Turn your best AI prompts into one-click tools in Chrome
christoff12
This could be interesting
jeffbee
I would be more excited by this if there was a better permissions model for these things. For example I can think of a skill that would need access to a certain corpus of documents that I host on Google Drive, but, as far as I have been able to determine using Google's other AI products, there is no way for me to grant read-only access to that corpus without granting read-write access to all of my data on Google, which is simply too much access for my taste. There has to be something less binary than Personalization:on/off?
orwin
I hate that. I understand that it might be useful, and tbh, on personnal PC, i'm not even concerned. But it is going towards people pushing to replace XQL or other query languages with prompting in natural languages, for no good reasons. Generate your query and copy paste if you don't want to read the documentation man, but please, please keep an intermediary between the LLM and the real world data. The last time your fucking prompt gave me a "log overview" i lost 2 hours understanding what the fuck i was reading, when a query would have taken me at most 20 minutes.
Convert my AI prompt into the code for a one-click tool, let me read and share it, that would be _great_.
jampekka
The examples in TFA don't really seem suitable for code, unless that code is a wrapper for calling LLMs call.
"Health & Wellness: quickly calculating protein macros for any recipe
Shopping: generating side-by-side spec comparisons across multiple tabs
Productivity: scanning lengthy documents for important information"
skeeter2020
my most commonly repeated prompt; would be nice if the baked it into the tool itself:
"No emojis. be concise. no suggestions unless I explicitly ask for them. answer questions like the machine you are. Don't try and add personality or humour; remember you're a robot."
I like it. Have you tried putting this in your LLM system prompt?
vasco
> Don't try and add personality or humour; remember you're a robot."
> remember you're a robot."
The anthropomorphization juxtaposed to the actual command is a bit ironic.
b00ty4breakfast
need prompt macros
sva_
I'd add "no ass-kissing"
loloquwowndueo
lol I once used a similar “you’re a machine so just do as you’re told” to a prompt and it answered back: “I’m not a machine, I’m Claude a helpful assistant” and refused to do what I asked because it claimed I didn’t have the authority to make the decision I’d asked it to convey in writing.
sagarpatil
Absolutely right! You must be fun at parties .
fragrom
[dead]
marsavar
Who wants this?
nine_k
I can imagine a moderator, or a marketing person, wanting such a tool. "Respond to this post in a polite and friendly manner, thank the user for choosing our company, discovering a problem, and taking the time to report it. Promise to sort this out quickly. If the user is really angry and threatens legal action, promise an immediate refund, and shoot me an email with the summary of the issue, and all the details."
If instead of a copy-pasting spree, or setting up a whateverClaw, the user might just click a button in Chrome, it could be actually useful. (Consider a dozen such buttons.)
gardenhedge
I can immediately think of personal use cases for this.
the13
OP. & I bet some people will want to play with it at least. Maybe it'll inspire builders to build something they themselves want.
qingcharles
Me. I have a prompt I use to get alt text and caption ideas for photos. I basically copy/paste it each time. This will save a step.
PunchTornado
Jesus, I don't want to be mean, but some things that Google creates are completeyl useless...
_doctor_love
I really hope this doesn't have the same security model as Chrome Extensions!
I can see the appeal of this feature and I am generally speaking an AI booster.
On the other hand...like...wat? This feature feels way too premature and risky to let loose on the public.
decimalenough
There are no third-party Skills, you can only create your own or use Google's readymade ones.
mwkaufma
Never before have people been able to effortlessly visualize whole landing pages to tell them to put glue on pizza.
londons_explore
So much of the web has no API anymore and is hostile to robots.
The script to turn the coffee maker on when dad posts on Facebook for the first time each morning that worked in 2014 won't work anymore in 2026.
Having this sort of thing built into a mainstream browser will open up a new avenue for automation, which I think will be a good thing for breaking down data silos and being good for the world overall.
croes
Just ignore the unreliability and the waste of resources
skybrian
This sounds to me like yet another way to automate filling out forms. I had been thinking about vibe-coding a Chrome extension for one form I fill in regularly, but perhaps this is easier.
hypfer
Ah yes. Ticks all the boxes
- Becoming a Platform
- AI
- User-generated content
[list continues]
There is something comforting about seeing that the SV stopped having ideas and now just recycles and recombines the same tropes over and over again.
