Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
Clief Notes
55.9k
5.0
Free
134 contributions to Clief Notes
Walkdown: What is actually in that skill?
Auditing Plumbline, the coding plugin I built, I found that it ships 43 files, about 50,000 tokens, that the AI never loads. ##What it is I built Walkdown, a pre-flight check for AI skills. You give it a GitHub link or a folder, and it reads the instruction layer: the SKILL.md files, agent definitions, hooks, manifests and CLAUDE.md, the English a model loads and runs with your permissions. For each finding it answers two questions, cited to a file and line. What does this text ask the model to do? What does installing it grant? Run it before you install someone else's skill, or before you ship your own. I built it for security. Most of what it taught me was about writing better skills. ## What you can learn from a run The summary page asks four questions: - **Size and shape.** What it costs in tokens every session and at its largest, against the context you expect. If you run local models, add `--context 8k` and watch the percentages move. It also lists the files that ship and never get used. - **Will it work somewhere else?** Hard-coded paths, programs it needs and never declares, and which AI tools besides Claude Code it's ready for. Got a CLAUDE.md and no AGENTS.md? You'll see it. - **Does it ask only for the tools it needs?** Tools granted and never used, loops with no stated limit, hooks that fire on every prompt. - **Anything to be careful about.** Hidden characters the model reads and you can't see. Dead links and files nothing points to. Instructions to go fetch more instructions from somewhere else. Simon Willison's lethal trifecta (can it read your data, take outside input, and send data out?). Leftover TODOs and pinned model IDs land here too. You can get deep into the details of everything it caught. Each finding also says how often that pattern turns up in other repos, so you can tell a common habit from an odd one. `review.html` walks you through each place one card at a time so you can mark it.
Walkdown: What is actually in that skill?
0 likes • 9d
@Aurel Babiš It kinda does that already. It will note changes from versions you point it to (Github versions) More could be done there. Thanks for the feedback!
1 like • 9d
@Clare Martinez It maps the folder/repo you point it at. It then looks for any file and folder references inside the text files. If it doesn't find a a reference, that is when it is flagged. It should catch the orphaned files. If you find one that is called out that is not let me know. I am glad it helped!
Connection Hub: 🧱 Data & Infrastructure Tech
Intros for The Connection Hub - The Vault 👤 Who I am: (name + where you're based) 🛠️ What I actually do: (the specific work — not "I'm in real estate" but "I run a 3-agent team doing residential resale in Austin") 🤖 What I'm building with AI right now: (your current project, workflow, or the thing you're stuck on) 🎯 What I'm looking for connection-wise: (pick one or two) 💡 Someone who's solved [X] 🤝 A collaborator / accountability partner 👀 Just here to learn from people in my field 🧰 Trading workflows & systems 📬 Best way to reach me: (DM here / comment / link)
10 likes • Jul 8
👤 Who I am: Toby I Minneapolis, MN 🛠️ What I actually do: Cloud Systems Analyst - QA and Support for a custom Hardware + SaaS company 🤖 What I'm building with AI right now: Plumbline - Coding agentic pipline - Build with ICM in mind. all auditable Polis - a society sim game using LLM as faction leaders you have to negotiate with. At the job - A integration program with Jira and Smartsheet APIs 🎯 What I'm looking for connection-wise: To learn, Open to colabs. Also a job in the field 📬 Best way to reach me: DM here works. https://profile.bytesbytoby.workers.dev/
0 likes • 24d
@Bill Bloomenkranz Hi bill. The short answer is each step uses what the previous one produces. If it is not there warnings go off. Then I have an independent auditor spun up that goes back to the spec and sees if the end result matches/does what was in the spec. It also helps when you need to change things. Change the spec and it remodels it all. Send me a message if you want to talk more.woyld love that
Jev is a Gamechanger!
