- 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).
Compared to purpose-tuned system prompts they don't require a purpose-specific agent, and they also compose (the agent can load multiple skills that make sense for a given task).
Part of the effectiveness of this, is that AI models are heavy enough, that running a sandbox vm for them on the side is likely irrelevant cost-wise, so now the major chat ui providers all give the model such a sandboxed environment - which means skills can also contain python scripts and/or js scripts - again, much simpler, more straightforward, and flexible than e.g. requiring the target to expose remote MCPs.
Finally, you can use a skill to tell your model how to properly approach using your MCP server - which previously often required either long prompting, or a purpose-specific system prompt, with the cons I've already described.
- 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 not obvious from the front-matter, it may never be discovered or used.
Additionally, skill descriptions are all essentially prompt injections, whether relevant/vector-adjacent to your current task or not; if they nudge towards a certain tone, that may apply to your general experience with the LLM. And, of course, they add to your input tokens on every agentic turn. (This feature was proudly brought to you by Big Token.) So be thoughtful about what you load in what context.
See e.g. https://github.com/openai/codex/blob/a6974087e5c04fc711af68f...
by freakynit
1 subcomments
- I already was doing something similar on a regular basis.
I have many "folders"... each with a README.md, a scripts folder, and an optional GUIDE.md.
Whenever I arrive at some code that I know can be reused easily (for example: clerk.dev integration hat spans frontend and backend both), I used to create a "folder" of the same.
When needed, I used to just copy-paste all the folder content using my https://www.npmjs.com/package/merge-to-md package.
This has worked flawlessly well for me uptil now.
Glad we are bringing such capability natively into these coding agents.
- I think Skills could turn into something like open source libraries: standardized solutions to common problems, often written by experts.
Imagine having Skills available that implements authentication systems, multi-tenancy, etc.. in your codebase without having to know all the details about how to do this securely and correctly. This would probably boost code quality a lot and prevent insecure/buggy vibe coded products.
- Skills, plugins, apps, connectors, MCPs, agents - anyone else getting a bit lost?
- 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?
- People are really misunderstanding Skills, in my opinion. It's not really about the .md file. It's about the bundling of code and instructions. Skills assume a code execution environment.
by orliesaurus
4 subcomments
- If there was a marketplace or directory of skills.md files that were ranked with comments, it would be a good idea for the propagating of this tech
- Anthropic: Chief Product Officer of OpenAI
- I wonder if generated skills could be useful to codify the outcome of long sessions where the agent has tried a bunch of things and then finally settled on a solution based on a mixture of test failures and user feedback
- How are skills different than tool/function calling?
- 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.
by mellosouls
2 subcomments
- 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 friction to an otherwise smooth skill integration process.
Having instead a transparent commission on usage sent to registered skill suppliers would be much cleaner but I'm not confident that would be offered fairly, and I've seen no guidance yet on plans in that regard.
- I don't understand how skills are different than just instructing your model to read all the front-matters from a given folder on your filesystem and then decide if they need to read the file body.
- 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.
by mikaelaast
4 subcomments
- 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.
by well_ackshually
1 subcomments
- 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
- Yes! I was raving about Claude Skills a few days ago (vide https://quesma.com/blog/claude-skills-not-antigravity/), and excited they come to Codex as well!
- This is great. At my startup, we have a mix of Codex/CC users so having a common set of skills we can all use for building is exciting.
It’s also interesting to see how instead of a plan mode like CC, Codex is implementing planning as a skill.
by jonrosner
2 subcomments
- one thing that I am missing from the specification is a way to inject specific variables into the skills. If I create let's say a postgres-skill, then I can either (1) provide the password on every skill execution or (2) hardcode the password into my script. To make this really useful there needs to be some kind of secret storage that the agent can read/write. This would also allow me as a programmer to sell the skills that I create more easily to customers.
by not_a_toaster
0 subcomment
- We’ve made a zero shot decision tree
- See also:
Anthropic: https://www.anthropic.com/engineering/equipping-agents-for-t...
Copilot: https://github.blog/changelog/2025-12-18-github-copilot-now-...
by rochansinha
1 subcomments
- 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.
- This seems great and all, but to my surprise the default $plan skill in Codex prefers to writing plan files to ~/.codex/plans. Is this intentional, or an idiosyncrasy of my particular instance of Codex? Every agent tool I've ever seen before puts planning documentation in the repo folder itself, not in a global user directory. Why this weird decision?
- At any HR conference you go, there are two overused words: AI and Skills.
As of this week, this also applies to Hacker News.
by karolcodes
0 subcomment
- anyone using this in agentic workflow already? how is it?
- why the need to use notion?
can we use notepad or somrthing free and not proprietary?
- What are your favourite skills?
by user3939382
0 subcomment
- What they’re calling skills is a 5% weak implementation of what skills should be. My AI models fix this.
Hacker News