Live data from Hacker News

Ask HN: How do you manage skills files?

news.ycombinator.com

201–210 of 318 posts

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

#202

I read somewhere that Boris (created Claude Code) recommends deleting skills, and hooks every so often and then observe how the LLM performs without them. Maybe better to periodically prune: tweak some skills, shorten some, delete some.

observing changes is slow and very subjective. i ask ai itself to update skill once a while

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

#204
I think people undervalue skills on the cross repo boundaries and how systems interact with other systems.

For instance… how to deploy a service or new service’a docker container. Get secrets in value blind, manage secrets value blind. Those sorts of things have been wildly valuable. Also due to the nature of skills and how they are pulled in by your harness they can really prime the context in a way that is really useful to agent autonomy if that is your thing.

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

#205
reduce and simplifies your skills periodically . And use workflow to separate skills ,not by functionality . The workflow would be simplified but will always be useful as long as business runs. Such as the software could be build by C/C++/Java/Go/Python but the workflow based on software keeps live.

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

#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 technical project plan skill suite in 90% of my sessions via direct reference, and the stage -> cross-model second-opinion review is how I land all my commits.

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

#208
post #116
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.…

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 plan, and validate the plans logic (subagents)

4. Implement

5. Runtime/local validation

6. Post PR, review it using applicable agents (database, security, code, prose...)

7. Fix PR based on feedback

I generally get excellent results out of this process, and I cannot imagine trying to orchestrate this without a skill. But I also can imagine my workflow isn't tuned to be super usable for anyone else.

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

#209
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.…

My company ran a test and found that they reduce token output on flagship model by something like 2-4x, and that number has been increasing with newer models. I suspect the increased subagent usage is driving this trend, because this means we're relying on models to do their own prompt engineering.

Yes, they are just text, and can therefore be replaced with good prompting. However, this also means they confer a real benefit: a good set of skills creates a transferable baseline, raising the skill floor and offering a more consistent experience across the organization.

Post reply on HN