Ask HN: How do you manage skills files? • Hacker News Board

Re: Ask HN: How do you manage skills files?

#241

Post by ma2kx » Mon, Sep 07, 2026, 3:53 PM UTC

avaer wrote: post #105

Skills are mostly snake oil, the way people use them (the aspiration to download kung foo from a celebrity). There was a time when maybe it mattered (last year), but with good repos and good prompts today's agents can find exactly what they need without any skills. "Skills" as developer macros can be useful, but at most those are things shared with the team (in the repo), not something you download from the internet.…

That's maybe the case if you always use the most popular framework and restrict your environment to a basic setup. But as soon as you e.g. build a website with SolidJS, Bulma and vite++ (vp), at least the models I tried are all the time somewhat confused, want to steer your project in a certain direction and build strange workaround so it works the way they are trained on.

Same with mcp. I want them to use the jsdelivr cdn instead of them scraping github against the rate limit. etc. But if I dont explicitly state to strictly use the $%!$@@! mcp for searching in repositories they simply ignore the mcp and even if clearly instructed, they still often fall back to gh.

Putting every detailed instruction in the AGENTS.md would just unnecessarily bloat the context and it works well enough to just instruct them in the AGENTS.md when to use which skill. Yet I agree that Skills are not some voodoo magic to provide your model super capabilities.

Re: Ask HN: How do you manage skills files?

#242

Post by mat_b » Mon, Sep 07, 2026, 3:55 PM UTC

Azkar wrote: post #208

saejox wrote: post #116

Earlier quoted context omitted.

i agree, skills downloaded from the internet are all snake oil. creating your own skills however good for both reducing the token usage & increasing reliability. those damn llms are not deterministic, asking same thing twice produces 2 different results.

This has been my experience (with downloaded skills), and currently my workflow is almost 100% skill driven. Every feature I build uses a skill that does the following: 1. Read a ticket and get context on the task. The ticket was probably written by another agent after a conversation with myself about what is happening/needs to happen, etc. 2. Plan the task, asking for clarification where needed 3. Pressure test the…

What does your prompting look like for step 3 - pressure test the plans?

Re: Ask HN: How do you manage skills files?

#243

Post by SoftTalker » Mon, Sep 07, 2026, 3:55 PM UTC

buffalobuffalo wrote: post #130

avaer wrote: post #105

Skills are mostly snake oil, the way people use them (the aspiration to download kung foo from a celebrity). There was a time when maybe it mattered (last year), but with good repos and good prompts today's agents can find exactly what they need without any skills. "Skills" as developer macros can be useful, but at most those are things shared with the team (in the repo), not something you download from the internet.…

If you are spending time on all text forums like this, you are likely a person whose skill set skews towards the verbalization of abstract concepts. This is also the exact skill set needed to use LLMs well. If you are able to articulate exactly what you want in a concise prompt, little else is needed. I think we tend to overlook the fact that LLMs have tilted the scales heavily in favor of those with good verbal skil…

In my experience, while software engineers can be socially awkward/introverted, they generally do have good verbal skills, an excellent vocabulary and can be concise and articulate in writing, when there's no social pressure. There are some exceptions of course, but being able to translate an idea or set of tasks into a concise written language form is essentially what programming is.

Re: Ask HN: How do you manage skills files?

#244

Post by wseqyrku » Mon, Sep 07, 2026, 3:57 PM UTC

I usually use this technology called Shift+Delete

Re: Ask HN: How do you manage skills files?

#245

Post by mstr32 » Mon, Sep 07, 2026, 3:59 PM UTC

xpnsec wrote: post #133

avaer wrote: post #105

Skills are mostly snake oil, the way people use them (the aspiration to download kung foo from a celebrity). There was a time when maybe it mattered (last year), but with good repos and good prompts today's agents can find exactly what they need without any skills. "Skills" as developer macros can be useful, but at most those are things shared with the team (in the repo), not something you download from the internet.…

Where they are very useful is as a documentation source for LLMs. For example, I work in infosec and often have to reference DSLs (Cobalt Strike aggressor script for example). Having a skill which is an offline index to carved up function docs, which an LLM can use without having to think, then search for, then download huge 1 page documents with all function documentation, and pollute the context… very useful.

Looks like this is a combination of documentation with a skill, right? How do you manage these skills across projects?

Re: Ask HN: How do you manage skills files?

#246

Post by dev-in » Mon, Sep 07, 2026, 3:59 PM UTC

[flagged]

Re: Ask HN: How do you manage skills files?

#247

Post by cainxinth » Mon, Sep 07, 2026, 4:01 PM UTC

I find the whole Skills.md idea a little silly. We have a technology that struggles to stay within rails due to its inherent makeup. And you think you can fix that by just telling it to?

It makes as much sense as the so-called “humanizer” tools that purport to make LLMs stop using their well-known verbal tells.

All you are doing is saying: “Hey you know that thing you can’t stop doing? Can you stop doing that?” The machine will say “Absolutely!” but eventually start doing it again.

Re: Ask HN: How do you manage skills files?

#248

Post by appplication » Mon, Sep 07, 2026, 4:03 PM UTC

cainxinth wrote: post #247

I find the whole Skills.md idea a little silly. We have a technology that struggles to stay within rails due to its inherent makeup. And you think you can fix that by just telling it to? It makes as much sense as the so-called “humanizer” tools that purport to make LLMs stop using their well-known verbal tells. All you are doing is saying: “Hey you know that thing you can’t stop doing? Can you stop doing that?” The m…

You’re not wrong, but I don’t see a lot of alternatives. So we just don’t try to fix it? At least skills give us a landing pad for “here’s how to attempt to do things consistently in a way I generally approve of”

Re: Ask HN: How do you manage skills files?

#249

Post by picklenerd » Mon, Sep 07, 2026, 4:11 PM UTC

I don’t find skills. I write my own skills based on things I do frequently and repeatably. I keep them version controlled locally and in GitHub, and I symlink that folder to my various agent skill folders so they all stay up to date.

I feel like downloading a bunch of skills is another one of those useless collections people make purely because they have infinite options. It’s like those collections of thousands of bookmarks you’re never going to click or pirated ebooks you’re never going to read.

It’s trivial to write your own skills with agents. The best way to use them, imo, is to make them when you have repeatable agent workflows, written to your own personal taste, and updated as your workflows change.

Here’s what I have for reference:

- Remove agent-speak from code, docs, and markdown files.

- Ask sequences of questions the way I like to be asked questions. Used instead of the question tool. This is my primary design skill as well.

- How to use jj the way I want my agent to use jj

- Dispatch subagents with 6 different sets of priorities. Those priorities are defined in the skill, so I can always dispatch all 6 of them to write or review code. Includes a template for code reviews

- Manage a local MD issue tracker for personal projects

Re: Ask HN: How do you manage skills files?

#250

Post by nhod » Mon, Sep 07, 2026, 4:15 PM UTC

I've been using a project called SX https://github.com/sleuth-io/sx to manage them. It has its quirks, but overall I find it to be very useful.

One thing I've had to write as a layer on top of it is a way to assemble agent-specific CLAUDE.md / AGENTS.md from fragments.

For example, I have a little fragment that has all agents respond to me in ordered list format. (Since they often ask a bunch of question all jumbled throughout a response, the ordered list format allows me to respond to those specific questions.) And I also have a growing anti-Claudeism fragment as well.

Then I combine this with project-specific fragments and have it assembled into into a single CLAUDE.md / AGENTS.md. The layer also does a little reporting on the length of the resulting files and notifies me if it ever grows beyond a certain size.