finish-branch
Finalizes a development branch by verifying tests pass, then presenting four completion options (merge locally, draft PR, keep as-is, or discard). Use when implementation is done, a feature branch is ready to ship, work needs to be merged or a PR created, or the user says "finish", "wrap up", "ship it", or "done with this branch". DO NOT TRIGGER when tests are still being written or implementation is incomplete.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly communicates specific capabilities, provides rich natural trigger terms, and explicitly defines both when to use and when not to use the skill. The inclusion of four enumerated completion options gives Claude precise understanding of the skill's scope, and the negative trigger clause helps prevent false matches with related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: verifying tests pass, presenting four explicit completion options (merge locally, draft PR, keep as-is, discard). Very clear about what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (finalizes branch by verifying tests and presenting completion options) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios plus a 'DO NOT TRIGGER' exclusion clause). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'finish', 'wrap up', 'ship it', 'done with this branch', plus contextual triggers like 'ready to ship', 'merged', 'PR created'. Also includes negative triggers to avoid false matches. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: branch finalization with specific completion options. The DO NOT TRIGGER clause further reduces conflict risk by excluding incomplete implementation scenarios. Unlikely to overlap with general git or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent workflow clarity, strong actionability through concrete commands and templates, and good progressive disclosure via sub-skill delegation. The main weakness is moderate redundancy between the Common Mistakes, Red Flags, and the inline guidance within the process steps, which could be consolidated to save tokens.
Suggestions
Consolidate 'Common Mistakes' and 'Red Flags' into a single section to eliminate redundancy — many items (test verification, discard confirmation, worktree cleanup, staging plans) appear in both.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the 'Common Mistakes' and 'Red Flags' sections overlap significantly (e.g., test verification, discard confirmation, worktree cleanup, staging docs/plans). The quick reference table is useful but the repeated staging guidance across Options 1 and 2 could be consolidated. | 2 / 3 |
Actionability | Provides concrete, executable bash commands for each option, specific file paths to exclude (docs/plans/*.md), exact text templates for user-facing messages, and clear references to sub-skills (kit:create-pr, kit:worktree-cleanup). The guidance is copy-paste ready and specific. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (verify tests → determine base → present options → execute choice) with explicit validation checkpoints: tests must pass before proceeding, test verification after merge, typed 'discard' confirmation for destructive operations, and clear stop conditions when tests fail. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, a quick reference table for at-a-glance understanding, and appropriate delegation to sub-skills (kit:create-pr, kit:worktree-cleanup) rather than inlining their details. The Integration section clearly signals relationships to other skills. | 3 / 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
- shousper/claude-kit
- Commit
a01bac9
- 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.