CtrlK
BlogDocsLog inGet started
Tessl Logo

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 structured options for merge, PR, or cleanup

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is finishing-a-development-branch in obra/superpowers

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-sequenced, highly actionable workflow with strong validation checkpoints for its destructive operations. Its weaknesses are token-efficiency redundancy across the Quick Reference / Common Mistakes / Red Flags sections and a monolithic single-file structure that underuses progressive disclosure.

Suggestions

Consolidate the overlapping rules in Common Mistakes and Red Flags (e.g. CWD-before-worktree-removal, discard confirmation, Options 1&4-only cleanup) into a single checklist to remove restatement, since the step bodies already enforce most of them.

Move the detailed cleanup-provenance logic and the Common Mistakes / Red Flags reference material into a referenced file (e.g. references/cleanup.md) so SKILL.md stays a lean overview with one-level-deep navigation.

Consider trimming the Quick Reference option matrix, as it restates the merge/push/keep/cleanup behavior already specified per-option in Step 5.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no git basics explained), but the Quick Reference, Common Mistakes, and Red Flags sections substantially restate each other and the step content (e.g. 'cd to main repo root before worktree removal' appears in Step 6, Common Mistakes, and Red Flags), so it could be tightened.

2 / 3

Actionability

It provides concrete, largely copy-paste-ready bash (git worktree remove, gh pr create with heredoc, git branch -D), exact menu text to present, and exact confirmation wording; placeholders like <base-branch> are justified by the task context.

3 / 3

Workflow Clarity

A clear 6-step sequence with explicit validation checkpoints (tests pass before options, verify tests on merged result, typed 'discard' confirmation) and feedback loops; the destructive/batch operations are guarded rather than missing validation.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single 248-line SKILL.md with reference-type content (Common Mistakes, Red Flags, detailed cleanup provenance) inlined rather than split into one-level-deep referenced files, fitting 'content that should be separate is inline'.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: third-person voice, explicit 'Use when...' trigger, concrete named actions (merge, PR, cleanup), and a clear distinct niche. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

The description lists multiple concrete integration actions — 'presenting structured options for merge, PR, or cleanup' — rather than vague language, matching the anchor that names several specific concrete actions.

3 / 3

Completeness

It explicitly answers both 'what' ('guides completion of development work by presenting structured options for merge, PR, or cleanup') and 'when' via an explicit 'Use when implementation is complete, all tests pass...' clause.

3 / 3

Trigger Term Quality

It uses natural phrasing a user would say ('implementation is complete', 'all tests pass', 'integrate the work', 'merge', 'PR', 'cleanup'), giving good coverage of likely trigger terms.

3 / 3

Distinctiveness Conflict Risk

The end-of-development / branch-integration niche with triggers tied to 'implementation is complete, all tests pass' is distinct and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.