Antigravity CLI's Killer Features That Make Gemini CLI Obsolete
This video walks through migrating from Gemini CLI to Google's new Antigravity CLI and demonstrates its slash commands by building a single-file HTML workout logger called Lift in the terminal.
AI with Surya11 minTranscript found
Quick learning frame
Read this before watching.
Creative automation uses agents to accelerate production while keeping human taste in story, pacing, selection, and critique.
New playlist item from AI with Surya; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: Operating Antigravity CLI's agentic slash-command workflow (grill me, goal, rewind) to build and iterate on a small app from the terminal.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Brief
02Source
03Generation
04Selection
05Edit
06Taste Review
Deep lesson
Turn this video into working knowledge.
2,111 cleaned transcript words reviewed across 588 timed caption segments.
Thesis
Antigravity CLI's Killer Features That Make Gemini CLI Obsolete teaches a practical creative automation move: This video walks through migrating from Gemini CLI to Google's new Antigravity CLI and demonstrates its slash commands by building a single-file HTML workout logger called Lift in the terminal.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
1:37
Rebuild, not rename
“machine. Your real system stays untouched. Then, they also introduced parallel sub-agents. The agent can spin up at once, each with their own context, doing research and proposing in parallel. Then, they have {slash} fork, which branches your...”
Antigravity CLI is a Go rebuild of Gemini CLI that runs faster and async by default, with a one-command migration path; Gemini CLI stops serving requests after June 18th. Run the install command, then execute the single migration command to bring your existing Gemini CLI settings and extensions over before the cutoff.
3:49
Grill me command
“what you want to do, and you just want agent to continue and build without asking you multiple times, you will be able to use goal. And then, grill me is where you will be asking agent to...”
The /grill me command makes the agent interrogate you with clarifying questions (UI style, autosuggestions, etc.) before writing code, so it captures intent up front instead of wasting iterations guessing. Start a build with /grill me and a detailed prompt, then answer its UI and feature questions and inspect the generated walkthrough.md and implementation plan artifacts.
7:00
Goal then rewind
“go through and look at what it has created. So, now it has started to actually build more and you can always like expand on it, right? So, I again come back and show you what it has...”
/goal gives the agent full autonomy to ship a specific change with no questions, while /rewind undoes an entire agent turn (not just a file or edit) like it never happened. Use /goal to add a new feature panel to your app without prompts, then use /rewind to roll the whole turn back and confirm the change disappears on refresh.
01
Brief
Start with this video's job: This video walks through migrating from Gemini CLI to Google's new Antigravity CLI and demonstrates its slash commands by building a single-file HTML workout logger called Lift in the terminal. Treat "Brief" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:37, where the video says: “machine. Your real system stays untouched. Then, they also introduced parallel sub-agents. The agent can spin up at once, each with their own context, doing research and proposing in parallel. Then, they have {slash} fork, which branches your...”
02
Source
Use "Source" to locate the part of the creative automation workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 3:49, where the video says: “what you want to do, and you just want agent to continue and build without asking you multiple times, you will be able to use goal. And then, grill me is where you will be asking agent to...”
03
Generation
Turn "Generation" into the reusable artifact for this lesson: A creative workflow board with critique criteria and review checkpoints. This is where watching becomes something you can inspect and reuse.
04
Selection
Use "Selection" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Edit
Use "Edit" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Taste Review
Use "Taste Review" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a creative workflow board with critique criteria and review checkpoints..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video walks through migrating from Gemini CLI to Google's new Antigravity CLI and demonstrates its slash commands by building a single-file HTML workout logger called Lift in the terminal.
02
Explain the practical stakes without hype: New playlist item from AI with Surya; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source -> Generation -> Selection -> Edit -> Taste Review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative workflow board with critique criteria and review checkpoints.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: Antigravity CLI's Killer Features That Make Gemini CLI Obsolete
- URL: https://www.youtube.com/watch?v=EFND9o4jiKY
- Topic: Creative Automation
- My current learning frame: Install Antigravity CLI and rebuild the Lift workout logger as a single local HTML file using /grill me to scope it, /goal to add a 'this week' panel, and /rewind to undo that turn.
- Why this matters: New playlist item from AI with Surya; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:00 / Evidence 1: "So, Google has replaced Gemini CLI with antigravity CLI. And I feel that this was a long time coming. And the moment that dropped, a lot of us had the same questions. >> Is this just a rename?"
- 1:37 / Evidence 2: "machine. Your real system stays untouched. Then, they also introduced parallel sub-agents. The agent can spin up at once, each with their own context, doing research and proposing in parallel. Then, they have {slash} fork, which branches your..."
- 3:49 / Evidence 3: "what you want to do, and you just want agent to continue and build without asking you multiple times, you will be able to use goal. And then, grill me is where you will be asking agent to..."
- 5:21 / Evidence 4: "build it, it's going to start building and it's going to give you the confirmation of the implementation progress. So, that's what you're seeing what is happening on the screen. I I feel grill me is a pretty..."
- 7:00 / Evidence 5: "go through and look at what it has created. So, now it has started to actually build more and you can always like expand on it, right? So, I again come back and show you what it has..."
- 9:50 / Evidence 6: "things that are really cool is, as I mentioned, the gold grill me and the stuff where you're also able to interact with it while you are working. So, for example, this "By the way" command, right? So,..."
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative workflow board with critique criteria and review checkpoints.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Brief -> Source -> Generation -> Selection -> Edit -> Taste Review
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "Antigravity CLI's Killer Features That Make Gemini CLI Obsolete", not a generic Creative Automation essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a creative workflow board with critique criteria and review checkpoints..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
The video stresses Antigravity CLI is not just a rename of Gemini CLI. What is it technically, and what hard deadline does it give Gemini CLI users?
Contrast what /grill me and /goal each do to the agent's behavior, and when you'd choose /goal.
What does /rewind undo, and how is its scope different from a normal file undo?
Source shelf
Use the video as a doorway, then verify with primary sources.