It's still all terrible, but it's a devil you know. You can live with that. You can skip the broken stair and duck, knowing exactly when they're trying to punch you in the face again.
Now here's hoping that eventually, they get bored and just stop entirely.
parasti
These days announcements like this just make me want to put on my tinfoil hat - what's in it for Google, though? Why make it more convenient for people to submit webpages to you?
kllrnohj
Presumably the upside for Google is they'll just lock it behind the "Google AI Plus" subscription plan if it isn't already
amelius
Yes. We desperately need more local models.
blcknight
Lots of people are flocking to Claude and ChatGPT -- and making Gemini more useful in the browser everyone already has makes a lot of sense.
More Google use, more data they gather, more ads they can show you
Honestly that would be quite good, an intelligent ad remover
that scans the page and the dom for modals and removes them.
Like a classic ad blocking tool on steroids.
hotsalad
So, bookmarklets for Chrome's AI integration?
woodydesign
My prompt collection lives in three different places right now — Raycast snippets, Apple Notes, and a Notion page that keeps growing. I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it.
The browser approach makes sense for Claude code and ChatGPT. I wonder how well it holds up once you have 50+ prompts though — finding the right one fast is the real problem for me.
qingcharles
My prompt collection simply lives in my chat history. I just hit search and type in something unique I remember.
This is cleaner, though :)
afro88
I know this was just an example, but:
> I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it
This is actually a really good use case for a skill. Then when you go "commit and push" it'll do the right thing
sublinear
It really does make you wonder why all the models seem to require that. In principle, it shouldn't be a property of LLMs, and lol no it's not an "emergent property".
embedding-shape
Post-training and "human preference" according to "data". Don't know a single developer who use these tools for work who prefer that though, but also don't know anyone who use LLMs a lot just "for fun" either, might just be vastly different preferences between the two userbases.
cherioo
LLM are a text prediction engine. Starting the prompt with “you are a helpful assistant” help make subsequent text prediction more in line of that of a helpful assistant.
OsrsNeedsf2P
Looks like it's read-only access. I'll still be using Claude Code with a Chrome MCP
ButlerianJihad
Over the past few months, more than a few Google Doodles have simply been Gemini search prompts. This was extremely underwhelming as I usually expect a fun game or some kind of clever hack to ensue. I was also rather irate that Google could simply insert some false prompt into my Gemini conversation history. "I did not say that!"
Furthermore, it led me to muse whether "Prompt Gemini for <xxx>" was a thing that any URL could do? If I went to a random malicious website, could they prompt Gemini to do something for me? If Gemini was hooked up to my Gmail, could a malicious prompt delete all my email, and all it would take is a misclick? Chilling.
tholman
Tried to visit the first domain, baydailymedia, but doesn't seem to exist... I know its unsurprising and not against the rules or even spirit of showing off your new toy, but some humor in the aria tag "Video of user creating a protein maxing Skill" and then within the video, a fat "Video for illustrative purposes" "Results may vary" "check response for accuracy"
Second video seem's more real. And yeah, again not against the rules, but dropping onto website, no ads, prompting data out of it is very in the ethos of our current "lets just do an ai" era to be relevent era.
debarshri
How can you try this out?
daveguy
How do you know which ones are your best vs your worst from day to day?
vomayank
[dead]
xuchenglan
[dead]
tracerbulletx
I know everyone hates ads or whatever, but why would anyone make content on their own website anymore if google and the browser are doing everything in their power to keep your users from interacting with your own page. Also I don't want to hear the crap about ads being too invasive, its their content, they can do that if they want, and you can not have access to their content. They have to be able to monetize the page to get viewers and its their mistake to make if they make it annoying that doesn't give everyone the right to their work.
fooker
This point naturally leads to a more general discussion.
If AI can do everything and gets everyone out of jobs, who is going to consume the ‘everything’ produced by AI for someone to pay for the AI?
