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

A Claude Code and Codex Skill for Deliberate Skill Development

github.com

Post reply on HN
Print view View original

41–50 of 65 posts

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#41

Post by Mashimo »

tomaytotomato wrote: post #23
Mashimo wrote: post #4

Mhh, interesting. I want to learn Java spring, and probably let ai help me / quiz me. I will take a look into the skills for inspiration.

I am a Java dev and Spring user for about 10 years now. If you want to learn how Spring framework and Spring boot works, the best thing to do is build your own library and then learn to add it to a new spring boot service. https://www.baeldung.com/spring-boot-custom-starter Depending on which AI tool you are using, you can also get it to debrief what it is doing and what layer of the Spring architecture it is using (…

Thanks mate. Will check it out later.

Current plan is to use a existing vue/typescript browser game as frontend, send high score and similar via web sockets. Do ~something~ with red panda to tip my toes into the Kafka world.

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#42

Post by gbro3n »

aplthrowaway67 wrote: post #24

I will never understand why someone would go through all the trouble of developing this cool idea, without bothering to link a demo or include sample output. I see this every day on HN. So the only way I can see what this skill actually looks like is to download and run it myself? No thank you.

I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location.

While building https://www.agentkanban.io (a Github CoPilot integrated task board), I experimented a lot with instruction placement. A single degree of separation from AGENTS.md works really well (I needed a robust means of having the agent pick up task specific IDs and so settled on a file called INSTRUCTION.md in a file managed by the tool which avoids polluting AGENTS.md as much as possible). I experimented with skills, but they were skipped too often for the tool to work as reliably as it now does.

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#43

Post by adastra22 »

gbro3n wrote: post #42
aplthrowaway67 wrote: post #24

I will never understand why someone would go through all the trouble of developing this cool idea, without bothering to link a demo or include sample output. I see this every day on HN. So the only way I can see what this skill actually looks like is to download and run it myself? No thank you.

I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location. While building h…

Claude auto-injects skill descriptions into the context, and is pretty good about using them. I don’t know about the other harnesses.

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#44

Post by aaronbrethorst »

gbro3n wrote: post #42
aplthrowaway67 wrote: post #24

I will never understand why someone would go through all the trouble of developing this cool idea, without bothering to link a demo or include sample output. I see this every day on HN. So the only way I can see what this skill actually looks like is to download and run it myself? No thank you.

I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location. While building h…

in the case of Claude Code, I explicitly kick off skills I want to use by prefixing their name with a `/`

e.g.:

  /go

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#45

Post by dcrazy »

giwook wrote: post #33
aplthrowaway67 wrote: post #24

I will never understand why someone would go through all the trouble of developing this cool idea, without bothering to link a demo or include sample output. I see this every day on HN. So the only way I can see what this skill actually looks like is to download and run it myself? No thank you.

The SKILL.md is right there, you can just read it to see what it does.

“The recipe is right there, you can just read it to see how it tastes.”

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#46

Post by enobrev »

adastra22 wrote: post #43
gbro3n wrote: post #42

Earlier quoted context omitted.

I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location. While building h…

Claude auto-injects skill descriptions into the context, and is pretty good about using them. I don’t know about the other harnesses.

I've had cases where it doesn't explicitly use a skill I've added BUT it still performs the actions described in the skill on its own more often than it did before I created the skill. I'd rather it use the skill for consistency, but having it follow most of the steps most of the time in cases I've forgotten to explicitly call out the skill is a better outcome.

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#48

Post by mywittyname »

gbro3n wrote: post #42
aplthrowaway67 wrote: post #24

I will never understand why someone would go through all the trouble of developing this cool idea, without bothering to link a demo or include sample output. I see this every day on HN. So the only way I can see what this skill actually looks like is to download and run it myself? No thank you.

I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location. While building h…

Question for you, since you seem like you know what you're doing here: How do I learn about stuff like agents.md? I feel like every week there's a new Claude feature people are talking about and I have no idea how they learned about it.

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#49

Post by hydra-f »

gbro3n wrote: post #42
aplthrowaway67 wrote: post #24

I will never understand why someone would go through all the trouble of developing this cool idea, without bothering to link a demo or include sample output. I see this every day on HN. So the only way I can see what this skill actually looks like is to download and run it myself? No thank you.

I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location. While building h…

I have a similar project. Through experimentation, I’ve realized a few things about skills that might be useful:

1. Less is better. A project rarely needs more than a few skills. A skill is best when the output is measurable and clearly defined. The size of the skill is also very important, since shorter ones are easier to actively maintain and for the agent to reliably follow.

2. Context is important. I keep a short knowledge map in my AGENTS.md file, which gives the agent the context it needs for the overall workflow.

3. Frontmatters work surprisingly well. It pairs nicely with agents and has given me good results (though this might be somewhat of a byproduct).

4. Consistency matters. All skills should follow the same format. For example, I strip all Markdown formatting and enforce a very specific format to them. If you import a skill, do change its format with yours.

I would also go and say not to mistake skills for prompts, but that depends on what you deem the ideal workflow.

I also have an .agents/rules/init.md with the following prompt:

"At the start of every chat or task, you MUST read the following file:

- [AGENTS.md](@AGENTS.md)". Most harnesses find this automatically, and I just give the file to those that don't.

Overall, I’ve found that a project usually only needs the AGENTS.md file and an .agents directory (prompts/, rules/, skills/).

I would love to hear other opinions on the things I just said.

The project in question: https://codeberg.org/hydrafog/kanban (agent-first task manager for the terminal)

Re: A Claude Code and Codex Skill for Deliberate Skill Development

#50

Post by fnordpiglet »

skinfaxi wrote: post #30
alexhans wrote: post #9

Earlier quoted context omitted.

Skills are just a good standard to describe repeatable workflows saving context through progressive disclosure, prompt sharing and, very underused feature, also bound the non deterministic parts with determism (which could be scripts). Conceptually, you should treat them as incremental software instead of magic you grab from others [1] The killer feature is that coding harnesses tend to have SkillBuilder agent skills…

After reading your first article I'm not sure I would agree. Skills are certainly transferrable in the sense that a sufficiently narrowly-tailored skill can be applicable for others with no modification. Similar to how we grab libraries that encapsulate certain abstractions for us.

They’re transferable to the next agent context session because every new session is a blank slate from the agents point of view. Capturing a workflow in skills is highly useful for your own workflows that you refine over time because you don’t have to reintroduce the concepts. You can use a lot of these triggers like hooks and scripts required by the skill use to inject a fair amount of constraints and determinism, and lean on the abductive abilities of the LLM to fill in the reasoning gaps. Teams also compile libraries of skills in plugin form via marketplaces to allow a certain amount of conformity of process, procedure, etc.

This is an interesting skill plugin for me because I actually face this inverse problem a fair amount where you want to teach people about a repo and the skills associated with it so they understand the intent behind things quickly. Seeing a bunch of skill commands and behaviors doesn’t always make clear why things are the way they are. The people on the other end need context, and the rapidity with which you can create fairly complex stuff means you need a faster way than “three months of onboarding” to get people up to speed.

Post reply on HN