What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
To make Google Antigravity useful for recurring coding chores, first give the agent the right project context, then write a bounded task with clear success criteria, and save repeatable guidance in the mechanism that matches your Antigravity surface. In the IDE, use Rules for standing instructions and Workflows for on-demand sequences; in Antigravity 2.0, use Agent Skills for reusable task instructions. The IDE’s current Workflows system is scheduled to stop working on October 19, 2026, so plan around that transition.
Choose the Antigravity surface that matches your work
Google documents three related but distinct surfaces: Antigravity 2.0, a desktop agent command center; Antigravity CLI, a terminal interface; and Antigravity IDE, an AI-powered development environment. The setup paths below are surface-specific: the Customizations panel instructions apply to the IDE, while project modes and Skills described for Antigravity 2.0 have their own setup. Google’s getting-started guide covers the current surfaces and download information.
For IDE version 2.0, Google lists macOS 12 or later on Apple Silicon (Intel is unsupported), Windows 10 64-bit, Linux with glibc 2.28 or later and glibcxx 3.4.25 or later, and Googlebook OS. Check the live guide before installing because platform requirements can change.
Give the agent bounded project context
Create an Antigravity 2.0 project
- Use the folder-plus control and choose New Project.
- Add one or more local folders or Git repositories, then select Create. Multiple folders provide cross-repository context; each project keeps its own settings and security policies.
- Enter a specific goal in the project chat input and choose an agent mode. Local lets the agent work in active folders; New worktree isolates its work in a Git worktree.
Google documents these project and mode options in its Antigravity 2.0 guide. As a practical prompt pattern, name the outcome, the files or boundaries that matter, and how you will verify success. For example: “Add unit tests for the date parser in src/date-parser. Don’t change its public API. Run the existing parser tests and report any failures.” This makes the request easier to review than an open-ended instruction such as “improve the tests.”
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallOutdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware match#1 Best Overall
Use commands for the right kind of direction
In Antigravity 2.0, /grill-me helps align on details before implementation, while /goal asks the agent to continue until the task is complete. Use the former when requirements are uncertain and the latter when completion conditions are clear. /schedule sets a one-time or recurring instruction; /browser controls browser debugging behavior in Chrome.
Set up reusable guidance in the IDE
In Antigravity IDE, open the ellipsis menu in the Agent panel, choose Customizations, then open Rules or Workflows. Google describes the distinction this way: Rules provide persistent, reusable context at the prompt level, while Workflows provide a structured sequence at the trajectory level. Both can be created globally for reuse across workspaces or at workspace scope for a project-specific process.
Use Rules for conventions that should always apply
Rules are a good place for standing expectations such as code style, modularity, or project-specific constraints. Google Codelabs says, “Rules help guide the behavior of the agent.” Keep a rule focused on context that is relevant across many tasks; a sprawling rule that attempts to prescribe every possible task is harder to maintain than focused guidance.
Use Workflows for repeatable, on-demand sequences
A Workflow is a Markdown file with a title, description, and task steps. Invoke it from the agent with a slash command such as /generate-unit-tests. Workflows can call other workflows and each file is limited to 12,000 characters, according to Google’s Workflows documentation.
Recommended Free Tools
A useful workflow might tell the agent to inspect the project’s test conventions, generate tests for a named module, run the established test command, and summarize the result. Keep steps concrete and tied to your repository’s real scripts rather than inventing checks. Google Codelabs’ example uses persistent rules for coding conventions and an on-demand workflow for unit-test generation; adapt that pattern to recurring tasks such as preparing a pull-request review or running established checks.
For Antigravity 2.0, create a reusable Skill
Agent Skills are the reusable task-instruction mechanism documented for Antigravity 2.0. A Skill is a folder containing a required SKILL.md file, with optional scripts, examples, and resources. Create a workspace Skill at <workspace-root>/.agents/skills/<skill-folder>/ or a global Skill at ~/.gemini/config/skills/<skill-folder>/. The agent can select a relevant Skill based on its description, or you can invoke it with /<skill-name>. See Google’s Agent Skills documentation for the current format.
Rank #4
- ENHANCED CONTEXT WITH MULTIMODAL INPUT: Capture audio, type notes, add images, and press to highlight key moments for richer context. During recording, instantly mark key moments with a single button press. Simultaneously enrich your audio by snapping photos of important documents or typing in ideas
- CHAT WITH YOUR RECORDINGS USING "ASK Plaud": Unlock deeper insights with this interactive AI. Ask questions, extract key points, draft emails, and get next-step suggestions—all grounded in your original audio for reliable, ready-to-use answers
- INTELLIGENT RECORDING WITH AI DIRECTIONAL AUDIO: Enjoy seamless, intelligent recording with Plaud Note Pro. Its AI automatically switches between call and meeting modes while recording, while directional audio and real-time spatial awareness minimize noise to capture voices with crystal clarity
- Everything Included: Includes Plaud Note Pro, magnetic case, magnetic ring, charging cable, and a free Starter Plan with 300 transcription minutes per month. Upgrade anytime in the Plaud app to Pro Plan (1,200 min/mo) or Unlimited Plan(Up to 24 hours of transcription per user per day)
- PREMIUM ULTRA-SLIM DESIGN WITH INSTANTVIEW DISPLAY: Meticulously designed, the AI Note Taker is just 0.12 inches thin and 1.06 oz —about the size of a credit card. Its sleek aluminum body with a textured wave finish features a vivid AMOLED display, letting you check battery and recording status at a glance, while it seamlessly works with Apple Find My to ensure you never misplace it
Do not assume Skills and IDE Workflows are identical: their setup locations and activation behavior differ. Google’s IDE Workflows page says the current workflow system will stop working on October 19, 2026, and points users to a Workflows-to-Skills migration guide or /migrate-workflows. That cutoff is still in the future as of October 7, 2026; migrate or re-check the live documentation before relying on current IDE workflows after that date.
Choose the right reusable mechanism
| Mechanism | When it applies | Best fit | Scope | Migration consideration |
|---|---|---|---|---|
| IDE Rules | Persistent reusable prompt-level context | Project conventions and standing expectations | Global or workspace | No shutdown date identified in the reviewed Google page |
| IDE Workflows | When explicitly invoked | Ordered steps for a repeated process | Global or workspace | Current system is scheduled to stop working October 19, 2026 |
| Antigravity 2.0 Skills | Selected when relevant or invoked with a slash command | Reusable task knowledge, with optional resources and scripts | Global or workspace | Identified by Google as the destination for the workflow transition |
These mechanisms solve related but distinct problems: Rules supply persistent context, while Workflows and Skills are task-oriented and activated on demand or when relevant. The migration date specifically concerns the current IDE Workflows system.
Review the agent’s work before accepting it
Agent completion is not proof that code is correct. Google’s Antigravity IDE Codelab demonstrates reviewing an implementation plan and task list, reviewing or rejecting code changes, commenting on artifacts to redirect work, and using Undo changes when dissatisfied. Google’s overview describes deliverables such as plans, diffs, diagrams, screenshots, and browser recordings. A practical review loop is:
- State the request and what counts as success.
- Inspect the plan and correct misunderstandings before implementation proceeds.
- Review the proposed code diff for scope, correctness, and unintended changes.
- Run the relevant checks from the project’s established workflow.
- Inspect any walkthrough, screenshot, or browser evidence that applies to the task.
- Accept the result only when the changes and checks support the requested outcome.
These are review practices based on the controls and artifacts Google documents, not a guarantee that an agent’s output will pass your project’s tests. Google also states that Antigravity IDE is not supported for enterprise customers; see the IDE overview.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
