git-worktrees
Creates an isolated git worktree workspace with smart directory selection, gitignore safety verification, dependency installation, and baseline test validation. Use when starting feature work, beginning a new branch, needing workspace isolation, setting up before plan execution, or the user says "new feature", "set up a worktree", or "isolate this work". DO NOT TRIGGER for worktree cleanup or removal — use kit:worktree-cleanup instead.
90
88%
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 hits all the marks. It provides specific concrete actions, comprehensive natural trigger terms, explicit 'Use when' and 'DO NOT TRIGGER' clauses, and clear disambiguation from related skills. The description is well-structured, uses third person voice correctly, and is concise while being thorough.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'isolated git worktree workspace', 'smart directory selection', 'gitignore safety verification', 'dependency installation', and 'baseline test validation'. These are all concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates isolated git worktree with directory selection, gitignore verification, dependency installation, test validation) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). Also includes a 'DO NOT TRIGGER' clause for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'new feature', 'set up a worktree', 'isolate this work', 'starting feature work', 'beginning a new branch', 'workspace isolation'. These are phrases users would naturally say. Also includes negative triggers to avoid conflicts. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (worktree creation/setup) and explicitly disambiguates from the related 'worktree-cleanup' skill with a 'DO NOT TRIGGER' clause. The specific triggers like 'set up a worktree' and 'isolate this work' are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent workflow clarity and concrete executable commands throughout. Its main weakness is redundancy — the Quick Reference, Common Mistakes, Red Flags, and core workflow sections repeat the same information in different formats, inflating token cost without proportional value. The safety verification workflow with gitignore checking and baseline test validation is well-designed with proper feedback loops.
Suggestions
Consolidate the Quick Reference table, Common Mistakes, and Red Flags sections into a single compact reference — they largely restate the same constraints already embedded in the workflow steps.
The Example Workflow section mostly mirrors the Creation Steps and could be removed or reduced to save tokens, since the steps themselves are already concrete enough to follow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy — the Quick Reference table, Common Mistakes, Red Flags, and Example Workflow sections overlap significantly in content. The 'Never/Always' lists largely restate what was already covered in the workflow steps and safety verification sections. | 2 / 3 |
Actionability | Provides concrete, executable bash commands throughout — from directory detection, git check-ignore verification, worktree creation, dependency installation auto-detection, to test running. Commands are copy-paste ready and cover multiple project types. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (directory selection → safety verification → creation → setup → test → report) with explicit validation checkpoints: gitignore verification before creation, baseline test verification before proceeding, and clear error recovery paths (add to .gitignore if not ignored, ask user if tests fail). | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and a logical flow, but it's somewhat monolithic — the Common Mistakes, Red Flags, Quick Reference, and Example Workflow sections add bulk that could be trimmed or moved to a separate reference file. The Integration section is appropriately brief with cross-references. | 2 / 3 |
Total | 10 / 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.