Plan Reminder | |--------|-------|------|----------------|---------------|----------------|-------------------| | 1. Merge locally | ✓ | - | ✓ | - | ✓ | ✓ | | 2. Create PR | - | ✓ | ✓ | ✓ | - | ✓ | | 3. Keep as-is | - | - | - | ✓ | - | ✓ | | 4. Discard | - | - | - | - | ✓ (force) | - |
**Skipping test verification**
**Open-ended questions**
**Automatic worktree cleanup**
**No confirmation for discard**
**Never:**
Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.
Repo: ed3dai/ed3d-plugins
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic…
Use when creating a new Claude Code plugin or setting up plugin structure - provides complete file organization, manifest format, and component definitions for…
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt…
Use when creating, releasing, or maintaining a Claude Code Plugin Marketplace - covers marketplace.json schema, version management, release checklists,…
Use when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale - analyzes what changed,…