Live data from Hacker News

Skills Officially Comes to Codex

developers.openai.com

121–130 of 133 posts

Re: Skills Officially Comes to Codex

#121

Earlier quoted context omitted.

That's why I give the LLM a readonly connection

This is much better than MCP, which also stuffs every session's precious context with potentially irrelevant instructions.

They could just make mcps dynamically loaded in the same way no?

Re: Skills Officially Comes to Codex

#123
post #121

Earlier quoted context omitted.

This is much better than MCP, which also stuffs every session's precious context with potentially irrelevant instructions.

They could just make mcps dynamically loaded in the same way no?

It is still worse as it consumes more context giving instructions for custom tooling whereas the LLM already understands how to connect to and query a read-only SQL service with standard tools

Re: Skills Officially Comes to Codex

#124
post #117

Earlier quoted context omitted.

Skills are the matrix scene where neo learns kungfu. Imagine they are a database of specialized knowledge that can an agent can instantly tap into _on demand_. The key here is “on demand”. Not every agent or convention needs to know kung fu. But when they do, a skill is waiting to be consumed. This basic idea is “progressive disclosure” and it composes nicely to keep context windows focused. Eg i have a metabase skil…

Nice analogy!

I cant claim credit. Im pretty sure Ive seen anthropic themselves use it in the original explainers

Re: Skills Officially Comes to Codex

#126
post #87

Earlier quoted context omitted.

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 extract…

Add reinforcement learning to figure out which skills are actually useful, and you're really cooking.

Combine that with retrying the same task again but with the improved skills in some sort of train loop that learns to bake in the skills natively to obviate the need for them.

The path to recursive self-improvement seems to be emerging.

Re: Skills Officially Comes to Codex

#127
Given how precious the main context is would it not make sense to have the skill index and skill runner occur in a subagent? e.g. "run this query against the dev db" the skills index subagent finds the db skill, runs the query then returns the result to the main context.

Re: Skills Officially Comes to Codex

#128
What is the advantage of skills over just calling code? From where I’m standing a Claude.md with a couple of examples of a particular bash script (examples and bash also written by Claude) is enough.

Re: Skills Officially Comes to Codex

#130

How can skills be monetised by creators? Obviously they are empowering Codex and Claude etc, and many will be open source or free. But for those who have commercial resources or tools to add to the skills choice, is there documentation for doing that smoothly, or a pathway to it? I can see at least a couple of ways it might be done - skills requiring API keys or or other authentication approaches, but this adds frict…

Sometimes, monetization is just impossible. But if you insist, have the skill call an API that needs a token, and charge for the API
Post reply on HN