I don’t think UBI is a real solution, it’s too hand wavy.
evolighting
But times have changed. You seem to be discussing the internet 10 to 20 years ago and the personal website operators of that era; but the internet today is actually... very different!
tonetheman
[dead]
dasl
their video demos were surprisingly bad. Hard to understand what they were showing.
christoff12
This could be interesting
jeffbee
I would be more excited by this if there was a better permissions model for these things. For example I can think of a skill that would need access to a certain corpus of documents that I host on Google Drive, but, as far as I have been able to determine using Google's other AI products, there is no way for me to grant read-only access to that corpus without granting read-write access to all of my data on Google, which is simply too much access for my taste. There has to be something less binary than Personalization:on/off?
orwin
I hate that. I understand that it might be useful, and tbh, on personnal PC, i'm not even concerned. But it is going towards people pushing to replace XQL or other query languages with prompting in natural languages, for no good reasons. Generate your query and copy paste if you don't want to read the documentation man, but please, please keep an intermediary between the LLM and the real world data. The last time your fucking prompt gave me a "log overview" i lost 2 hours understanding what the fuck i was reading, when a query would have taken me at most 20 minutes.
Convert my AI prompt into the code for a one-click tool, let me read and share it, that would be _great_.
jampekka
The examples in TFA don't really seem suitable for code, unless that code is a wrapper for calling LLMs call.
"Health & Wellness: quickly calculating protein macros for any recipe
Shopping: generating side-by-side spec comparisons across multiple tabs
Productivity: scanning lengthy documents for important information"
skeeter2020
my most commonly repeated prompt; would be nice if the baked it into the tool itself:
"No emojis. be concise. no suggestions unless I explicitly ask for them. answer questions like the machine you are. Don't try and add personality or humour; remember you're a robot."
I like it. Have you tried putting this in your LLM system prompt?
vasco
> Don't try and add personality or humour; remember you're a robot."
> remember you're a robot."
The anthropomorphization juxtaposed to the actual command is a bit ironic.
b00ty4breakfast
need prompt macros
sva_
I'd add "no ass-kissing"
loloquwowndueo
lol I once used a similar “you’re a machine so just do as you’re told” to a prompt and it answered back: “I’m not a machine, I’m Claude a helpful assistant” and refused to do what I asked because it claimed I didn’t have the authority to make the decision I’d asked it to convey in writing.
sagarpatil
Absolutely right! You must be fun at parties .
fragrom
[dead]
marsavar
Who wants this?
nine_k
I can imagine a moderator, or a marketing person, wanting such a tool. "Respond to this post in a polite and friendly manner, thank the user for choosing our company, discovering a problem, and taking the time to report it. Promise to sort this out quickly. If the user is really angry and threatens legal action, promise an immediate refund, and shoot me an email with the summary of the issue, and all the details."
If instead of a copy-pasting spree, or setting up a whateverClaw, the user might just click a button in Chrome, it could be actually useful. (Consider a dozen such buttons.)
gardenhedge
I can immediately think of personal use cases for this.
the13
OP. & I bet some people will want to play with it at least. Maybe it'll inspire builders to build something they themselves want.
qingcharles
Me. I have a prompt I use to get alt text and caption ideas for photos. I basically copy/paste it each time. This will save a step.
PunchTornado
Jesus, I don't want to be mean, but some things that Google creates are completeyl useless...
_doctor_love
I really hope this doesn't have the same security model as Chrome Extensions!
I can see the appeal of this feature and I am generally speaking an AI booster.
On the other hand...like...wat? This feature feels way too premature and risky to let loose on the public.
decimalenough
There are no third-party Skills, you can only create your own or use Google's readymade ones.
mwkaufma
Never before have people been able to effortlessly visualize whole landing pages to tell them to put glue on pizza.
londons_explore
So much of the web has no API anymore and is hostile to robots.
The script to turn the coffee maker on when dad posts on Facebook for the first time each morning that worked in 2014 won't work anymore in 2026.
