Create Isolated Git Worktrees
Developers need isolated workspaces before agents change code. This skill guides Claude, Codex, and Claude Code through repeatable Git worktree setup and baseline checks.
This skill is part of a pack
Install the whole pack to get every skill the task needs, in one command.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "using-git-worktrees" from https://skillstore.io/skills/obra-using-git-worktrees.md and its manifest at https://skillstore.io/api/skills/obra-using-git-worktrees/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "using-git-worktrees". I need to build a login feature without disturbing my current branch.
Expected outcome:
The assistant reports the selected worktree location, confirms ignore protection, creates the feature workspace, and states whether baseline tests passed.
Using "using-git-worktrees". Prepare a worktree for a hotfix and verify the baseline.
Expected outcome:
The assistant creates a clean hotfix workspace, runs approved setup steps, summarizes test results, and asks before proceeding if tests fail.
Using "using-git-worktrees". Our repository has custom worktree guidance. Use it safely.
Expected outcome:
The assistant checks repository guidance, validates the requested location, asks about unusual paths, and then follows the approved setup process.
Most static findings are Markdown formatting or documented Git workflow commands, not executable Ruby backticks or hidden secret access. Real risks remain where the skill asks the agent to run package managers, test commands, use repository-provided preferences, and commit ignore changes without explicit approval. No prompt injection attempt was found in SKILL.md.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/obra-using-git-worktrees/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/obra-using-git-worktrees?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/obra-using-git-worktrees?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/obra-using-git-worktrees/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/obra-using-git-worktrees.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>obra. (2026). using-git-worktrees security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/obra-using-git-worktrees/audits/8@techreport{obra-obra-using-git-worktrees-2026,
author = {obra},
title = {using-git-worktrees security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/obra-using-git-worktrees/audits/8},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "using-git-worktrees security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "obra"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/obra-using-git-worktrees/audits/8"
identifiers:
- type: other
value: "skillstore:obra-using-git-worktrees:audit:8"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
zhanlincui-using-git-worktrees
2026-08-21
doyajin174-using-git-worktrees
2026-08-21
codingcossack-using-git-worktrees
2026-08-21
dyai2025-using-git-worktrees
2026-08-21
obra-using-git-worktrees
2026-08-21
cygnusfear-using-git-worktrees
2026-08-21
sickn33-using-git-worktrees
2026-08-21
davila7-using-git-worktrees
2026-08-21
cycleaddict-using-git-worktrees
2026-08-21
Create an isolated branch workspace before implementing a feature with an AI assistant.
Open a clean hotfix workspace without disturbing current local changes.
Give AI coding agents a repeatable process for worktree location, setup, and baseline testing.
Create an isolated Git worktree for my next feature. Ask before installing dependencies or changing git history.
Use this skill to inspect existing worktree directories and repository guidance. Validate the location with me before creating the worktree.
Set up a worktree for feature <name>, run approved setup commands, run baseline tests, and report any failures before implementation.
For two planned branches, propose safe worktree locations, required setup commands, test checks, and cleanup notes before creating anything.
Author
obraLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
8 downloads · 236 views
File structure
📄 SKILL.md
Create Detailed Implementation Plans
Complex work is risky when requirements are not broken into clear steps. This skill turns specs into test-focused implementation plans for Claude, Codex, and Claude Code.
Execute Implementation Plans with Checkpoints
Implementation plans can lose focus when work moves into a separate AI session. This skill guides Claude, Codex, and Claude Code through batch execution, verification, and review checkpoints.
Build Tested AI Skills
AI skills can fail when instructions are vague or untested. This skill guides test-driven skill writing with pressure scenarios and verification loops.
Evaluate Code Review Feedback
Code review feedback can be unclear, incorrect, or incomplete. This skill helps Claude, Codex, and Claude Code verify suggestions, ask precise questions, and implement reviewed changes carefully.
Plan Features Through Guided Brainstorming
Feature ideas often move to implementation before goals and constraints are clear. This skill guides Claude, Codex, and Claude Code through questions, trade-offs, and validated design notes.
Execute Plans with Subagent Reviews
Complex implementation plans lose quality when one context handles every task. This skill coordinates fresh subagents for implementation, spec checks, and code quality reviews.
Write Conventional Git Commits
by 0xmsc
Developers often lose time turning staged changes into clear commit history. This skill guides Conventional Commits, atomic changes, and safe git review steps.
Master Advanced Git Workflows
by AutumnsGrove
Complex Git maintenance can make history changes and conflict resolution difficult. This skill provides structured guidance, recovery steps, and an optional local helper for common advanced workflows.
Create Conventional Git Commits
by 21pounder
Manual commit preparation can miss staged changes, message style, or sensitive files. This skill reviews git state and helps create clear conventional commits.
Draft Git Commit Messages From Staged Changes
by AbeJitsu
Writing commit messages from staged changes takes time and can miss important context. This skill collects git status and diff details so AI can draft a clear message.
Review Changed Code Before Release
by DavidDworetzky
Code changes can hide security flaws, performance regressions, and project-standard violations. This skill guides Claude, Codex, or Claude Code through a structured review of modified files.
Implement Tasks with TDD Workflow
by sickn33
Task plans can drift when implementation, tests, commits, and approvals are handled inconsistently. This skill provides a structured TDD workflow with checkpoints, verification gates, and git tracking.