Don't Ship Skills Without Evals — Philipp Schmid, Google DeepMind

[music] Yes, so hi everyone. My name is Philip.

I'm based out of Germany. I'm part of the Google DeepMind team mostly working on Gemini API and agents. And we are going to talk about why you should not ship skills without eval. And maybe

before we start, I need a little bit of your help. So if you could raise your

your help. So if you could raise your hands if you use coding agents to write code.

So yeah, hopefully every every hand goes up, right? And do you use skills with

up, right? And do you use skills with it?

Okay.

Do you have evals for those skills?

Okay, yeah, that's um not a lot of hands. Everyone uses skills, no one has

hands. Everyone uses skills, no one has evals. Hopefully we can fix that today.

evals. Hopefully we can fix that today.

And like very important is like why checks fail in productions. And um Skill Bench is a very popular and nice like eval or benchmark which um index like

over like 50,000 skills from like it up and like try to look into him and almost none of those skills had evals. Most of

them were AI written um not really tested and it's very hard to know if your skill is good or bad because like agents are really non-deterministic. So

you might not know if your uh task fails because your skill is bad or if your task fails because it's way too challenging for the model. So

um very important um before we go into it there's I want to like really make sure that we know the difference between the agents we use and the agents we build. Um most of us use agents for

build. Um most of us use agents for writing code, doing productivity work.

That's the agents we use. It's like

anti-gravity, cursor, Claude code. And

there are you are the engineer and you have context about skills, right? If you

write some prompt to I don't know, like help me build a new Gemini API feature.

And if your agent does not invoke the skill on the first time, you will notice it very quickly. You stop your your task and reprompt it or like use slash commands for for triggering those

skills. When you build an agent inside

skills. When you build an agent inside your application for consumer or customers, they have no idea about what a skill is. They don't start their

prompt with use customer support skill to like help me refund or use refund skill to help me solve my problem. So,

there's a big difference between the agents we use and how we use skills and the agents we build and how our customers might want to use skills in like the context there. And what is a

skill? I mean, every one of us knows

skill? I mean, every one of us knows hopefully in by now what a skill is.

It's like basically really a folder with a skills.md file in it and then some

a skills.md file in it and then some additional assets to make that skill really work. And the big difference with

really work. And the big difference with skills is that they work on progressive disclosure. So, most of the skills start

disclosure. So, most of the skills start very small. So, you have the title and a

very small. So, you have the title and a description. The description is normally

description. The description is normally part of the model's context. So, the model knows when to use the skill. Second layer is we have a skills body with more instructions, more details, and

hopefully more references to external files. And then you can really go deep

files. And then you can really go deep in those reference files where there's all of the context the model needs to discover to to solve the task.

And I like to differentiate between two kinds of skills. So, they are capability skills and preference skills. Capability

skills teach models something they cannot do consistently at the moment.

Maybe it's like, I don't know, like tracing some logs, creating a new React app. And those capability skills are

app. And those capability skills are temporary. So, the better our model

temporary. So, the better our model gets, the more likely it is that we can remove those skills. And Evals will tell us when we can retire skill and when not. And then we have preference skills.

not. And then we have preference skills.

Those are more durable, mostly encode some references. So, if you have a

some references. So, if you have a specific workflow in your team or a specific style language or other preferences which are very specific to your company,

Um will have or create preference skills and those uh preference skills are then protected with e-walls where because most of like the foundation models might not uh integrate the knowledge which is

very specific to your use case or your domain. And preference skills are very

domain. And preference skills are very valuable, so we really want to make sure that those are working and we don't like update our agents to uh degrade performance.

So, do skills work? Yes, they do work and I going back to a skills bench which has an update of 1.1 which has evaluated all kinds of open and closed models in

different harnesses showing that skills on average improve the performance by roughly 15%. Skills bench covers around

roughly 15%. Skills bench covers around 100 different tasks uh based on like coding and also productivity across different languages. It's uh openly

different languages. It's uh openly available and they have a very nice website, a very nice leaderboard, are also very open for uh community contributions. And then they did a

contributions. And then they did a second analysis on self-generated or AI-generated skills, right? It's very

easy if you are in a coding agent and you work on something, tell the model create a skill and then it writes a skill.md file. We maybe look at it very

skill.md file. We maybe look at it very closely. It roughly covers what we want

closely. It roughly covers what we want to do and then we just accept it and start using it. And what I found out is that human-written skills are the best we can

provide.

