Tessl • The management layer for AI agent skills

An exemplary lean, fully executable workflow: concrete commands, explicit conflict-handling and verification checkpoints, and clean section organization with no padding. No bundle files are present and none are needed at this size.

Dimension	Reasoning	Score
Conciseness	~60 lean lines with zero concept explanations: every line instructs (commands, paths, conflict handling). The one illustrative sentence ("gh pr checkout handles fetching, fork tracking, and branch setup automatically") earns its place by preventing redundant manual steps.	5 / 5
Actionability	Fully executable, copy-paste-ready commands throughout: `mkdir -p <repo-root>/.worktrees`, `git worktree add .worktrees/<name> --detach`, `gh pr view <number> --json headRefName -q .headRefName`, `git checkout --no-track -b <new-branch>`, and concrete edge-case handling (existing worktree, branch already checked out elsewhere).	5 / 5
Workflow Clarity	A clearly sequenced 4-step workflow with explicit checkpoints: branch-conflict detection (check `git worktree list` output, then `AskUserQuestion` with a defined stop condition) and a `pwd` verification step that halts on failure. Worktree creation is not a destructive or batch operation, so no validation cap applies.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and none are needed: the skill is short and self-contained with well-organized sections (Steps 1-4). Per the rubric's simple-skill guidance, well-organized sections suffice when no external references are required.	5 / 5
	Total	20 / 20 Passed

Description

70%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 specific, third-person description naming concrete actions in a distinct niche, weakened by the absence of an explicit "Use when..." trigger clause and slightly thin synonym coverage. Adding trigger guidance would lift the two dimensions currently scoring 3 and 4.

Suggestions

Append an explicit trigger clause, e.g. "Use when asked to review a PR, work on a branch in isolation, or set up an isolated checkout."

Add natural variations users would say: "worktrees", "PR", "check out a pull request", "isolated checkout".

Optionally mention that it can set up a new branch in the worktree, since the body supports it (git checkout --no-track -b).

Dimension	Reasoning	Score
Specificity	"Create or reuse a git worktree for a pull request or branch" names the domain and several concrete actions (create, reuse, PR/branch handling) with only minor coverage gaps. It falls between the 1-2-action anchor (3) and the multiple-specific-actions anchor (5), noticeably above the midpoint.	4 / 5
Completeness	The "what" is clear ("Create or reuse a git worktree for a pull request or branch"), but there is no "Use when..." clause or equivalent explicit trigger guidance; "so reviews and work happen in isolation" only weakly implies when. Per the rubric guidelines, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural keywords "git worktree", "pull request", "branch", "reviews", "isolation" give good coverage of what a user would say. Missing common variations like "worktrees", "PR", or "checkout", so it does not reach the comprehensive synonym coverage of 5.	4 / 5
Distinctiveness Conflict Risk	"git worktree" is a clear niche with distinct triggers (worktree, pull request, branch checkout in isolation); a user asking for a worktree would unambiguously land here. Minimal overlap with other skills.	5 / 5
	Total	16 / 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: dlt-hub/dlt
Path: .claude/skills/create-worktree/SKILL.md
Revision: e914711

Reviewed: 27 days ago

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.

create-worktree

Table of Contents

Is this your skill?