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

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

#331

Post by verdverm » Wed, Sep 09, 2026, 4:15 PM UTC

woud420 wrote: post #330

verdverm wrote: post #237

Earlier quoted context omitted.

We do that, but keep the scripts in the code and just tell them in the markdown where the scripts are, same with "references" (docs/) for us. It never made sense to me to put those in a skill dir, many are useful across skills and for humans (many written for humans before agents were a thing) One of the more interesting benefits to skills is that many harnesses now run the inline command(s) in backticks, shortcuttin…

+1 on all of this, it is similar to the pattern I see emerging as well. For example I have open-sourced (let's be honest, it's just my personal tooling of taste) a repo on gh to try and formalize these things. I'd rather not share out of mostly imposter syndrome but essentially it's a scaffolding tool ala "create-react-app" for the stack I generally use. Part of that is to create standardized "docs/{architecture, dec…

I was solving your problem.before LLMs with my personal developers Swiss army knife (hof gen/CUE+templates). I'm somewhat keen to see how I can capture the agent markdown I want in many places, like project init, in CUE via embed and modules I can import and version, skipping the need for a markdown dependency cycle management system.

https://github.com/hofstadter-io/hof

(sharing because it has sloppy parts and that/I.S. shouldn't stop you from sharing!)

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

#332

Post by alexsmirnov » Wed, Sep 09, 2026, 4:45 PM UTC

mstr32 wrote: post #245

xpnsec wrote: post #133

Earlier quoted context omitted.

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?

I did create special repo that has all skills/agents/scripts and MCP configuration. All agents ( currently 3 in use: claude code, opencode, and pi ) packed in docker container, with artifacts required by project technologies, and task at hand ( planning, code review, documentation management, web design, ... ). Nothing but a small file with list of technologies committed to project.

For evaluation, there is command to record session, repository commit, and observed problems that stored in special database, so each session can be reproduced. Developer commit reports, I do analysis, refine and evaluate system.

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

#333

Post by crmasterton » Wed, Sep 09, 2026, 9:52 PM UTC

github repo with a sync skill (ha!) that copies to the global skills on each computer, and also checks and updates the github repo with any skills that got... well.. updated.

at best, skills keep me consistent. at worst, its a prompt repo.

I like skills

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

#334

Post by subeadia » Thu, Sep 10, 2026, 3:19 PM UTC

darren0 wrote: post #238

Skills are encoding a process. The more niche the process the more useful the skill. As the process grows to a larger audience it becomes more generic and thus converges with the models knowledge. So skills are better for a smaller group of people. And similarly how it's packaged and maintained becomes specific to that group.

This is it in a nutshell. Great advice.

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

#335

Post by breckenedge » Thu, Sep 10, 2026, 6:32 PM UTC

sleepybrett wrote: post #305

breckenedge wrote: post #179

Earlier quoted context omitted.

My approach is different. Skills I write mostly use Python to save on the agent needing to run its own loops. I use these loops to monitor the CI build and PR approvals rather than having the agent poll, and even Opus gets the commands wrong enough to make it worth it. Last week I wired up a skill for the agent to share screenshots in PRs via specific S3 buckets and AWS CLIs. Again, the agents guess at the right comm…

the problem with that, that i'm seeing is just the sheer proliferation of internal skills. There are now so many that I can't see how they can possibly remain maintained. It feels like at the project/product/middle management layer this type of 'big pile of skills to do some very specific task' is very popular. I think this is probably for a few reasons. I think the largest factor is that these task management items…

Yea I definitely keep engineering skills and org skills separate.

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

#336

Post by amoriz » Thu, Sep 10, 2026, 7:24 PM UTC

hadlock wrote: post #306

jurgenburgen wrote: post #292

Earlier quoted context omitted.

Can you elaborate why a debugging skill would save those tokens?

Rather than teach the agent where grafana is, how to use a sentry trace id to find a otel traceparent, where my ALB is, I'm what clusters do what, which namespace prod is in, what our stack looks like, that thing that looks broken actually isn't, etc etc etc. I just paste in the sentry trace id, a guess of what might be wrong ("i think we overtuned gunicorn again" or "developer bob pushed short sha 123456 and nothing…

[flagged]