311–320 of 383 posts
What useful Claude Code Skills have you made so far?
1. A skill for refactoring code using ast-grep
2. A skill for searching code using my Symbex tool
3. A skill for building Datasette plugins
None of them feel quite good enough to share yet, I'm still exploring what patterns work the best.
So far not impressed with CC's ability to invoke skills automatically. I made a skill with the unambiguous description: "Use when creating or editing bash scripts" Yet, Claude does not invoke the skill when asked to write a bash script. https://gist.github.com/raine/528f97375e125cf97a8f8b415bfd80...
Hah, yeah that's a total miss there. Maybe it messed that up because writing bash scripts is so core to how Claude Code works? Much of the existing system prompt (and I bet a lot of the fine-tuning data) is about how to use the Bash tool.
description: CRITICAL: Use when writing bash scripts
Earlier quoted context omitted.
I'm not. Here are my disclosures: https://simonwillison.net/about/#disclosures And if my disclosures aren't enough for you, here's the FTC explaining how it would be illegal for an AI vendor to pay someone to write something like this without both sides disclosing the relationship: https://www.ftc.gov/business-guidance/resources/ftcs-endorse...
While it's very honest of you to disclose in full your various affiliations to the LLM vendors, and it does look like you're not being paid by them - the reason they are inviting you for the early previews and all that is precisely because they either expect or assume you won't go to critical on them. And that shows in your writing to be honest. I'd assume the same in their place. So yeah, not paid obviously, but it…
I wrote about how good skills are... but pointed out the flaws in MCP at the same time. Anthropic have invested way more in MCP.
I called out Claude Haiku 4.5 as being more expensive than previous Haiku models when the thing I was hoping for was something that was price competitive with GPT-5 Mini/Nano and Gemini Flash Lite.
NVIDIA sent me a review unit of their Spark and I wrote about how hard it was to get CUDA and Arm working together.
OpenAI invited me to DevDay and I published a GPT-5 Pro pelican that took 6 minutes and cost $1.10 cents, plus made fun of their terrible track record for announcing and then failing to ship revenue sharing on a livestream: https://www.youtube.com/live/M6paPiur4yQ?si=XXKkIKY2J71QCJKW...
The reason I get invited to stuff is that I'm a trusted independent voice in the space. The labs appear smart enough not to expect me to throw away my credibility for a free event ticket or early preview access to their launches.
More importantly: I don't value early access or event invitations very highly. If a lab stopped inviting me to stuff it really wouldn't affect me much at all. Might even help give me some space to focus on other things!
Earlier quoted context omitted.
Strong disagreement on the helpfulness of the name- if anything calling a context file a skill is really misleading. It evokes something like a LoRA or pluggable modality. Skill is the wrong name imo
IMO LoRAs are no different from context tokens. In fact, before LoRAs tuned prompt vectors were a popular adapter architecture. Conceptually, the only difference is that prompt adapters only interact with other tokens through the attention mechanism while LoRAs allow you to directly modify any linear layer in the model. Essentially, you can think of your KV cache as dynamically generated model weights. Moreover, I ca…
But even if LoRA isn't it - the point is that "skill" seems like the wrong term for something that already has a name: instructions. These are instruct-tuned models. Given instructions they can do new things; this push to rebrand it as a "skill" just seems like marketing.
Earlier quoted context omitted.
Strong disagreement on the helpfulness of the name- if anything calling a context file a skill is really misleading. It evokes something like a LoRA or pluggable modality. Skill is the wrong name imo
I think skill is the perfect name for this. You provide the LLM with a new skill by telling it how to do a thing and providing supporting scripts to help it do that thing.
We're doing something like this internally. Our monorepo context files were much too big, so we built a progressive tree of fragments to load up for different tasks. I am struck by how much these kinds of context documents resemble normal developer documentation, but actually useful and task-oriented. What was the barrier to creating these documents before? Three theories on why this is so different: 1) The feedback…
In a proprietary system, there is pressure against creating quality technical documentation because it can be used to train your replacement. Writing docs solely for your own benefit, or your colleagues' benefit, is also dubious because you already know the things you wrote. Although returning to a thing you made months/years ago can be painful, it's not the day-to-day common case in enterprise software development.
AI assistants flip the incentives. Now, your docs are helping to steer your personal digital goblin in the right direction. The docs are tangibly augmenting your own abilities.
We're doing something like this internally. Our monorepo context files were much too big, so we built a progressive tree of fragments to load up for different tasks. I am struck by how much these kinds of context documents resemble normal developer documentation, but actually useful and task-oriented. What was the barrier to creating these documents before? Three theories on why this is so different: 1) The feedback…
> 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 just instructions with RAG. The more I read about this the more convinced I am that this is just marketing.
Earlier quoted context omitted.
Would really like something selfhosted that does the basic Wolfram Alpha math things. Doesn't need the craziest math capability but standard symbolic math stuff like expression reduction, differentiation and integration of common equations, plotting, unit wrangling. All with an easy to use text interface that doesn't require learning.
Personal faves: - Mathematica - Maple - MathStudio (mobile) - Ti-89 calculator (high school favorite) Others: - SageMath - GNU Octave - SymPy - Maxima - Mathcad
Earlier quoted context omitted.
tbh wolfram alpha was the craziest thing ever. haven't done much research on how this was implemented back in the day but to achieve what they did for such complex mathematical problems without AI was kind of nuts
Wolfram Alpha is AI. It's just not an LLM. AI has been a thing since the 60s. LLMs will also become "not AI" in a few years probably.