wt

Create a git worktree in worktree/ subdirectory with up-to-date master

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/wt/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

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 lean, fully executable single-task workflow with clean organization. Its only real gap is the absence of validation checkpoints for the several git commands that can fail mid-sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean — a one-line description, a code block with minimal inline comments, and three short note bullets — and it does not explain concepts Claude already knows, matching anchor 3.	3 / 3
Actionability	The guidance is a fully executable, copy-paste-ready bash block with specific commands (git checkout, pull, worktree add, submodule update), matching anchor 3.	3 / 3
Workflow Clarity	Steps are clearly sequenced and commented, but there are no validation checkpoints or error handling for failure-prone commands such as 'git pull origin master', 'git worktree add', and 'git submodule update' — matching anchor 2, not 3.	2 / 3
Progressive Disclosure	This is a simple single-purpose skill under 50 lines with no need for external references and well-organized sections (Execution, Notes), so per the judging guideline progressive disclosure scores 3.	3 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 concrete and distinguishable but incomplete: it states what the skill does without any explicit "when to use it" trigger guidance and with limited natural-language trigger terms. It is a solid single-purpose description held back by the missing trigger clause.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers, e.g. 'Use when you need an isolated working copy, to work on a branch in parallel, or to avoid switching branches in your main checkout.'

Broaden trigger-term coverage by including natural phrasings users actually say, such as 'worktree', 'isolated environment', 'parallel branch', or 'work on a branch without disturbing master'.

Mention the concrete follow-on actions the skill performs (pulling latest master, initializing submodules) so the capability list reads as comprehensive rather than a single action.

Dimension	Reasoning	Score
Specificity	Names the git-worktree domain and one concrete action with specific details ("worktree/ subdirectory", "up-to-date master"), but lists only a single action rather than multiple — matching anchor 2, not anchor 3.	2 / 3
Completeness	It clearly answers "what" (create a git worktree with up-to-date master) but provides no "Use when…" trigger clause, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	"git worktree" is a natural term a user would say, but coverage is thin and misses common variations such as "isolate changes", "parallel work", or "branch" — matching anchor 2.	2 / 3
Distinctiveness Conflict Risk	"Create a git worktree in worktree/ subdirectory" describes a clear, specific niche unlikely to trigger for unrelated skills, matching anchor 3.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: homeassistant-ai/ha-mcp
Path: .claude/skills/wt/SKILL.md
Commit: 01964cc

Reviewed: 11 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.