What is Jev? A newly released decision model: you give it text and a set of options, and it tells you which option fits and how sure it is. And it does so extremely fast and cheaply. I did several tests. This is what I saw. In my own test it labelled 14,007 emails in 4 minutes for about $0.50. Running the same job through Sonnet would have cost about $42 and taken a lot longer. On a smaller run the answers were as good while being 80 times cheaper and fast enough you could use it practically in real time. Why does any of this matter? Let me explain in an example of a workflow that would crank on this: You have incoming email. Send it through a decision tree: - Is the email for support or finance? - Jev - If support, what product is it for? - Jev - If for a TV, is it about the recall, or which of 3 TVs? - Jev - If recall, send canned message - code - Depending on which TV, assign to X person - code - Search documents based on the question and draft a first response - LLM The expensive LLM no longer does all the decision tree work it would have in the past. Jev does that for about 1/80th of the cost. The LLM (Or Human) is at the end of the tree not spending time pointing it in the right direction. The recall is an example of adding a new or temporary category. With Jev that means writing one more sentence describing it. No retraining, no labelled examples. If it's a recall, send them where to go for it and no LLM is called at all. It's cheaper than it looks. Questions about the same email can all go in one call: support or finance, which product, recall or not. The whole top of the tree comes back in one round trip. Only the LLM step at the bottom has to wait. Where it needs care There will always be ambiguity in text. LLMs and Jev are susceptible to this. Jev returns a confidence score that you can choose how to interpret. Is 70% good enough to move to sending a response before a human looks at it? It's cheap enough to run on every email even when a human still reads them all. It sorts the pile and flags the unsure ones first.
3 likes • Sep 25
Thanks everyone for the feedback! @Bas Rosario I am curious what you come up with. On Laya (A local model) vs Jev and my testing: ( @Alex Elger @Stephen Ward ) My main testing on a mostly junk email account. 3 labels Promotion, Notification (Bill/receipt), Personal. 100 hand inspected by me for sorting. The personal was the hardest to judge because some were friends telling me about a gathering so possible mixed with Notifications. I struggled classifying some of them. Argimax accuracy Sonnet 5 0.727 Jev 0.717 Laya 0.434 Laya's top scoring matched mine less than 50% of the time. This is a job that I have not trusted with confidence with any LLM yet. But other jobs, I would have to test before trusting.
1 like • Sep 26
@Bas Rosario they were clustered. It classified promotion and personal at near the same level. I see many possibilities to use it. I wash I had the project to take full use of it.
Show me what you're building 🧱
I don't want a progress percentage today. I want to know what's actually changing. If you've been working through Building Your Stack, what is one decision you've made because of it? - Maybe you added something. - Maybe you removed something. - Maybe you realized part of your current stack makes absolutely no sense. 😂 Whatever it is, post it below. What did Building Your Stack make you rethink? And if you've been flying through the lessons but skipping the quizzes or accountability posts... Go back. Those are there to make sure you can actually explain and apply what you're learning rather than just consuming it. Drop your biggest realization below. 👇 And keep going. New roadmap next Friday, September 25th.
0 likes • Sep 18
Went back to my cycling router this week. Basically give AI a length and a start time for a bike ride. It give me a route and a place to stop (art fair, farmers market, etc.) takes into account weather and wind direction. This issues are I don't want a turn by turn. I want landmark by landmark that have good cycling infrastructure between them. Without building the landmark and path structures myself (Nodes and links) it fails. Giving AI another try at mapping it.
What OS are you running, and why did you stay?
Your operating system is one of those quiet decisions that shapes every tool after it. I'm curious what this room actually runs. 1. What OS are you on day to day? 2. Why that one over the alternatives? 3. How long have you been on it? I'll go first: I've been a die hard Mac girl my entire life from a ui and creative perspective they always gave me the best experience. However now with the age of Ai I'm experimenting with Omarchy Linux, It is a Distro that has a skill for the OS... So yes that does mean we are in the Vibe-Code your own OS modification era. Just remember... With great power... Comes great hallucinations... No wrong answers. Dual boot counts. Distro names welcome. The "I switched last month because X" stories are the useful ones. OMARCHY: https://omarchy.org/ //A<3
Poll
73 members have voted
What OS are you running, and why did you stay?
0 likes • Sep 8
Windows and Linux.
1-10 of 134
Toby Iverson
6
1,434 points to level up
@toby-iverson-8674
Older QA/systems analys getting into AI.

Active 2h ago
Joined Aug 2, 2026
Twin Cities
Powered by