Skip to content
SkillModel-led1,884 tokens in use

finishing-a-development-branch

Verifies tests, detects your worktree setup, offers merge, pull request or keep, and cleans up after you decide.

322,762 stars on the repository MIT Licenseobra/superpowers · skills/finishing-a-development-branch
/plugin install superpowers@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing finishing-a-development-branch costs

27tokens idle
1,884tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectedgitdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 31
  • Runs git commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 94

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity56
  • Maintenance68
  • Community64
  • Maturity36
  • Momentum40

Finishing a Development Branch closes out completed work. It runs the full test suite first and stops on failures. When the suite is green it works out whether you are in a normal repository, a named-branch worktree or a detached HEAD, shows the options that apply, and carries out the one you choose.

What You Get

  • A green-suite gate before any option is shown
  • A menu matched to the git state, with three options normally and two on a detached HEAD
  • Merge, push and pull request, or keep, run with the right git commands
  • Worktree cleanup that asks you before it forces anything

Common Use Cases

  • Wrapping up a feature branch after the last task passes
  • Opening a pull request from a worktree
  • Removing a worktree after a local merge

What Makes It Unique

It compares the git directory with the common git directory to tell worktrees from normal repositories, and adjusts the menu and cleanup to match. Cleanup removes only worktrees under .worktrees or worktrees, the ones the skill family created, and it asks before any forced removal. Discarding work needs the word discard typed back.

Under The Hood

Instructions with shell snippets. The agent runs your test command and git commands: rev-parse to detect the worktree state, checkout, pull and merge, push with upstream tracking, branch delete, and worktree remove and prune. Pull request creation uses the forge’s command-line tool when one is available. It writes no files and calls only your git remotes.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers