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

1–10 of 133 posts

Re: Skills Officially Comes to Codex

#2

Post by rochansinha »

Agent Skills let you extend Codex with task-specific capabilities. A skill packages instructions, resources, and optional scripts so Codex can perform a specific workflow reliably. You can share skills across teams or the community, and they build on the open Agent Skills standard.

Skills are available in both the Codex CLI and IDE extensions.

Re: Skills Officially Comes to Codex

#3

Post by dan_wood »

rochansinha wrote: post #2

Agent Skills let you extend Codex with task-specific capabilities. A skill packages instructions, resources, and optional scripts so Codex can perform a specific workflow reliably. You can share skills across teams or the community, and they build on the open Agent Skills standard. Skills are available in both the Codex CLI and IDE extensions.

Thanks to Anthropic.

Re: Skills Officially Comes to Codex

#8

Post by mikaelaast »

Are we sure that unrestricted free-form Markdown content is the best configuration format for this kind of thing? I know there is a YAML frontmatter component to this, but doesn't the free-form nature of the "body" part of these configuration files lead to an inevitably unverifiable process? I would like my agents to be inherently evaluable, and free-text instructions do not lend themselves easily to systematic evaluation.

Re: Skills Officially Comes to Codex

#9

Post by Etheryte »

mikaelaast wrote: post #8

Are we sure that unrestricted free-form Markdown content is the best configuration format for this kind of thing? I know there is a YAML frontmatter component to this, but doesn't the free-form nature of the "body" part of these configuration files lead to an inevitably unverifiable process? I would like my agents to be inherently evaluable, and free-text instructions do not lend themselves easily to systematic evalu…

The modern state of the art is inherently not verifiable. Which way you give it input is really secondary to that fact. When you don't see weights or know anything else about the system, any idea of verifiability is an illusion.
Post reply on HN