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

Ask HN: How do you manage skills files?

news.ycombinator.com

Post reply on HN
Print view View original

251–260 of 291 posts

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

#251

Post by kristianc »

sigmoid10 wrote: post #117
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.…

>but with good repos and good prompts I think waaay more people struggle with this than HN would have you believe. In the real world, not everyone is a software dev with a developer mindset to using these tools. Normal people essentially type the equivalent of "Make me X!" and complain when the model assumes anything in their underspecified mess of a prompt. There are skills like grill-me that can potentially help th…

It's interesting as grill-me and the other Matt skills are very much positioned to people who would consider themselves as developers. In fact, I'm not sure if people who were completely new to development would have heard of him at all.

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

#252

Post by alexhans »

mark_l_watson wrote: post #184
stingraycharles wrote: post #53

Earlier quoted context omitted.

People always say this about the evals, but I find it hard to have a practical implementation of such a thing where you won’t end up spending 100x the amount of time on the evals than building the skill itself. Like, ok, I have a debugging skill, now how do I make evals except for the most trivial things?

I am starting to wonder if I am doing something wrong: I ignore evals and instead I just try new models or new harnesses (or tweak my own harnesses) by solving problems I want to solve in any case; I just use new tools and form my own subjective opinions of them.

When I say evals I mean the evals you write that verify that your use cases are upheld. Think of it like a regression test for different behaviours/user stories.

The idea would be that if you already know what you want from an autonomous system, you don't need to verify manually every time and instead just run these tests to see if there's any regression of any kind. Generally I recommend structure output and evals that are just a plain assertion, if possible. Cheaper, faster, deterministic assertions.

Does that make more sense?

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

#253

Post by veryfancy »

picklenerd wrote: post #249

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 b…

+1 to keeping ownership of skills defining just what I like and symlinking them in where I work.

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

#254

Post by threecheese »

mceachen wrote: post #206

Have your agent make a plugin marketplace -- mine is here (feel free to crib): https://github.com/photostructure/coding-skills Be sure to increment unofficial plugin versions when you make edits: codex's auto-update works reasonably well, claude not so much, but when asked, both can fix their own config. And like others have said, imho the skills that are incanted as macros are much more reliably useful. I use my tec…

Codex and Claude Code support plugin symlinks for local development; if you don’t mind keeping a local clone of your skills repo they can just use it. Claude needs a shim, as it wants to cache plugins; it’ll run a shell command (!) locally to get the plugin path. Codex supports this natively.

Here’s the spec I used for my skills repo:

https://claude.ai/public/artifacts/d37077a6-2cdd-4961-b504-b...

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

#255

Post by kbos87 »

picklenerd wrote: post #249

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 b…

Similar take here - I only find value in skills as a way to repeatably carry out tasks that are specific to my workflow; any skills I've seen shared broadly don't seem to add much value beyond what the model itself can already handle.

At work I'll occasionally repurpose a skill that someone else has shared as a starting point, but those skills are already somewhat customized to the environment I operate in.

I have all of my skills maintain a single table in a markdown file with a description of each skill, when it last ran, exceptions it encountered, and when it was last edited.

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

#257

Post by alexhans »

imadtaieber wrote: post #187
alexhans wrote: post #43

- I don't find skills, I create them - Keep them organised in software repos that you install with symlinks for all coding harnesses that you have. Progressive disclosure based on the frontmatter does the rest. - I make sure they work with AI evals. Think of them like integration tests to prove behaviour. They're useful to optimize your flows. I try to make my skills be mostly a translation between natural language a…

What about skills that you need across projects?

Since I install them with symlinks in the tools "global" locations I get access to them across projects.

Think ~/.codex/skills/Same for ~/.Claude or any other tool that supports skills.

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

#259

Post by Azkar »

mat_b wrote: post #242
Azkar wrote: post #208

Earlier quoted context omitted.

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?

I had claude define an agent for a "skeptic", the first few lines in the agent file are "You are a skeptic. Your job is to refuse to take claims on faith and instead verify them against ground truth. You are not a general code reviewer. You are not a stylist. You are not a cheerleader. You take a list of claims (explicit or implicit), and for each one, you find the evidence — or the absence of it — and report what you found."

It goes on to describe what counts as a claim, how to verify the claims, and how to respond. It responds to each claim with verified, unverified, or contradicted.

The skeptic agent has been the most high value thing I've added to the workflow.

Post reply on HN