Uh AI-generated skills can uh impact performance negatively. And that skills

performance negatively. And that skills or skills.md files should be below 500

or skills.md files should be below 500 lines of words. So, if you have your laptop open and have a skill available, if you open that and if it's above 500 lines, you should definitely look at the

skill after our session.

And um the last topic about what is a skill and how a skill works, uh we have different ways of triggering our skill, right? We

can have a model-triggered skill meaning uh based on the context and the description, the model decides to use or read a skill to, uh uh, get more context to solve a task. And

then there are user-invoked skills. And

I think people underestimate how powerful user-invoked skills are. Um,

and they most of the time just accept, uh, the overhead by pro- like adding it into the context. I have like many user-invoked

context. I have like many user-invoked skills for more workflow type of tasks like creating a pull request, uh, staging documentation, and all like of the very uh,

normal dev work which could be run in a script should most likely be a user-invoked, uh, skill. And when you build agents for customer, you don't have those user-invoked skills. We are

only working in the model-invoked skills, and that's where we are like focusing on for the small eval section we are going to look in a second. So,

writing skills, um, is an important topic. Uh, we're going to look at eight,

topic. Uh, we're going to look at eight, um, examples on how or tips on how you can write good skills. And most importantly, if you work with model-invoked skills is

the description because the description are most of the time two sentences we provide to the system instruction to help the model know when it should use a skill or not.

And it's bad if your description is too weak because then it might trigger too often or the it might not be triggered if you need it. So,

very important is the the why and the how for the model. So, why it should use that skill and then how it should use that skill. Um, very common is like use

that skill. Um, very common is like use that skill if you are working on a React application, for example. And then, of course, the when.

And we should write directives instead of essays. So, we should not say

of essays. So, we should not say something like, "Hey, the Interactions API is recommended for multi-chat um multi-chat because it handles like session state and it's like where you

should be way more directive like use the Interactions API if you're working on like a chat application. So, you need to give the model like clear instructions and directives on when it

should use the skill and how it should use the skill. And

similar to what we have seen in the skills bench results, we should keep the skill lean and layer information. So,

the description is the cost you always pay on every model invocation. So, on

every model call, the description is part of the model context. So, you

always pay that 100 200 tokens cost and you don't want to have a super long description because then you always have to pay that. When you have a very long skill MD file, it will be always read into context when the model decides to

read the the skill or to use the skill.

Uh which can be expensive as well.

That's why we want to keep it as concise as possible, but still include all of the reference and details for the model to solve the task. And then of course, the layer three is like we can have those reference files where the model

needs to like um go really deep into a very specific task. And a good example for this is like if you are working in like maybe a multi-cloud environment and you have a skill to deploy your

application, you might need instruction to deploying to AWS and deploying to Google Cloud. Those should not be part

Google Cloud. Those should not be part of your skill MD file. Those should be references. That you have a reference

references. That you have a reference for AWS, reference for Google Cloud, maybe a reference for Azure so that the model can basically explore based on the context where it should go to get all of that information.

Then we should set the right level of freedom. Um I see many people

freedom. Um I see many people very clearly describing the exact workflow in a skill. Step one, go there.

Step two, do this. Step three, do this.

If you have those type of use cases, you should not use skills. You maybe you should write a script because if the the process or the workflow is always the same, you don't need to waste models and

tokens for that exercise. You can create a script. You can tell the model use

a script. You can tell the model use that script to run a specific workflow.

So, rather define goals and constraints.

So, if you need to like deploy to your update or stage your documentation, describe how the model can do that. Or

like for your database updating a config, you should not say like read the config, update the port, and then like deploy again. The model knows what to

deploy again. The model knows what to do. Just like hey, if we need to change

do. Just like hey, if we need to change the config, here's the file, make the change. Then uh don't skip negative

change. Then uh don't skip negative cases. So, we always look at the when we

cases. So, we always look at the when we want to use this skill, but most of the time we don't look at when we don't want to use this skill. So, if we have a description for our skill which says use

it for web development tasks, it might over trigger. Maybe you work with React,

trigger. Maybe you work with React, maybe you also work with Angular, and the model always loads the skill if you are working in like a web development environment, but if you are very specific for like hey, only use that

skill for React components or for Tailwind CSS, then the model knows hey, that's very specific for one to use. And

with Evals, we can also identify those.

Um And then test early. So, that's what we are going to look at. We should really try to test when you create a new skill.

