Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Skills Officially Comes to Codex

developers.openai.com

Post reply on HN
Print view View original

71–80 of 133 posts

Re: Skills Officially Comes to Codex

#71

Post by erichocean »

btown wrote: post #63

Something that’s under-emphasized and vital to understand about Skills is that, by the spec, there’s no RAG on the content of Skill code or markdown - the names and descriptions in every skill’s front-matter are included verbatim in your prompt, and that’s all that’s used to choose a skill. So if you have subtle logic in a Skill that’s not mentioned in a description, or you use the skill body to describe use-cases no…

Some agentic systems do apply RAG to skills, there's nothing about skills that requires blind insertion into prompts.

This is really an agentic harness issue, not an LLM issue per se.

In 2026, I think we'll see agentic harnesses much more tightly integrated with their respective LLMs. You're already starting to see this, e.g. with Google's "Interactions" API and how different LLMs expect CoT to be maintained.

There's a lot of alpha in co-optimizing your agentic harness with how the LLM is RL-trained on tool use and reasoning traces.

Re: Skills Officially Comes to Codex

#72

Post by macNchz »

hu3 wrote: post #13
cube2222 wrote: post #11

It's so nice that skills are becoming a standard, they are imo a much bigger deal long-term than e.g. MCP. Easy to author (at its most basic, just a markdown file), context efficient by default (only preloads yaml front-matter, can lazy load more markdown files as needed), can piggyback on top of existing tooling (for instance, instead of the GitHub MCP, you just make a skill describing how to use the `gh` cli). Comp…

Perhaps you could help me. I'm having a hard time figuring out how could I leverage skills in a medium size web application project. It's python, PostgreSQL, Django. Thanks in advance. I wonder if skills are more useful for non crud-like projects. Maybe data science and DevOps.

There’s nothing super special about it, it’s just handy if you have some instructions that you don’t need the AI to see all the time, but that you’d like it to have available for specific things.

Maybe you have a custom auth backend that needs an annoying local proxy setup before it can be tested—you don’t need all of those instructions in the primary agents.md bloating the context on every request, a skill would let you separate them so they’re only accessed when needed.

Or if you have a complex testing setup and a multi-step process for generating realistic fixtures and mocks: the AI maybe only needs some basic instructions on how to run the tests 90% of the time, but when it’s time to make significant changes it needs info about your whole workflow and philosophy.

I have a django project with some hardcoded constants that I source from various third party sites, which need to be updated periodically. Originally that meant sitting down and visiting a few websites and copy pasting identifiers from them. As AI got better web search I was able to put together a prompt that did pretty well at compiling them. With a skill I can have the AI find the updated info, update the code itself, and provide it some little test scripts to validate it did everything right.

Re: Skills Officially Comes to Codex

#73

Post by coldtea »

mikaelaast wrote: post #39
coldtea wrote: post #23

Earlier quoted context omitted.

Would a structured skills file format help you evaluate the results more?

Yes. It would make it much easier to evaluate results if the input contents were parameterized and normalized to some agreed-upon structure. Not to mention the advantages it would present for iteration and improvement.

"if the input contents were parameterized and normalized to some agreed-upon structure"

Just the format would be. There's no rigid structure that gets any preferrential treatment by the LLM, even if it did accept. In the end it's just instructions that are no different in any way from the prompt text.

And nothing stops you from making a "parameterized and normalized to some agreed-upon structure" and passing it directly to the LLM as skills content, or parsing it and dumping it as skills regular text content.

Re: Skills Officially Comes to Codex

#74

Post by username223 »

well_ackshually wrote: post #67

Ah, yes, simple text files that describe concepts, and that may contain references to other concepts, or references to dive in deeper. We could even call these something like a link. And they form a sort of... web, maybe ? Close enough, welcome back index.htm, can't wait to see the first ads being served in my skills

Imagine SUBPROGRAMs that implement well-specified sequences of operations in a COmmon Business-Oriented Language, which can CALL each other. We are truly sipping rocket fuel.

Re: Skills Officially Comes to Codex

#75

Post by mkagenius »

jimmydoe wrote: post #69
btown wrote: post #63

Something that’s under-emphasized and vital to understand about Skills is that, by the spec, there’s no RAG on the content of Skill code or markdown - the names and descriptions in every skill’s front-matter are included verbatim in your prompt, and that’s all that’s used to choose a skill. So if you have subtle logic in a Skill that’s not mentioned in a description, or you use the skill body to describe use-cases no…

but that's same for MCP and tools, no?