Having this sort of thing built into a mainstream browser will open up a new avenue for automation, which I think will be a good thing for breaking down data silos and being good for the world overall.
croes
Just ignore the unreliability and the waste of resources
skybrian
This sounds to me like yet another way to automate filling out forms. I had been thinking about vibe-coding a Chrome extension for one form I fill in regularly, but perhaps this is easier.
hypfer
Ah yes. Ticks all the boxes
- Becoming a Platform
- AI
- User-generated content
[list continues]
There is something comforting about seeing that the SV stopped having ideas and now just recycles and recombines the same tropes over and over again.
It's still all terrible, but it's a devil you know. You can live with that. You can skip the broken stair and duck, knowing exactly when they're trying to punch you in the face again.
Now here's hoping that eventually, they get bored and just stop entirely.
parasti
These days announcements like this just make me want to put on my tinfoil hat - what's in it for Google, though? Why make it more convenient for people to submit webpages to you?
kllrnohj
Presumably the upside for Google is they'll just lock it behind the "Google AI Plus" subscription plan if it isn't already
amelius
Yes. We desperately need more local models.
blcknight
Lots of people are flocking to Claude and ChatGPT -- and making Gemini more useful in the browser everyone already has makes a lot of sense.
More Google use, more data they gather, more ads they can show you
Honestly that would be quite good, an intelligent ad remover
that scans the page and the dom for modals and removes them.
Like a classic ad blocking tool on steroids.
hotsalad
So, bookmarklets for Chrome's AI integration?
woodydesign
My prompt collection lives in three different places right now — Raycast snippets, Apple Notes, and a Notion page that keeps growing. I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it.
The browser approach makes sense for Claude code and ChatGPT. I wonder how well it holds up once you have 50+ prompts though — finding the right one fast is the real problem for me.
qingcharles
My prompt collection simply lives in my chat history. I just hit search and type in something unique I remember.
This is cleaner, though :)
afro88
I know this was just an example, but:
> I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it
This is actually a really good use case for a skill. Then when you go "commit and push" it'll do the right thing
sublinear
It really does make you wonder why all the models seem to require that. In principle, it shouldn't be a property of LLMs, and lol no it's not an "emergent property".
embedding-shape
Post-training and "human preference" according to "data". Don't know a single developer who use these tools for work who prefer that though, but also don't know anyone who use LLMs a lot just "for fun" either, might just be vastly different preferences between the two userbases.
cherioo
LLM are a text prediction engine. Starting the prompt with “you are a helpful assistant” help make subsequent text prediction more in line of that of a helpful assistant.
OsrsNeedsf2P
Looks like it's read-only access. I'll still be using Claude Code with a Chrome MCP
ButlerianJihad
Over the past few months, more than a few Google Doodles have simply been Gemini search prompts. This was extremely underwhelming as I usually expect a fun game or some kind of clever hack to ensue. I was also rather irate that Google could simply insert some false prompt into my Gemini conversation history. "I did not say that!"
Furthermore, it led me to muse whether "Prompt Gemini for <xxx>" was a thing that any URL could do? If I went to a random malicious website, could they prompt Gemini to do something for me? If Gemini was hooked up to my Gmail, could a malicious prompt delete all my email, and all it would take is a misclick? Chilling.
tholman
Tried to visit the first domain, baydailymedia, but doesn't seem to exist... I know its unsurprising and not against the rules or even spirit of showing off your new toy, but some humor in the aria tag "Video of user creating a protein maxing Skill" and then within the video, a fat "Video for illustrative purposes" "Results may vary" "check response for accuracy"
Second video seem's more real. And yeah, again not against the rules, but dropping onto website, no ads, prompting data out of it is very in the ethos of our current "lets just do an ai" era to be relevent era.
debarshri
How can you try this out?
daveguy
How do you know which ones are your best vs your worst from day to day?
vomayank
[dead]
xuchenglan
[dead]
tracerbulletx
I know everyone hates ads or whatever, but why would anyone make content on their own website anymore if google and the browser are doing everything in their power to keep your users from interacting with your own page. Also I don't want to hear the crap about ads being too invasive, its their content, they can do that if they want, and you can not have access to their content. They have to be able to monetize the page to get viewers and its their mistake to make if they make it annoying that doesn't give everyone the right to their work.
fooker
This point naturally leads to a more general discussion.
If AI can do everything and gets everyone out of jobs, who is going to consume the ‘everything’ produced by AI for someone to pay for the AI?
