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

Claude Skills are awesome, maybe a bigger deal than MCP

simonwillison.net

Post reply on HN
Print view View original

341–350 of 383 posts

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#341

Post by habitue »

causal wrote: post #318
consumer451 wrote: post #294

> Over time the limitations of MCP have started to emerge. The most significant is in terms of token usage: GitHub’s official MCP on its own famously consumes tens of thousands of tokens of context, and once you’ve added a few more to that there’s precious little space left for the LLM to actually do useful work. Supabase MCP really devours your context window. IIRC, it uses 8k for its search_docs tool alone, just on…

It's also not clear to me why using "skills" would consume less context once invoked. It's just instructions with RAG. The more I read about this the more convinced I am that this is just marketing.

Skills wont use less context once invoked, the point is that MCP in particular frontloads a bunch of stuff into your context on the entire api surface area. So even if it doesn't invoke the mcp, it's costing you.

That's why it's common advice to turn off MCPs for tools you dont think are relevant to the task at hand.

The idea behind skills us that they're progressively unlocked: they only take up a short description in the context, relying on the agent to expand things if it feels it's relevant.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#343

Post by thenanyu »

oblio wrote: post #339
thenanyu wrote: post #303

Earlier quoted context omitted.

I hate this analogy. NBA players can all hit 90% of their free throws shooting overhand too. Just some of them are much worse at handling the pressure and pace change of the situation in a game context.

The underhanded throw is mechanically just better for free throws. Much easier to put backspin, for example. It's just a shot that doesn't help anywhere else.

That’s beside the point. It wouldn’t help shaq or any of those big men hit free throws. They have no problems with mechanics.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#344

Post by apitman »

simonw wrote: post #332
crowbahr wrote: post #328

Earlier quoted context omitted.

The moment you write documentation it becomes stale. It's additional debt you've incurred and the upkeep must be payed every modification to the code. That doesn't mean you should skip it - but it's vital to recognize the costs. When I joined my current company they had extensive documentation on several systems, all of it outdated, stale or even just straight up wrong. I wasted cumulative weeks depending on other pr…

The fix for that is to keep the documentation in the same repository as the code it documents, and then to enforce that it gets updated as part of your code review process. Don't let a PR land if it doesn't also update any relevant documentation at the same time. Keeping documentation in a separate system - like a wiki - is an anti-pattern in most cases. It leads to documentation that nobody trusts (and hence nobody…

I've really been enjoying "hey Codex I just implemented such a fun such code change, where are all the places in the docs that I need to update?"

I've been slow adopting things. I know the cool kids are having agents do the docs changes and the code changes in the first place.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#345

Post by freedomben »

simonw wrote: post #332
crowbahr wrote: post #328

Earlier quoted context omitted.

The moment you write documentation it becomes stale. It's additional debt you've incurred and the upkeep must be payed every modification to the code. That doesn't mean you should skip it - but it's vital to recognize the costs. When I joined my current company they had extensive documentation on several systems, all of it outdated, stale or even just straight up wrong. I wasted cumulative weeks depending on other pr…

The fix for that is to keep the documentation in the same repository as the code it documents, and then to enforce that it gets updated as part of your code review process. Don't let a PR land if it doesn't also update any relevant documentation at the same time. Keeping documentation in a separate system - like a wiki - is an anti-pattern in most cases. It leads to documentation that nobody trusts (and hence nobody…

Indeed, I frequently will ask Claude code if the documentation needs to be updated, and it's pretty good at doing so

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#346

Post by taormina »

Nevermark wrote: post #278
taormina wrote: post #268

Earlier quoted context omitted.

Nah, it's definitely not that. I have it explicitly several times over in that file and it insists on commenting so much it's absurd.

Can you tell it to put the comments somewhere else? A special "Important Comments" folder? Ha! These things.

I haven't tried that, it might be worth a shot.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#347

Post by lolc »

stuaxo wrote: post #298
evanmoran wrote: post #280

Earlier quoted context omitted.

I know this is highly controversial, but I now leave the comments in. My theory is that the “probability space” the LLM is writing code in can’t help but write them, so if i leave them next LLM that reads the code will start in the same space. Maybe it’s too much, but currently I just want the code to be right and I’ve let go of the exact wording of comments/variables/types to move faster.

Similar logic, but hard disagree on keeping comments that are exactly what the following code does. They are useful to the LLM in writing the code (which comes after). But when it comes to an LLM reading that code later its just a waste of context. For humans its a waste of screen space. A comment should only explain what the following thing does if its hard to parse for some reason. Otherwise it should add informati…

Prompting to remove redundant comments works quite well, but I dislike the extra step.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#348

Post by lolc »

jychang wrote: post #287
evanmoran wrote: post #280

Earlier quoted context omitted.

I know this is highly controversial, but I now leave the comments in. My theory is that the “probability space” the LLM is writing code in can’t help but write them, so if i leave them next LLM that reads the code will start in the same space. Maybe it’s too much, but currently I just want the code to be right and I’ve let go of the exact wording of comments/variables/types to move faster.

I think the code comments straight up just help understanding, whether human or AI. There's a piece of common knowledge that NBA basketball players can all hit over 90% on free throws, if they shot underhand (granny style). But for pride reasons, they don't throw underhand. Shaq just shot 52%, even though it'd be free points if he could easily shoot better. I suspect there's similar things in software engineering. I'…

I like comments about intent, about the why. The generators are really bad at intent, they just write dross comments about the how. The worst part is how they're not accustomed to comments about intent and tend to drop those!

Say I wrote a specific comment why this fencepost here needs special consideration. The agent will come through and replace that reasoned comment with "Add one to index".

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#349

Post by hansmayer »

simonw wrote: post #340
hansmayer wrote: post #336

Earlier quoted context omitted.

Well, if we do, those would be very different dictionaries indeed. Do you not know "forecast" is a synonym to "prediction" ? I was going to qualify this with a "practically", but then it turns out according to Mirriam-Webster, prediction is literally a synonym of "forecast". So explain again, what exactly is your "dictionary definition" for "prediction" again? Unless it's guessing, but then, anyone can then make "pre…

Is this perhaps some weird British vs American English thing I was unaware of? Oxford Learners Dictionary (because the Oxford English Dictionary is behind a paywall): "a statement that says what you think will happen; the act of making such a statement" https://www.oxfordlearnersdictionaries.com/us/definition/eng... The current Wikipedia definition looks like a good fit for how I'm using the term here: A prediction (…

No, it's just a matter of not trying to make "guessing" equal to "predicting". In this day and age we should know better then to make wild guesses.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#350

Post by hansmayer »

simonw wrote: post #335
hansmayer wrote: post #333

Earlier quoted context omitted.

Don't know what to tell you. I read through your blog quite often and it just...does not come across as fully unbiased. While I am sure you are putting in a lot of effort and genuinely want to be impartial, it just does not come across as such. Now, you are making another assumption here. You may think you are getting early access because you are a trusted independent voice. But think about the alternative possibilit…

What would "unbiased" even mean for a blog like mine? I don't particularly try to be unbiased because I don't think that's an achievable goal. What I aim for instead is honesty and truthfulness. I try very hard not to put false information out into the world, and when I do that I work hard to retract it - here's a recent example: https://simonwillison.net/2025/Oct/7/gemini-25-computer-use-... I'm also take care to di…

unbiased as in: not immediately claiming a new feature would be big, mere 24h after it was released to the general public?
Post reply on HN