Always try to create 10 of 20 prompts. I

like to create five for like the happy path. So, when do I want to use that

path. So, when do I want to use that skill? Five when I don't want to use

skill? Five when I don't want to use that skill just to make sure the model is not over triggering the skill and confusing itself. And then if you have

confusing itself. And then if you have already some customer or production traces, try to include those as well because nothing is better than than real-world data.

And then tip seven which is quite new and I have to give all credits to Matt. So, if you don't know Matt, he's a great AI educator and you should definitely follow him. He published a tweet and

follow him. He published a tweet and also a skill on like killing all of the no-ops. And what he found is that AI

no-ops. And what he found is that AI generated skills tend to include a lot of no-ops. And no-ops basically is an

of no-ops. And no-ops basically is an instruction which does nothing to change the agent's behavior. It's like before making an implementation easy to read.

Like the model knows how it when it should make something easy to read or write clear high-quality code. I mean,

like that's what we expect from the model to do without telling it really.

So, um definitely look at those no-ops.

He have has published a very good skill in in his like skills repository. Uh and

then last but not least, uh know when you should retire skill. Um skills are not there to live forever. Models get

better, behaviors change, expectation change, um the environment changes. So,

um always try to run evals with and without the skill enabled. And if the model achieves the performance without even like triggering the skill, you know you can retire that skill, save the cost

uh for your tokens, and then also um don't keep like it redundant. So, save

cost at the end and maintenance also as well. And to look at a little bit of a

well. And to look at a little bit of a practical example and also how you can create your own small eval or eval harness for skills. Um earlier this year

we wanted to create a new skill for the Gemini Interactions API. So, the Gemini Interactions API is our new interface for working with Gemini models and with agents. And the Interactions API was

agents. And the Interactions API was released after the last training of Gemini. So, the model or Gemini 3 and

Gemini. So, the model or Gemini 3 and like 3.1 or even 3.5 has no context about what is the the Gemini Interactions API. So, we

decided, "Okay, let's look uh at creating a skill to help the model create good code for the Interactions API, to use the latest models." And to

do that, we created 117 test cases.

Those are uh based on like data we see uh from real users trying to generate uh Gemini code from um synthetic generated uh test cases, and also from like

feedback we see people like, "Hey, the model is like using Gemini 2.0 even if we are already on 3.0." And the the end result was that we improved the the

performance up to like almost 90% for generating valid interactions API code with the latest Gemini models. And to do this we

basically only needed like two very simple uh assets. So, one of that was a JSON file with all of our test cases.

And it's very like no clear structure.

It's like, "Hey, we have a prompt."

That's basically what we expect the user to provide. We have a language because

to provide. We have a language because we wanted to test the skill against TypeScript and Python.

Uh we have a should trigger. That's

basically there to tell us if the agent should read the skill or not read the skill. And then we have different

skill. And then we have different expected checks. Uh we look at them in a

expected checks. Uh we look at them in a little bit. Those are basically uh very

little bit. Those are basically uh very simple asserts uh for that prompt if it should trigger or not. And then we have a very basic

or not. And then we have a very basic Python script which runs a coding agent.

In this case, it was the Gemini CLI which uh passes the output and returns runs it so we can like take a look at the the outcome whether we have valid

code for the interactions API or not.

And uh most of the tests or evals for skills can be regex. It's like very amazing how good

regex. It's like very amazing how good of regex you can write using coding agents. And it's really for us it was

agents. And it's really for us it was all about, "Okay, do we use the correct SDK? Do we use the correct um model? Do

SDK? Do we use the correct um model? Do

we use the correct methods? Do we use any old patterns?" And we created um very basic asserts for all of those cases, which are very cheap to run. So,

we can run our skill against the evals many times. So, if a new model releases,

many times. So, if a new model releases, we have a very easy way to update those asserts to the latest model IDs. And

it's very cheap to run for it well because we don't need to use like LLM as a judge. But of course, you can use LLM

a judge. But of course, you can use LLM as a judge if you have like more complex skills which need to look at the whole traces or the whole steps taken. And a

very easy case is like you just create LLM as a judge with a rubric on like what you want to look at, and then like take the output, put it through the LLM as a judge, try to get a pass or a fail,

and then if it fails, look at the data, and then like try to um improve your skill based on that.

And that's also how we now uh eval skills at Google DeepMind. So, the

we don't use YAML, but it's like just as like uh an example. Uh we have um tests or evals alongside every skill we have internally at Google DeepMind.