I don’t think UBI is a real solution, it’s too hand wavy.
evolighting
But times have changed. You seem to be discussing the internet 10 to 20 years ago and the personal website operators of that era; but the internet today is actually... very different!
tonetheman
[dead]
dasl
their video demos were surprisingly bad. Hard to understand what they were showing.
This could be interesting
I would be more excited by this if there was a better permissions model for these things. For example I can think of a skill that would need access to a certain corpus of documents that I host on Google Drive, but, as far as I have been able to determine using Google's other AI products, there is no way for me to grant read-only access to that corpus without granting read-write access to all of my data on Google, which is simply too much access for my taste. There has to be something less binary than Personalization:on/off?
I hate that. I understand that it might be useful, and tbh, on personnal PC, i'm not even concerned. But it is going towards people pushing to replace XQL or other query languages with prompting in natural languages, for no good reasons. Generate your query and copy paste if you don't want to read the documentation man, but please, please keep an intermediary between the LLM and the real world data. The last time your fucking prompt gave me a "log overview" i lost 2 hours understanding what the fuck i was reading, when a query would have taken me at most 20 minutes.
Convert my AI prompt into the code for a one-click tool, let me read and share it, that would be _great_.
The examples in TFA don't really seem suitable for code, unless that code is a wrapper for calling LLMs call.
"Health & Wellness: quickly calculating protein macros for any recipe
Shopping: generating side-by-side spec comparisons across multiple tabs
Productivity: scanning lengthy documents for important information"
my most commonly repeated prompt; would be nice if the baked it into the tool itself:
"No emojis. be concise. no suggestions unless I explicitly ask for them. answer questions like the machine you are. Don't try and add personality or humour; remember you're a robot."
try to add it here: https://gemini.google.com/saved-info
I like it. Have you tried putting this in your LLM system prompt?
> Don't try and add personality or humour; remember you're a robot."
> remember you're a robot."
The anthropomorphization juxtaposed to the actual command is a bit ironic.
need prompt macros
I'd add "no ass-kissing"
lol I once used a similar “you’re a machine so just do as you’re told” to a prompt and it answered back: “I’m not a machine, I’m Claude a helpful assistant” and refused to do what I asked because it claimed I didn’t have the authority to make the decision I’d asked it to convey in writing.
Absolutely right! You must be fun at parties .
[dead]
Who wants this?
I can imagine a moderator, or a marketing person, wanting such a tool. "Respond to this post in a polite and friendly manner, thank the user for choosing our company, discovering a problem, and taking the time to report it. Promise to sort this out quickly. If the user is really angry and threatens legal action, promise an immediate refund, and shoot me an email with the summary of the issue, and all the details."
If instead of a copy-pasting spree, or setting up a whateverClaw, the user might just click a button in Chrome, it could be actually useful. (Consider a dozen such buttons.)
I can immediately think of personal use cases for this.
OP. & I bet some people will want to play with it at least. Maybe it'll inspire builders to build something they themselves want.
Me. I have a prompt I use to get alt text and caption ideas for photos. I basically copy/paste it each time. This will save a step.
Jesus, I don't want to be mean, but some things that Google creates are completeyl useless...
I really hope this doesn't have the same security model as Chrome Extensions!
I can see the appeal of this feature and I am generally speaking an AI booster.
On the other hand...like...wat? This feature feels way too premature and risky to let loose on the public.
There are no third-party Skills, you can only create your own or use Google's readymade ones.
Never before have people been able to effortlessly visualize whole landing pages to tell them to put glue on pizza.
So much of the web has no API anymore and is hostile to robots.
The script to turn the coffee maker on when dad posts on Facebook for the first time each morning that worked in 2014 won't work anymore in 2026.
Having this sort of thing built into a mainstream browser will open up a new avenue for automation, which I think will be a good thing for breaking down data silos and being good for the world overall.
Just ignore the unreliability and the waste of resources
This sounds to me like yet another way to automate filling out forms. I had been thinking about vibe-coding a Chrome extension for one form I fill in regularly, but perhaps this is easier.
