finishing-a-development-branch
Skill4 starsChanged 3 months agoApache-2.0View on GitHub
Finish a development branch — commit, verify, push, open PR. PR is the only path. Load when implementation is complete and tests pass. Triggers: \"finish this branch\", \"wrap up\", \"open a PR\".
- Commits and pushes
187 other projects use a version of this.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- chrysogonus/power-agentstheir own version, first seen Nov 8, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
- lhbsaa/apex-unifiedtheir own version, first seen Nov 8, 2026
Used with
Projects 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.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
Leodorareluctant259Skillchinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 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 20 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
MicrosoftSkilltesting-anti-patterns
Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies
Also in 4 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
- +3 more from Leodorareluctant259
Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 187
- obra/superpowers★ 314ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- microsoft/FluidFramework★ 4.9ksame name
- lingyired/status-trio★ 1.8ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
- DemonDamon/AgenticX★ 1ksame name
- coco-research/coco★ 797same name
177 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.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 12-factor-appSkill
- caveman-commitSkill
- caveman-reviewSkill
- cavemanSkill
- conventional-commitsSkill
- creating-pull-requestsSkill
- deep-researchSkill
- dispatching-parallel-agentsSkill
- domain-modelingSkill
- forge-cleanupSkill
- forge-docsSkill
- forge-eu-accessibilitySkill
- forge-flowSkill
- forge-initSkill
- forge-seoSkill
- forge-setupSkill
- forgeSkill
- forge-tailwindcss-conventionsSkill
- frontend-designSkill
- git-issue-trackerSkill
- grillingSkill
- kiss-principleSkill
- loopsSkill
- planning-and-task-breakdownSkill
- prototypeSkill
- pr-resolveSkill
- pr-reviewSkill
- resolving-merge-conflictsSkill
- ste100Skill
- subagent-driven-developmentSkill
- use-git-identitySkill
- using-git-worktreesSkill
- verification-before-completionSkill
- wayfinderSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 173 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Leading word: done when: Every step ends on a checkable criterion.
- Distinctive: line 30
Commit list (SHA + subject, one per line)
- Distinctive: line 31
Test status (command run, pass/fail)
- Very specific: line 40
Run the full suite. If tests fail, report failures and stop — everything below comes after a green suite.
- Distinctive: line 74
After all branches merged, run full suite on the merged result.
“Common” is measured: kept by at least 6 in 10 of the 173 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
Pick the variant that matches your role:
| Role | Variant |
| Subagent in an assigned worktree | Subagent Variant — commit, verify, report |
| Coordinator after swarm completes | Coordinator Variant — push + open PR |
| Solo work, no swarm | Coordinator Variant, single branch |
Leading word: done when. Every step ends on a checkable criterion.
Hard rule: NEVER merge to main/master. Main receives changes only via pull request.
Subagent Variant
You run inside a worktree the coordinator assigned. You do not merge, push, or present options.
- Commit all work. Stage everything; use
caveman-commit+conventional-commits. - Verify a clean tree.
git statusmust show nothing to commit, working tree clean. - Run the test suite.
npm test/cargo test/pytest/go test ./.... If tests fail, fix or report verbatim — do not claim completion on a red suite. - Report these four items:
- Branch name
- Commit list (SHA + subject, one per line)
- Test status (command run, pass/fail)
- One-paragraph summary of what changed and why
Done when: the four-item report is delivered. Commits already live in the shared object store — the coordinator handles the rest.
Coordinator Variant
1. Verify tests
Run the full suite. If tests fail, report failures and stop — everything below comes after a green suite. Load verification-before-completion — "tests passed earlier" is not evidence.
Done when: suite is green on the tree you're about to integrate.
2. Detect environment
GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
WORKTREE_PATH=$(git rev-parse --show-toplevel)| State | Meaning |
GIT_DIR == GIT_COMMON | Normal repo, no worktree cleanup needed |
GIT_DIR != GIT_COMMON, named branch | Worktree — cleanup is provenance-based (Step 5) |
GIT_DIR != GIT_COMMON, detached HEAD | Externally managed — leave in place |
3. Confirm base branch
The base is whatever the forked work split from — integration branch for swarm work. If unknown, ask: "This branch split from <best guess> — correct?" Confirm before merging.
4. Merge each subagent branch
For each branch a subagent reported (cross-reference subagent-driven-development):
MAIN_ROOT=$(git -C "$(git rev-parse --git-common-dir)/.." rev-parse --show-toplevel)
cd "$MAIN_ROOT"
git checkout <integration-branch>
git merge --squash <task-branch>
git commit -m "<conventional-commit>"After all branches merged, run full suite on the merged result. Red: stop, leave everything in place, investigate (nothing pushed, local + recoverable).
If merge conflicts occur during merge, load resolving-merge-conflicts — it handles steps 1–3, and for multi-branch conflicts delegates to subagent-driven-development to unblock in parallel.
5. Push and create PR
git push -u origin <integration-branch> (detached: git push origin HEAD:refs/heads/<new>), follow creating-pull-requests. Keep worktrees for PR feedback.
Done when: PR URL returned, AI disclosure in place, worktrees preserved for PR feedback.
6. Cleanup workspaces
Runs only if work is discarded (explicit request). All other paths preserve worktrees.
GIT_DIR == GIT_COMMON: nothing to clean..worktrees/orworktrees/:git worktree remove "$path" && git worktree prune.- Otherwise: host environment owns it — leave in place.
Done when: .worktrees/ holds only in-flight work.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

