Agent skill
finish-branch
Install this agent skill to your Project
npx add-skill https://github.com/iamladi/cautious-computing-machine--sdlc-plugin/tree/main/skills/finish-branch
SKILL.md
Finish Branch Skill
Priorities
Safety > Completeness > Speed
Goal
Clean up local and worktree branches after PR merge. Verify merge status via gh pr view or git branch --merged, switch to main, pull latest, run tests, delete branch using safe delete, and remove associated worktree if present. Maintain repository hygiene without losing work.
Constraints
- Check merge detection: use gh pr view for PR numbers, git branch -r --merged for branch names
- Never delete unmerged: use git branch -d (safe delete), never -D
- Verify clean state: check git status before switching branches
- Confirm worktree cleanup: git worktree remove only after verifying path
- Stop if PR not merged or branch has unmerged commits
- Warn on test failures but continue cleanup
Workflow
- Parse arguments: PR number, branch name, or detect from current branch
- Verify merge status: gh pr view or git branch --merged check
- Check uncommitted changes: git status --porcelain, warn if dirty
- Switch to main: git checkout main
- Pull latest: git pull origin main
- Run tests: detect and execute appropriate test command
- Delete branch: git branch -d [name]
- Clean worktree: git worktree list, then git worktree remove if exists
- Prune remotes: git remote prune origin
Safety Checks
- PR merge detection: always verify before cleanup
- Safe delete only: never force delete with -D
- Check before switch: confirm no uncommitted work
- Worktree path confirmation: verify worktree path before removal
- Stop on unmerged: halt cleanup if branch not merged to main
Arguments
$ARGUMENTS
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
tdd
TDD enforcement during implementation. Reads `tdd:` setting from CLAUDE.md. Modes - strict (human approval for escape), soft (warnings), off (disabled). Auto-invoked by /implement.
judgment-eval
Evaluates agent judgment quality through scenario-based testing in-conversation. Use when the user wants to test, validate, or stress-test an agent, skill, or command definition — e.g. "test this agent", "evaluate this skill", "does this prompt handle edge cases", "check this agent's judgment", or after writing or modifying any agent/skill/command .md file.
update-models
Re-resolve the model registry by querying OpenAI Codex cache, Google AI API, and Oracle CLI. Use when models feel stale or after a major model release.
gemini
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Resolves the latest flagship model from the model registry.
agent-change-walkthrough
Generates a narrative walkthrough of AI-authored code changes. Use after implementation to explain what changed, why, and how it behaves.
interview
Interview me about anything in depth
Didn't find tool you were looking for?