Ah yes. Ticks all the boxes
- Becoming a Platform
- AI
- User-generated content
[list continues]
There is something comforting about seeing that the SV stopped having ideas and now just recycles and recombines the same tropes over and over again.
It's still all terrible, but it's a devil you know. You can live with that. You can skip the broken stair and duck, knowing exactly when they're trying to punch you in the face again.
Now here's hoping that eventually, they get bored and just stop entirely.
These days announcements like this just make me want to put on my tinfoil hat - what's in it for Google, though? Why make it more convenient for people to submit webpages to you?
Presumably the upside for Google is they'll just lock it behind the "Google AI Plus" subscription plan if it isn't already
Yes. We desperately need more local models.
Lots of people are flocking to Claude and ChatGPT -- and making Gemini more useful in the browser everyone already has makes a lot of sense.
More Google use, more data they gather, more ads they can show you
>what's in it for google
gemini is a paid product.
I need skill to block ads
https://www.firefox.com/ + https://addons.mozilla.org/en-US/firefox/addon/ublock-origin... + https://www.xda-developers.com/switched-from-pi-hole-to-unbo...
Honestly that would be quite good, an intelligent ad remover that scans the page and the dom for modals and removes them. Like a classic ad blocking tool on steroids.
So, bookmarklets for Chrome's AI integration?
My prompt collection lives in three different places right now — Raycast snippets, Apple Notes, and a Notion page that keeps growing. I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it.
The browser approach makes sense for Claude code and ChatGPT. I wonder how well it holds up once you have 50+ prompts though — finding the right one fast is the real problem for me.
My prompt collection simply lives in my chat history. I just hit search and type in something unique I remember.
This is cleaner, though :)
I know this was just an example, but:
> I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it
This is actually a really good use case for a skill. Then when you go "commit and push" it'll do the right thing
It really does make you wonder why all the models seem to require that. In principle, it shouldn't be a property of LLMs, and lol no it's not an "emergent property".
Post-training and "human preference" according to "data". Don't know a single developer who use these tools for work who prefer that though, but also don't know anyone who use LLMs a lot just "for fun" either, might just be vastly different preferences between the two userbases.
LLM are a text prediction engine. Starting the prompt with “you are a helpful assistant” help make subsequent text prediction more in line of that of a helpful assistant.
Looks like it's read-only access. I'll still be using Claude Code with a Chrome MCP
Over the past few months, more than a few Google Doodles have simply been Gemini search prompts. This was extremely underwhelming as I usually expect a fun game or some kind of clever hack to ensue. I was also rather irate that Google could simply insert some false prompt into my Gemini conversation history. "I did not say that!"
Furthermore, it led me to muse whether "Prompt Gemini for <xxx>" was a thing that any URL could do? If I went to a random malicious website, could they prompt Gemini to do something for me? If Gemini was hooked up to my Gmail, could a malicious prompt delete all my email, and all it would take is a misclick? Chilling.
Tried to visit the first domain, baydailymedia, but doesn't seem to exist... I know its unsurprising and not against the rules or even spirit of showing off your new toy, but some humor in the aria tag "Video of user creating a protein maxing Skill" and then within the video, a fat "Video for illustrative purposes" "Results may vary" "check response for accuracy"
Second video seem's more real. And yeah, again not against the rules, but dropping onto website, no ads, prompting data out of it is very in the ethos of our current "lets just do an ai" era to be relevent era.
How can you try this out?
How do you know which ones are your best vs your worst from day to day?
[dead]
[dead]
I know everyone hates ads or whatever, but why would anyone make content on their own website anymore if google and the browser are doing everything in their power to keep your users from interacting with your own page. Also I don't want to hear the crap about ads being too invasive, its their content, they can do that if they want, and you can not have access to their content. They have to be able to monetize the page to get viewers and its their mistake to make if they make it annoying that doesn't give everyone the right to their work.
This point naturally leads to a more general discussion.
If AI can do everything and gets everyone out of jobs, who is going to consume the ‘everything’ produced by AI for someone to pay for the AI?
I don’t think UBI is a real solution, it’s too hand wavy.
But times have changed. You seem to be discussing the internet 10 to 20 years ago and the personal website operators of that era; but the internet today is actually... very different!
