dev-worktree

AI DevKit · Worktree setup and resume guidance for isolated feature work. Use when starting, resuming, switching, or verifying a feature branch/worktree for lifecycle, debugging, implementation, review, or multi-agent workflows.

Quality

77%

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 ./skills/dev-worktree/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 body is lean, highly actionable, and well-structured with concrete git commands and explicit validation checkpoints; its only gap is the absence of error-recovery guidance when a verification step fails.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence: no explanation of what a worktree is, direct commands throughout, and every section earns its place; the scope-guarding sentence is useful boundary-setting rather than fluff.	3 / 3
Actionability	Fully executable, copy-paste-ready commands are given for every step (e.g. 'git worktree add -b feature-<name> .worktrees/feature-<name>', 'npm ci', 'uv sync', 'git -C .worktrees/feature-<name> branch --show-current').	3 / 3
Workflow Clarity	Sequences are clear with explicit validation checkpoints ('Confirm the target... before switching', 'verifying it is clean enough', 'it must equal feature-<name>'), but no error-recovery feedback loop is specified for when verification fails.	2 / 3
Progressive Disclosure	Well-organized into logical sections (Phase Contract, Start, Resume, Dependency Bootstrap, Output) with no nested references and all content appropriately inline; no bundle files are present or needed.	3 / 3
	Total	11 / 12 Passed

Description

67%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 answers both what and when with an explicit Use-when clause and concrete worktree triggers, but its specificity and distinctiveness are dragged down by branding noise and over-claimed applicability to implementation/review that the body disallows.

Suggestions

Drop the 'AI DevKit ·' branding prefix and the over-claiming tail ('lifecycle, debugging, implementation, review, or multi-agent workflows') since the body forbids implementation/review work here.

Add natural trigger variations a user would actually say, e.g. 'git worktree', 'create a worktree', or 'isolated feature branch'.

Keep the trigger list tight to the skill's real scope: starting, resuming, switching, and verifying feature worktrees.

Dimension	Reasoning	Score
Specificity	Lists concrete worktree actions ('setup and resume', 'starting, resuming, switching, or verifying a feature branch/worktree'), but pads with over-claiming buzzwords ('debugging, implementation, review, or multi-agent workflows') that the body explicitly disclaims.	2 / 3
Completeness	Clearly states what it does ('Worktree setup and resume guidance for isolated feature work') and when to use it via an explicit 'Use when starting, resuming, switching, or verifying...' clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Relevant natural terms ('worktree', 'feature branch', 'feature work') are present, but the 'AI DevKit ·' branding prefix and jargon tail ('lifecycle', 'multi-agent workflows') dilute the triggers, and simpler variations like 'git worktree' or 'create a worktree' are missing.	2 / 3
Distinctiveness Conflict Risk	The worktree-isolation niche is distinct, but the trailing claim of applicability to 'debugging, implementation, review, or multi-agent workflows' overlaps with many other skills and raises conflict risk.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: codeaholicguy/ai-devkit
Path: skills/dev-worktree/SKILL.md
Commit: 15b09d2

Reviewed: 12 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.