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
88
83%
Does it follow best practices?
Impact
98%
1.92xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
75%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 has strong completeness with an explicit 'Use when' clause and good distinctiveness for its niche in the development workflow. However, it could be more specific about what concrete actions it performs beyond 'presenting structured options,' and could benefit from additional trigger term variations that developers might naturally use.
Suggestions
List more specific concrete actions the skill performs, e.g., 'Presents structured options for merging branches, creating pull requests, squashing commits, or cleaning up feature branches'
Add more natural trigger term variations such as 'pull request', 'push changes', 'ready to merge', 'done coding', 'submit for review', 'finish up work'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (development workflow completion) and some actions (merge, PR, cleanup), but the actions are presented as options rather than concrete capabilities the skill performs. 'Guides completion of development work by presenting structured options' is somewhat vague about what it actually does. | 2 / 3 |
Completeness | Clearly answers both 'what' (guides completion of development work by presenting structured options for merge, PR, or cleanup) and 'when' (when implementation is complete, all tests pass, and you need to decide how to integrate the work). The 'Use when' clause is explicit and detailed. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'merge', 'PR', 'tests pass', 'cleanup', and 'implementation is complete', which are natural developer terms. However, it misses common variations like 'pull request', 'push changes', 'submit code', 'done coding', 'finish up', or 'ready to merge'. | 2 / 3 |
Distinctiveness Conflict Risk | This has a clear niche: the post-implementation decision point for code integration. The specific trigger conditions (implementation complete + tests pass + integration decision needed) make it unlikely to conflict with general coding, testing, or git skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with clear, actionable workflows and excellent validation checkpoints throughout. The structured 4-option approach eliminates ambiguity, and the confirmation gate on destructive operations demonstrates good safety practices. Minor improvement could come from consolidating the slightly overlapping 'Common Mistakes' and 'Red Flags' sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient throughout. It doesn't explain what git, PRs, or worktrees are—it assumes Claude knows. Every section serves a purpose, and the quick reference table is a compact summary rather than redundant content. | 3 / 3 |
Actionability | Every step includes executable bash commands, exact text to present to users, and specific templates (e.g., PR body format). The options are copy-paste ready with concrete git commands for each path. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (verify → determine base → present options → execute → cleanup) with explicit validation checkpoints: tests must pass before proceeding, tests re-run after merge, typed confirmation required before discard. Error recovery is addressed (test failures block progress, discard requires confirmation). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a quick reference table, but it's all inline in one file. The 'Common Mistakes' and 'Red Flags' sections partially overlap and could be consolidated. However, for a skill of this complexity, the single-file approach is reasonable—it just slightly exceeds what needs to be inline. | 2 / 3 |
Total | 11 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- obra/superpowers
- Commit
6efe32c
- 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.