using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Quality

68%

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 ./plugins/superpowers/skills/using-git-worktrees/SKILL.md

The canonical home for this skill is using-git-worktrees in obra/superpowers

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a clearly sequenced, well-validated workflow with concrete executable commands and strong feedback loops for a risky operation. It loses points for redundant summary sections, an incomplete create-worktree code block with undefined variables, and the absence of file-based progressive disclosure for a 210-line skill.

Suggestions

Define $BRANCH_NAME and $LOCATION/$path concretely in the create-worktree block (or provide one complete worked example) so the central command is copy-paste ready rather than relying on commented guidance.

Collapse or merge the redundant Quick Reference / Common Mistakes / Red Flags sections, which restate the same rules 3-4 times and add tokens without new information.

Move detailed edge-case material (Common Mistakes, Red Flags, directory-selection priority) into a reference file and keep SKILL.md as a lean overview to practice progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The core steps are lean with no basic-concept padding, but the Quick Reference table, Common Mistakes, and Red Flags sections restate directives already in the steps (e.g., "Fighting the harness", "Skipping ignore verification") 3-4 times, matching "Mostly efficient but includes some unnecessary explanation or could be tightened."	2 / 3
Actionability	Most commands (detection, git check-ignore, project setup) are executable, but the central create-worktree block uses undefined $BRANCH_NAME, $LOCATION, and $path with commented guidance ("# Determine path based on chosen location"), so it is not copy-paste ready — matching "Some concrete guidance but incomplete... missing key details."	2 / 3
Workflow Clarity	There is a clear sequence with explicit validation checkpoints and feedback loops: Step 0 submodule guard, the git check-ignore verification with "If NOT ignored: Add to .gitignore, commit, then proceed", and Step 4 "If tests fail: Report failures, ask whether to proceed or investigate" — matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle/reference files exist and everything (edge cases, Quick Reference, Common Mistakes, Red Flags) is inline in a single ~210-line file; it is well-sectioned but exceeds the 50-line simple-skill threshold and keeps content that could be split into references inline, matching "Some structure... content that should be separate is inline."	2 / 3
	Total	9 / 12 Passed

Description

75%

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 clearly states both what (ensure an isolated workspace via native tools or git fallback) and when (feature work needing isolation, before implementation plans), occupying a distinctive worktree niche. Trigger phrasing is somewhat technical and could use more colloquial variations, and the single-purpose action set is narrow.

Suggestions

Add colloquial trigger variations a user might naturally say (e.g., 'work on a separate branch', 'keep changes isolated from my current workspace') to broaden trigger-term coverage beyond the technical phrasing.

Surface the key concrete sub-actions (detect existing isolation, then create the workspace) in the description so the action set reads as more comprehensive rather than a single bundled action.

Dimension	Reasoning	Score
Specificity	It names the domain and concrete mechanisms ("ensures an isolated workspace exists via native tools or git worktree fallback"), but as a single-purpose skill it does not enumerate multiple distinct actions like the score-3 example, matching "Names domain and some actions, but not comprehensive."	2 / 3
Completeness	It explicitly answers when ("Use when starting feature work that needs isolation... or before executing implementation plans") and what ("ensures an isolated workspace exists via native tools or git worktree fallback") with an explicit trigger clause, matching the score-3 anchor; not 2 because the 'when' is explicit rather than implied.	3 / 3
Trigger Term Quality	The triggers "starting feature work that needs isolation" and "before executing implementation plans" are reasonably natural, but phrasing like "isolation from current workspace" and "native tools or git worktree fallback" leans technical and misses colloquial variations, matching "Some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	The niche is clearly defined by "isolation from current workspace" and "git worktree fallback" — a distinctive worktree-isolation domain unlikely to trigger unrelated skills, matching "Clear niche with distinct triggers; unlikely to conflict."	3 / 3
	Total	10 / 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: openai/plugins
Path: plugins/superpowers/skills/using-git-worktrees/SKILL.md
Commit: 11c74d6

Reviewed: about 10 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.