[dead]
their video demos were surprisingly bad. Hard to understand what they were showing.
This could be interesting
I would be more excited by this if there was a better permissions model for these things. For example I can think of a skill that would need access to a certain corpus of documents that I host on Google Drive, but, as far as I have been able to determine using Google's other AI products, there is no way for me to grant read-only access to that corpus without granting read-write access to all of my data on Google, which is simply too much access for my taste. There has to be something less binary than Personalization:on/off?
I hate that. I understand that it might be useful, and tbh, on personnal PC, i'm not even concerned. But it is going towards people pushing to replace XQL or other query languages with prompting in natural languages, for no good reasons. Generate your query and copy paste if you don't want to read the documentation man, but please, please keep an intermediary between the LLM and the real world data. The last time your fucking prompt gave me a "log overview" i lost 2 hours understanding what the fuck i was reading, when a query would have taken me at most 20 minutes.
Convert my AI prompt into the code for a one-click tool, let me read and share it, that would be _great_.
The examples in TFA don't really seem suitable for code, unless that code is a wrapper for calling LLMs call.
"Health & Wellness: quickly calculating protein macros for any recipe
Shopping: generating side-by-side spec comparisons across multiple tabs
Productivity: scanning lengthy documents for important information"
my most commonly repeated prompt; would be nice if the baked it into the tool itself:
"No emojis. be concise. no suggestions unless I explicitly ask for them. answer questions like the machine you are. Don't try and add personality or humour; remember you're a robot."
try to add it here: https://gemini.google.com/saved-info
I like it. Have you tried putting this in your LLM system prompt?
> Don't try and add personality or humour; remember you're a robot."
> remember you're a robot."
The anthropomorphization juxtaposed to the actual command is a bit ironic.
need prompt macros
I'd add "no ass-kissing"
lol I once used a similar “you’re a machine so just do as you’re told” to a prompt and it answered back: “I’m not a machine, I’m Claude a helpful assistant” and refused to do what I asked because it claimed I didn’t have the authority to make the decision I’d asked it to convey in writing.
Absolutely right! You must be fun at parties .
[dead]
Who wants this?
I can imagine a moderator, or a marketing person, wanting such a tool. "Respond to this post in a polite and friendly manner, thank the user for choosing our company, discovering a problem, and taking the time to report it. Promise to sort this out quickly. If the user is really angry and threatens legal action, promise an immediate refund, and shoot me an email with the summary of the issue, and all the details."
If instead of a copy-pasting spree, or setting up a whateverClaw, the user might just click a button in Chrome, it could be actually useful. (Consider a dozen such buttons.)
I can immediately think of personal use cases for this.
OP. & I bet some people will want to play with it at least. Maybe it'll inspire builders to build something they themselves want.
Me. I have a prompt I use to get alt text and caption ideas for photos. I basically copy/paste it each time. This will save a step.
Jesus, I don't want to be mean, but some things that Google creates are completeyl useless...
I really hope this doesn't have the same security model as Chrome Extensions!
I can see the appeal of this feature and I am generally speaking an AI booster.
On the other hand...like...wat? This feature feels way too premature and risky to let loose on the public.
There are no third-party Skills, you can only create your own or use Google's readymade ones.
Never before have people been able to effortlessly visualize whole landing pages to tell them to put glue on pizza.
So much of the web has no API anymore and is hostile to robots.
The script to turn the coffee maker on when dad posts on Facebook for the first time each morning that worked in 2014 won't work anymore in 2026.
Having this sort of thing built into a mainstream browser will open up a new avenue for automation, which I think will be a good thing for breaking down data silos and being good for the world overall.
Just ignore the unreliability and the waste of resources
This sounds to me like yet another way to automate filling out forms. I had been thinking about vibe-coding a Chrome extension for one form I fill in regularly, but perhaps this is easier.
Ah yes. Ticks all the boxes
- Becoming a Platform
- AI
- User-generated content
[list continues]
There is something comforting about seeing that the SV stopped having ideas and now just recycles and recombines the same tropes over and over again.
