finishing-a-development-branch
Skill15 starsChanged 5 days agoMITView on GitHub
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
- Commits and pushes
We split this skill into the rules it gives an agent
10 rules. 1 is common, 9 are distinctive, and 0 are very specific to this project.
1
Common
Most of the 172 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 13
Core principle: Verify tests → Present options → Execute choice → Clean up.
- Distinctive: line 37
Stop. Don't proceed to Step 2.
- Distinctive: line 65
Don't add explanation: - keep options concise.
- Distinctive: line 123
Wait for exact confirmation.
- Distinctive: line 125
If confirmed — delete the branch from the canonical checkout, then clean up the worktree:
- Distinctive: line 155
Fix: Always verify tests before offering options
- Distinctive: line 162
Problem: Remove worktree when might need it (Option 2, 3)
- Distinctive: line 163
Fix: Only cleanup for Options 1 and 4
- Distinctive: line 174
Delete work without confirmation
- Distinctive: line 178
Verify tests before offering options
“Common” is measured: kept by at least 6 in 10 of the 172 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Finishing a Development Branch
Overview
Guide completion of development work by presenting clear options and handling chosen workflow.
Core principle: Verify tests → Present options → Execute choice → Clean up.
Announce at start: "I'm using the finishing-a-development-branch skill to complete this work."
The Process
Step 1: Verify Tests
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.
Step 2: Determine Base Branch
# Try common base branches
git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/nullOr ask: "This branch split from main - is that correct?"
Step 3: Present Options
Present exactly these 4 options:
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)
4. Discard this work
Which option?Don't add explanation - keep options concise.
Step 4: Execute Choice
Option 1: Merge Locally
Base-branch work happens in the canonical checkout, not in the session's worktree. If the session is currently in a worktree (see using-git-worktrees), run these from the primary worktree (or session_move back first). You cannot git checkout <base-branch> inside the feature worktree — the base branch is already checked out in the primary worktree, and git refuses to check out the same branch in two worktrees at once.
# In the canonical checkout (primary worktree):
git checkout <base-branch>
git pull
git merge <feature-branch>
<test command> # verify the merged result
git branch -d <feature-branch>Then: move the session back to the canonical checkout (if it was in the worktree), and clean up the worktree (Step 5).
Option 2: Push and Create PR
# 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
)"Report: "PR created. Branch <name> and worktree preserved."
Don't cleanup worktree.
Option 3: Keep As-Is
Report: "Keeping branch <name>. Worktree preserved at <path>."
Don't cleanup worktree.
Option 4: Discard
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 — delete the branch from the canonical checkout, then clean up the worktree:
# In the canonical checkout (primary worktree), NOT the session's worktree:
git branch -D <feature-branch>Then: Cleanup worktree (Step 5).
Step 5: Cleanup Worktree
For Options 1, 4:
Removing a worktree whose session is still inside it is not safe, so do this in two parts:
- If the session is in the worktree, move it back to the canonical checkout first (
session_moveto the primary worktree path — see using-git-worktrees). A worktree that is the active session Location cannot be removed cleanly. - Remove the worktree. For an opencode v2 worktree (created by
worktree_create), use the nativeworktree_removetool with the worktreedirectory.git worktree remove <path>is only for plain-git worktrees that opencode does not record. Never setforceunless the user has confirmed the uncommitted work should be discarded.
Quick Reference
| Option | Merge | Push | Keep Worktree | Cleanup Branch |
| 1. Merge locally | ✓ | - | - | ✓ |
| 2. Create PR | - | ✓ | ✓ | - |
| 3. Keep as-is | - | - | ✓ | - |
| 4. Discard | - | - | - | ✓ (force) |
Common Mistakes
Skipping test verification
- Problem: Merge broken code, create failing PR
- Fix: Always verify tests before offering options
Open-ended questions
- Problem: "What should I do next?" → ambiguous
- Fix: Present exactly 4 structured options
Automatic worktree cleanup
- Problem: Remove worktree when might need it (Option 2, 3)
- Fix: Only cleanup for Options 1 and 4
No confirmation for discard
- Problem: Accidentally delete work
- Fix: Require typed "discard" confirmation
Red Flags
Never:
- Proceed with failing tests
- Merge without verifying tests on result
- Delete work without confirmation
- Force-push without explicit request
Always:
- Verify tests before offering options
- Present exactly 4 options
- Get typed confirmation for Option 4
- Clean up worktree for Options 1 & 4 only
Integration
Called by:
- subagent-driven-development — after the final code review, once all tasks are complete
- executing-plans (Step 7: Hand Off) — after all batches complete
Pairs with:
- using-git-worktrees - Cleans up worktree created by that skill
Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 155
- obra/superpowers★ 305k12% same
- openai/plugins★ 7.4k12% same
- farm-fe/farm★ 5.6k41% same
- pcvelz/superpowers★ 1.3k12% same
- coco-research/coco★ 79771% same
- derHaken/SuperAntigravity★ 43982% same
- koaning/wigglystuff★ 43739% same
- Ibrahim-3d/conductor-orchestrator-superpowers★ 38156% same
- Ibrahim-3d/orchestrator-supaconductor★ 37856% same
- totvs/engpro-advpl-tlpp-skills★ 16682% same
145 more not listed
Wrote their own version · 32
- jnMetaCode/superpowers-zh★ 8.4ksame name
- microsoft/FluidFramework★ 5ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- shibit-net/xuanji-community★ 90same name
- withzombies/hyperpowers★ 80same name
- GEd520/legados★ 75same name
- drvoss/everything-copilot-cli★ 49same name
- RBraga01/a-team★ 24same name
- 5throck/ai-workspace-standards★ 23same name
- PracticalSwan/agent-skills★ 22same name
22 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use chinese-code-review, chinese-commit-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GEd520Skillchinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。
Also in 7 projects that use this
GEd520Skillchinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。
Also in 7 projects that use this
obraSkilldiagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Also in 12 projects that use this
10CGSkillworkflow-runner
十步循环轻量编排器,协调 Phase Skills 执行,支持灵活组合。
Also in 7 projects that use this
MicrosoftSkillroot-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Also in 5 projects that use this
kntismSkillcondition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
Also in 3 projects that use this
- +2 more from GEd520
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- applying-themesSkill
- brainstormingSkill
- building-accessible-interfacesSkill
- building-finetuning-datasetsSkill
- building-mcp-serversSkill
- building-web-artifactsSkill
- coauthoring-docsSkill
- creating-algorithmic-artSkill
- creating-skillsSkill
- designing-canvas-artSkill
- designing-frontend-interfacesSkill
- designing-user-experienceSkill
- dispatching-parallel-agentsSkill
- evolving-apis-and-schemasSkill
- executing-plansSkill
- investigating-performanceSkill
- processing-pdfSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- reviewing-interface-qualitySkill
- reviewing-securitySkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- testing-skillsSkill
- testing-webappsSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verifying-before-completionSkill
- writing-internal-commsSkill
- writing-plansSkill
- writing-release-notesSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