Yes. Infact you can serve each Skill as a tool exposed via MCP if you want. I did the same to make Skills work with Gemini CLI (or any other tool that supports MCP) while creating open-skills.

1. Open-Skills: https://github.com/BandarLabs/open-skills

Re: Skills Officially Comes to Codex

#76

Post by NitpickLawyer »

cube2222 wrote: post #11

It's so nice that skills are becoming a standard, they are imo a much bigger deal long-term than e.g. MCP. Easy to author (at its most basic, just a markdown file), context efficient by default (only preloads yaml front-matter, can lazy load more markdown files as needed), can piggyback on top of existing tooling (for instance, instead of the GitHub MCP, you just make a skill describing how to use the `gh` cli). Comp…

On top of everything you've described, one more advantage is that you can use the agents themselves to edit / improve / add to the skills. One easy one to do is something like "take the key points from this session and add the learnings as a skill". It works both on good sessions with new paths/functionality and on "bad" sessions where you had to hand-hold the agent. And they're pretty good at summarising and extracting tidbits. And you can always skim the files and do quick edits.

Compared to MCPs, this is a much faster and more approachable flow to add "capabilities" to your agents.

Re: Skills Officially Comes to Codex

#77

Post by zahlman »

Recently there was a submission (https://news.ycombinator.com/item?id=45840088) breaking down how agents are basically just a loop of querying a LLM, sometimes receiving a specially-formatted (using JSON in the example) "request to use a tool", and having the main program detect, interpret and execute those requests.

What do "skills" look like, generically, in this framework?

Re: Skills Officially Comes to Codex

#78

Post by didibus »

zahlman wrote: post #77

Recently there was a submission ( https://news.ycombinator.com/item?id=45840088 ) breaking down how agents are basically just a loop of querying a LLM, sometimes receiving a specially-formatted (using JSON in the example) "request to use a tool", and having the main program detect, interpret and execute those requests. What do "skills" look like, generically, in this framework?

The agent can selectively loads one or more of the "skills", which means it'll pull it's prompt once it decided that it should be loaded, and the skill can have accompanying scripts that the prompt also describes to the LLM.

So it's just like a standard way to bring in prompts/scripts to the LLM with support from the tooling directly.

Re: Skills Officially Comes to Codex

#79

Post by colonCapitalDee »

zahlman wrote: post #77

Recently there was a submission ( https://news.ycombinator.com/item?id=45840088 ) breaking down how agents are basically just a loop of querying a LLM, sometimes receiving a specially-formatted (using JSON in the example) "request to use a tool", and having the main program detect, interpret and execute those requests. What do "skills" look like, generically, in this framework?

Before the first loop iteration, the harness sends a message to the LLM along the lines of.

  

    postgres

    Directions on how to query the pre-prod postgres db
            skills/postgres.md

The harness then may periodically resend this notification so that the LLM doesn't "forget" that skills are available. Because the notification is only name + description + file, this is cheap r.e tokens. The harness's ability to tell the LLM "IMPORTANT: this is a skill, so pay attention and use it when appropriate" and then periodically remind them of this is what differentiates a proper Anthropic-style skill from just sticking "If you need to do postgres stuff, read skills/postgres.md" in AGENTS.md. Just how valuable is this? Not sure. I suspect that a sufficiently smart LLM won't need the special skill infrastructure.

(Note that skill name is not technically required, it's just a vanity / convenience thing).

Re: Skills Officially Comes to Codex

#80

Post by didibus »

hu3 wrote: post #13
cube2222 wrote: post #11

It's so nice that skills are becoming a standard, they are imo a much bigger deal long-term than e.g. MCP. Easy to author (at its most basic, just a markdown file), context efficient by default (only preloads yaml front-matter, can lazy load more markdown files as needed), can piggyback on top of existing tooling (for instance, instead of the GitHub MCP, you just make a skill describing how to use the `gh` cli). Comp…

Perhaps you could help me. I'm having a hard time figuring out how could I leverage skills in a medium size web application project. It's python, PostgreSQL, Django. Thanks in advance. I wonder if skills are more useful for non crud-like projects. Maybe data science and DevOps.

There can be a Django template skill for example, which is just a markdown file which reminds the LLM the syntax of Django Templates and best practices for it. It could have an included script that the LLM can use to test a single template file for example.
Post reply on HN