It's still all terrible, but it's a devil you know. You can live with that. You can skip the broken stair and duck, knowing exactly when they're trying to punch you in the face again.
Now here's hoping that eventually, they get bored and just stop entirely.
These days announcements like this just make me want to put on my tinfoil hat - what's in it for Google, though? Why make it more convenient for people to submit webpages to you?
Presumably the upside for Google is they'll just lock it behind the "Google AI Plus" subscription plan if it isn't already
Yes. We desperately need more local models.
Lots of people are flocking to Claude and ChatGPT -- and making Gemini more useful in the browser everyone already has makes a lot of sense.
More Google use, more data they gather, more ads they can show you
>what's in it for google
gemini is a paid product.
I need skill to block ads
https://www.firefox.com/ + https://addons.mozilla.org/en-US/firefox/addon/ublock-origin... + https://www.xda-developers.com/switched-from-pi-hole-to-unbo...
Honestly that would be quite good, an intelligent ad remover that scans the page and the dom for modals and removes them. Like a classic ad blocking tool on steroids.
So, bookmarklets for Chrome's AI integration?
My prompt collection lives in three different places right now — Raycast snippets, Apple Notes, and a Notion page that keeps growing. I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it.
The browser approach makes sense for Claude code and ChatGPT. I wonder how well it holds up once you have 50+ prompts though — finding the right one fast is the real problem for me.
My prompt collection simply lives in my chat history. I just hit search and type in something unique I remember.
This is cleaner, though :)
I know this was just an example, but:
> I know I wrote a good one for my git commit/push flow somewhere, but finding it when I need it usually takes longer than just rewriting it
This is actually a really good use case for a skill. Then when you go "commit and push" it'll do the right thing
It really does make you wonder why all the models seem to require that. In principle, it shouldn't be a property of LLMs, and lol no it's not an "emergent property".
Post-training and "human preference" according to "data". Don't know a single developer who use these tools for work who prefer that though, but also don't know anyone who use LLMs a lot just "for fun" either, might just be vastly different preferences between the two userbases.
LLM are a text prediction engine. Starting the prompt with “you are a helpful assistant” help make subsequent text prediction more in line of that of a helpful assistant.
Looks like it's read-only access. I'll still be using Claude Code with a Chrome MCP
Over the past few months, more than a few Google Doodles have simply been Gemini search prompts. This was extremely underwhelming as I usually expect a fun game or some kind of clever hack to ensue. I was also rather irate that Google could simply insert some false prompt into my Gemini conversation history. "I did not say that!"
Furthermore, it led me to muse whether "Prompt Gemini for <xxx>" was a thing that any URL could do? If I went to a random malicious website, could they prompt Gemini to do something for me? If Gemini was hooked up to my Gmail, could a malicious prompt delete all my email, and all it would take is a misclick? Chilling.
Tried to visit the first domain, baydailymedia, but doesn't seem to exist... I know its unsurprising and not against the rules or even spirit of showing off your new toy, but some humor in the aria tag "Video of user creating a protein maxing Skill" and then within the video, a fat "Video for illustrative purposes" "Results may vary" "check response for accuracy"
Second video seem's more real. And yeah, again not against the rules, but dropping onto website, no ads, prompting data out of it is very in the ethos of our current "lets just do an ai" era to be relevent era.
How can you try this out?
How do you know which ones are your best vs your worst from day to day?
[dead]
[dead]
I know everyone hates ads or whatever, but why would anyone make content on their own website anymore if google and the browser are doing everything in their power to keep your users from interacting with your own page. Also I don't want to hear the crap about ads being too invasive, its their content, they can do that if they want, and you can not have access to their content. They have to be able to monetize the page to get viewers and its their mistake to make if they make it annoying that doesn't give everyone the right to their work.
This point naturally leads to a more general discussion.
If AI can do everything and gets everyone out of jobs, who is going to consume the ‘everything’ produced by AI for someone to pay for the AI?
I don’t think UBI is a real solution, it’s too hand wavy.
But times have changed. You seem to be discussing the internet 10 to 20 years ago and the personal website operators of that era; but the internet today is actually... very different!
[dead]
their video demos were surprisingly bad. Hard to understand what they were showing.