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

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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

Quality

Content

88%Weight 40%Scale 1-5

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

This is a highly actionable, well-sequenced skill: every step has executable commands, exact user-facing text, and explicit validation gates for the destructive operations (merge, discard, worktree removal). The only weaknesses are mild redundancy across the Common Mistakes, Red Flags, and Quick Reference sections and the lack of any content split, which keep conciseness and progressive disclosure at 4 rather than 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-first with almost no explanation of concepts Claude already knows; the only trimmable material is redundancy between the "Common Mistakes", "Red Flags", and "Quick Reference" sections, which repeat the cleanup/confirmation rules. This matches the 'efficient; minor instances of over-explanation that could be trimmed' anchor rather than the fully lean anchor at 5.	4 / 5
Actionability	The skill provides copy-paste-ready bash (worktree provenance detection via GIT_DIR/GIT_COMMON, MAIN_ROOT resolution, "git worktree remove" + "prune" sequence), exact menus to present verbatim, and an exact typed-confirmation script for the discard option. Placeholders like <feature-branch> and <base-branch> are appropriate context-dependent parameterization, not gaps, matching the fully executable anchor.	5 / 5
Workflow Clarity	A clear 6-step sequence with explicit validation checkpoints: tests must pass before options are shown ("Stop. Don't proceed to Step 2"), tests are re-verified on the merged result, merge success is confirmed before any removal, and discard requires typed "discard" confirmation. The destructive-operation cap at 3 does not apply because validation and confirmation gates are present throughout, matching the explicit-validation-with-feedback anchor.	5 / 5
Progressive Disclosure	The skill is a single file with no bundle directories or external references, and its sections (Overview, Process steps, Quick Reference, Common Mistakes, Red Flags) are well organized with no buried or dangling references. It sits at 'good structure; minor organization gaps' rather than 5 because at ~240 lines the overlapping Common Mistakes and Red Flags sections could be consolidated, and there is no reference structure of the kind the top anchor rewards.	4 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

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

A strong description: it pairs an explicit, concrete "Use when..." trigger with a clear third-person statement of what the skill does, and its trigger terms are natural to the moment of need. Keyword coverage and action coverage are good but not exhaustive, and there is minor overlap risk with general git/PR skills.

Dimension	Reasoning	Score
Specificity	"guides completion of development work by presenting structured options for merge, PR, or cleanup" names several concrete actions (presenting options, merge, PR, cleanup), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because coverage is not comprehensive (e.g., branch deletion and keep-as-is are not named), and exceeds 3 because more than 1-2 actions are listed.	4 / 5
Completeness	The description explicitly answers both questions: an explicit "Use when implementation is complete, all tests pass, and you need to decide how to integrate the work" trigger clause and a clear third-person "what" ("guides completion of development work by presenting structured options for merge, PR, or cleanup"). It matches the anchor requiring both what and when with concrete trigger phrases, exceeding 4 where the when-clause could be more specific.	5 / 5
Trigger Term Quality	"implementation is complete", "all tests pass", "merge", "PR", and "integrate" are phrases a user or agent would naturally produce at this decision point, giving good keyword coverage. A few natural terms are missing (e.g., "finish the branch", "wrap up", "ship"), keeping it below the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The end-of-development integration decision is a fairly distinct niche with specific triggers (tests passing, integration decision), giving minor overlap risk only with closely related git/PR skills. It is not a 5 because generic git-workflow or PR-creation skills could plausibly trigger on "merge" and "PR".	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/finishing-a-development-branch/SKILL.md
Commit: 899d1fb

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.