worktrees
Guide for using git worktrees to parallelize development with coding agents. Use this skill when the user requests to work in a new worktree
Open source Repository Open in the app JSON README (API)
About
Guide for using git worktrees to parallelize development with coding agents. Use this skill when the user requests to work in a new worktree or wants to work on a separate feature in isolation (e.g.,
Details
- Kind
- Agent skills
- Topic
- Version control
- Publisher
- maragudk
- Origin
- majiayu
- Category
- ferramentas
- Stars
- 17
- Forks
- 8
- Last push
- 2026-03-27T14:01:08Z
- Repository state
- ativo
- Language
- Shell
- License
- MIT
- Added
- 2026-08-30 15:39:04
- Updated
- 2026-08-30 15:39:04
- Origin id
maragudk/skills/worktrees@main
README
# skills > **Note:** Skills have moved to [maragudk/factory](https://github.com/maragudk/factory). <img src="logo.png" alt="Logo" width="300" align="right"> Skills for AI agents. Made with ✨sparkles✨ by [maragu](https://www.maragu.dev/): independent software consulting for cloud-native Go apps & AI engineering. [Contact me at markus@maragu.dk](mailto:markus@maragu.dk) for consulting work, or perhaps an invoice to support this project? ## Usage Install skills with [npx skills](https://skills.sh): ```shell npx skills add maragudk/skills ``` ## Available Skills - **address-code-review** - Address code review feedback by walking through comments one at a time (GitHub PR, document, or conversation) - **autoresearch** - Autonomous experiment loop that iteratively improves a measurable metric through branching, measuring, and keeping or discarding changes - **bluesky** - Guide for posting content to the Bluesky social network using the bsky terminal app - **brainstorm** - Guide for brainstorming ideas and turning them into fully formed designs through iterative questioning - **code-review** - Guide for making code reviews using competing agents to find architecture and implementation issues - **collaboration** - Guide for collaborating on code in open source projects (forking, PRs, reviews, issues) - **datastar** - Guide for building interactive web UIs with Datastar and gomponents-datastar - **decisions** - Guide for recording significant architectural and design decisions in `docs/decisions.md` - **design-doc** - Guide for writing design documents and specifications, especially after brainstorm or feature design sessions - **diary** - Implementation diary that captures the narrative of your work: what changed, why, what worked, what failed, and what was tricky - **garden** - Autonomous project gardening: scans for maintenance issues, picks one, fixes it in a worktree with self-review, and opens a PR - **git** - Guide for using git according to preferences (branch naming, commit messages, issue references) - **go** - Guide for developing Go apps and modules/libraries (code style, testing, dependency injection, package structure) - **gomponents** - Guide for working with gomponents, a pure Go HTML component library for building HTML views - **marimo** - Guide for creating and working with marimo notebooks, the reactive Python notebook that stores as pure .py files - **nanobanana** - Guide for generating and editing images using generative AI with the nanobanana CLI - **observable-plot** - Guide for using Observable Plot, a JavaScript library for exploratory data visualization with marks, scales, and transforms - **save-web-page** - Guide for saving a web page for offline use using the [monolith CLI](https://github.com/Y2Z/monolith) - **sql** - Guide for working with SQL queries, in particular for SQLite (queries, schemas, migrations) - **worktrees** - Guide for using git worktrees to parallelize development with coding agents in isolated environments ## See also - [evals-skills](https://github.com/maragudk/evals-skills) - Skills related to LLM evaluation workflows