Um every test has multiple cases with like a prompt. Uh we all run them in like clear workspaces, so you can define your workspace or environment if it should include additional files like

your application environments. You have

uh startup commands, which basically preloads or installs libraries into the environment. And then you have script

environment. And then you have script evals or data. Those are those regex where we look at all of the traces to see what the skill triggered, was a certain command run, was a certain CLI

run. And then we also have LLM as a

run. And then we also have LLM as a judge where we have some expectations, which are basically matched against like hey, did it trigger the skill, did it run a certain bash command to like

also evaluate it. And we run them on every change to the skill. So, if a change happens to or like a diff to the skill file, the eval will be run, and

there will also be a result, and the change will not be merged if it is not improving the test cases. So, we always have those regression tests for every change to the skill, and you can only

change the skill if it improves the eval or add new evals. And um

yeah, that that's how we we we basically manage it. And then last but not least,

manage it. And then last but not least, uh 10 examples for best practices for skills.

You don't need to take photos. They are

in the blog post I can share later. So,

um the I mean, we had it many, many times.

The the skill skill description is very important. Uh we have seen 50% of the

important. Uh we have seen 50% of the failures uh because the skill was not triggered correctly because the prompt of the user was not uh detailed enough for the model to understand, "Hey, I need to use that skill to solve that

task." And especially if you build

task." And especially if you build agents for others, they are not aware of the skill descriptions you have for your model and for your skill. So, they might

write something very um shallow and then the model needs to know, "Okay, I need to trigger that skill."

Um we should write directors over passive information. So, we should

passive information. So, we should always think about it. You should tell the agent what to do or not what to do and not just like, "Hey, if you feel happy today, please use the skill." Um

include negative tests. Uh we always forget negative tests. Start small. Even

like 10 to 20 skill eval samples are better than nothing. You will be surprised on how much you will find even from like five to 10 examples. And then

like definitely create outcomes, not paths. Uh we don't want to test if the

paths. Uh we don't want to test if the model loads the skill on like the first turn. We really want to test if it can

turn. We really want to test if it can achieve the task based on the prompt.

And if it loads the skill, it loads the skill. If not, then not. If it um loads

skill. If not, then not. If it um loads the skill after five turns, that's also okay. Then we want to have isolated runs

okay. Then we want to have isolated runs because coding agents are very good at finding or cheating. So, if you run inside uh

or cheating. So, if you run inside uh your existing environment, it might look up previous chats or it might look up some other executions and then like try to cheat it and get the context from the

skill without even using the skill. Then

definitely run more than one trial when running evals. Like agents, our models

running evals. Like agents, our models are non-deterministic.

Maybe the first one works, the second one doesn't. So, always run the to six

one doesn't. So, always run the to six uh trials per case and to measure reliability Uh um test across different harnesses if you work with like or if you have employees or

um people working with like different harnesses, not only just evaluate against Claude or anti-gravity. If you

have people working with cursor, try to include them as well because agent harnesses behave differently and of course model behaves differently. So,

maybe your skill is very good with a Gemini but very bad with Codex and then you have uh customers, consumers using your harness with Codex and then it fails. And then um create your evals.

fails. And then um create your evals.

So, if your um model is good enough that it doesn't need the skill anymore, keep that eval. You don't

need to throw that eval away because you throw the skill away. You can keep that eval to make sure that the model or the agent keeps the performance and as soon as you start seeing some degradation, you can reintroduce the skill. You can

maybe tweak some other tools or pieces to keep like the the performance up and then really detect when you can retire skill and you will be very surprised with all of the model updates how fast

you can retire skill which you might need it like six months ago but not today anymore. And I have some homework

today anymore. And I have some homework for you. So, if you are back from

for you. So, if you are back from holiday on Monday, um pick uh the most used skill and write five test prompts. Uh you can also use your

test prompts. Uh you can also use your coding agent and ask it to see look at your trajectories which are my most used skills and then try to create some some skills. It's you have seen it's like

skills. It's you have seen it's like very easy to write your eval harness.

It's like a JSON or YAML file and then like some Python script which runs your coding agent or your agent harness and then like look at the outcome.

Definitely uh try to look at the removing no-ops. Maybe it does not

removing no-ops. Maybe it does not change the eval performance but it helps you save cost because all of the tokens which are not helpful or not changing

the agent behavior are money you will like spend. So, look at um writing great

like spend. So, look at um writing great skills uh from Matt. It's you can find it on on GitHub and then also run ablation test. So, run always evals with

ablation test. So, run always evals with your skill loaded and without your skill loaded. Only that way you will know when

loaded. Only that way you will know when you can retire skill or if a skill is really helpful for your performance. So,

don't ship skills without evals.

Thank you.

[applause]