wt-switch-create

Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it. Use when launching a session that should work in its own worktree.

Quality

83%

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

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.

A tightly written, highly actionable skill body with concrete commands, an explicitly sequenced workflow, and robust validation/recovery checkpoints. Its only real weakness is mild verbosity in the error-recovery branches and no use of separate reference files for that detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient prose covering harness/worktrunk-specific behavior Claude would not already know, with a few wordy error-recovery branches that could be trimmed — fitting 4 rather than 5 (some over-explanation) or 3 (largely assumes competence).	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout — EnterWorktree({name:…}), wt -C <repo> switch --create … --format=json, git stash push -u, cd <path>, ExitWorktree({action:"keep"}) — plus concrete invocation examples covering common cases.	5 / 5
Workflow Clarity	A clearly sequenced three-step process with explicit validation checkpoints (JSON path extraction, 'Branch already exists' detection, 'Shell cwd was reset' reachability test) and error-recovery feedback loops, matching the 5 anchor.	5 / 5
Progressive Disclosure	A single cohesive, well-sectioned document (Arguments / What to do / Cleanup / Scope) with no nested references, but at over 50 lines the under-50-lines 5-exception does not apply and the long error-recovery section could be split out, so 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

78%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 clear, third-person description that states concrete actions and an explicit 'Use when' trigger. It is distinctive and well-targeted; the main weakness is a single-scenario trigger clause that could enumerate more natural trigger phrases.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Create a new worktrunk worktree', 'switch this session's working directory into it', 'optionally in another repo' — with only minor coverage gaps, fitting the 4 anchor rather than 5 (not comprehensive) or 3 (more than 1–2 actions).	4 / 5
Completeness	Explicitly answers both what ('Create a new worktrunk worktree … and switch …') and when ('Use when launching a session that should work in its own worktree'), but the 'when' is a single scenario rather than enumerated concrete triggers, placing it at 4 instead of 5.	4 / 5
Trigger Term Quality	Includes natural terms users would say — 'worktree', 'work in its own worktree', 'launching a session' — giving good coverage, though a few synonyms (isolation, branch) are missing, so it sits at 4 rather than 5 or 3.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — worktree creation and session re-rooting via the worktrunk/wt tooling — with distinct triggers and minimal overlap with other skills, matching the 5 anchor.	5 / 5
	Total	17 / 20 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: max-sixty/worktrunk
Path: skills/wt-switch-create/SKILL.md
Commit: 6c263ed

Reviewed: 11 hours 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.