finishing-a-development-branch
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…
Skill by Fleron
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fleron-finishing-a-development-branch
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill 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
- License
- MIT
- Instructions
- 230 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "finishing-a-development-branch" does not match folder "finishing-branch"
Files (1)
- SKILL.md
SKILL.md (first lines)
> **Pipeline position:** final stage — runs after all tasks complete — see [`../../reference/pipeline-flow.md`](../../reference/pipeline-flow.md). # Finishing a Development Branch ## Overview Guide completion of development work by presenting clear options and handling chosen workflow. **Core principle:** Verify tests and linting → Present options → Execute choice → Clean up. **Announce at start:** "I'm using the finishing-a-development-branch skill to complete this work." ## The Process ## PR-Ready Mode When invoked by scaffolded goal execution, use PR-ready mode. In this mode, after tests and critical lint/format checks pass, pushing the branch and creating a Pull Request is mandatory. Do not present the local merge, keep-as-is, or discard options as the normal completion path. PR-ready completion must: 1. Run `gh auth status` and stop with a clear blocked state if `gh` is missing or unauthenticated. 2. Push the current branch. 3. Create a PR with `gh pr create`. 4. Update the active goal metadata to `workflow_stage: implementation_pr_open`, `implementation_pr_url`, and `implementation_pr_number`. 5. Stop and state that human review plus PR merge is the acceptance gate. ### Step 1a: Verify Tests **Before presenting options, verify tests pass:** ```bash # 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 1b: Verify lint and formatting ```bash # Run lint and formatting checks npm run lint / cargo clippy / flake8 / go fmt -l ./... ``` **If formatting and linting fail:** First define each failure based on if it is critical (e.g. clippy warnings treated as errors) or non-critical (e.g. go fmt issues that can be auto-fixed). ``` <formatter(eg. clippy)> failing (<N> failures). Must fix before completing: [Show failures] Cannot proceed with merge/PR until critical formatting linting pass. ``` ### Step 2: Determine Base Branch ```bash # 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?" ### 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 ```bash # 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: Cleanup worktree (Step 5) #### Option 2: Push and Create PR ```bash
From Fleron/Claude-plugins, MIT.
More from Fleron/Claude-plugins
- 0.567score
code-review
Fleron
Use when the user asks for a review of the current diff, branch or pull request, wants a final check before shipping or opening a PR, asks what is wrong with…
SkillAFreshness: A★ 1Claude Code +9 - 0.527score
babysit-pr
Fleron
Use when the user asks to monitor, watch or babysit a pull request, keep an eye on CI, handle incoming review comments, or stay on top of failures and…
SkillBFreshness: B★ 1Claude Code +9 - 0.494score
rebuild-guidelines-index
Fleron
Rebuild navigational index files for coding guidelines.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
claude-control-goals
Fleron
Minimal /goal integration for Claude and Codex.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
extensive-build
Fleron
Guided feature development with codebase understanding and architecture focus
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
create-feature
Fleron
Guided feature development with codebase understanding and architecture focus
SkillCFreshness: C★ 1Claude Code +9 - 0.476score
team-build
Fleron
Implement the plan
SkillCFreshness: C★ 1Claude Code +9 - 0.471score
executing-plans
Fleron
Use when you have a written implementation plan to execute in a separate session with review checkpoints
SkillCFreshness: C★ 1Claude Code +9 - 0.471score
subagent-driven-development
Fleron
Use when executing implementation plans with independent tasks in the current session
SkillCFreshness: C★ 1Claude Code +9 - 0.471score
subagent-driven-development
Fleron
Use when executing implementation plans with independent tasks in the current session
SkillCFreshness: C★ 1Claude Code +9 - 0.471score
plan-writing
Fleron
Use when you have a spec or requirements for a multi-step task, before touching code
SkillCFreshness: C★ 1Claude Code +9 - 0.469score
brainstorm
Fleron
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 16, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Fleron/Claude-plugins
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Fleron
- 0.567score
code-review
Fleron
Use when the user asks for a review of the current diff, branch or pull request, wants a final check before shipping or opening a PR, asks what is wrong with…
SkillAFreshness: A★ 1Claude Code +9 - 0.527score
babysit-pr
Fleron
Use when the user asks to monitor, watch or babysit a pull request, keep an eye on CI, handle incoming review comments, or stay on top of failures and…
SkillBFreshness: B★ 1Claude Code +9 - 0.494score
rebuild-guidelines-index
Fleron
Rebuild navigational index files for coding guidelines.
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
claude-control-goals
Fleron
Minimal /goal integration for Claude and Codex.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
create-feature
Fleron
Guided feature development with codebase understanding and architecture focus
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
extensive-build
Fleron
Guided feature development with codebase understanding and architecture focus
SkillCFreshness: C★ 1Claude Code +9
Cite this page
finishing-a-development-branch skill. Agent Mart. https://agentmart.dev/skills/fleron-finishing-a-development-branch (last updated 2026-10-24)