to me i solely evaluate on the way they write prompts and how elaborate they are in terms of explaining it and the patience when the model messed up

while i was learning, i used to experiment by first solving the problem in terms of input output and then optimise it one by one. and with the technique/triggers you mentioned, i'm not sure if it'd cater to somebody like me

I've been using Bitwarden, can anybody help me with how are they compared to 1Password?

Yeah, we've had a few super early stage startups who've straight up asked as to why can't we just vibe code this. So that's there.

But I truly resonate with the workflow approach, how I see the new SaaS model is like pieces of Lego. You can plug and play and then the world will start making sense ig?

Lol, I felt the same and this sort of also led us to build what i ended up founding now

Just go with Pop OS, easy to setup, great community, slightly heavy on the memory though but is a great starter.

And if you don't care of what others think and want to truly learn, I'd say Ubuntu.

As a founder, it helps me keep track of things by understanding our user session recordings and telling me where exactly they're going wrong.

I don't think AI traders will ever become as common as people think because then it'll just take away all the delta.

Evaluating is a big problem again altogether as you mentioned.

PS: For context, I did paper trade one alpha for 7 days then decided not to run it just because I did it as a hobby.

hey! how are you tracking usage for this currently?

I've spent the last 6 months maintaining a 3000-line prompt library for Claude. Yesterday, Anthropic shipped Skills and made 90% of it obsolete. Skills are basically organized folders (SKILL.md files) that Claude loads dynamically when relevant. What makes them interesting:

1. Progressive disclosure - Claude only loads full skill content when needed, not at startup. This scales way better than Custom Instructions or Projects for context management.

2. Composability - Multiple skills stack automatically. Ask it to build a signup form, and it might activate brand-guidelines + accessibility + responsive-design skills without you specifying them.

3. Security model - You can restrict which tools a skill can use via `allowed-tools`. Want a read-only code auditor that literally cannot modify files? That's now possible.

4. Cross-platform - Same skill works in Claude.ai, Claude Code CLI, and the API.

The anthropics/skills repo has some good examples: artifacts-builder (React + Tailwind), webapp-testing (Playwright), document generation, etc.

Real talk though: this isn't "the end of prompt engineering." You're still writing prompts - just packaging them better. But the DX improvement is legit. I went from copy-pasting prompts from Notion to having Claude auto-load the right context based on what i'm doing.

Box, Rakuten, and Canva are apparently already using this in production after 2 weeks, which... seems fast? Rakuten mentioned going from "a day to an hour" on some workflows.

Wrote up my experience here with code examples and the technical details on how progressive disclosure works in the URL.

Current rough edges: no skill marketplace yet, discovery is based on description matching (works surprisingly well but not perfect), sharing is manual (git clone to ~/.claude/skills/), and testing/debugging tooling is basically non-existent.

Has anyone else been playing with this? Curious what workflows people are building skills for.