Something to keep in mind is if your CLAUDE.md file is getting large, consider alternative approaches especially for repeatable tasks. Using slash commands and skills for workflows that are repeatable is a really nice way to keep your rules file from exploding. I have slash commands for code review, and git commit management. I have skills for complex tool interactions. Our company has it's own deployment CLI tool so using skills to make Claude Code an expert at using this tool has done wonders to improve Claude Codes performance when working on CI/CD problems.
I am currently working on a new slash command /investigate <service> that runs triage for an active or past incident. I've had Claude write tools to interact with all of our partner services (AWS, JIRA, CI/CD pipelines, GitLab, Datadog) and now when an incident occurs it can quickly put together an early analysis of a incident finding the right people to involve (not just owners but people who last touched the service), potential root causes including service dependency investigations.
I am putting this through it's paces now but early results are VERY good!
If you are consistent with how you do your projects you shouldn't need to update CLAUDE.md nearly every day. Early on, I was adjusting it nearly every day for maybe a couple of projects but now I have very little need to make any adjustments.
Often the challenge is users aren't interacting with Claude Code about their rules file. If Claude Code doesn't seem to be working with you ask it why it ignore a rule. Often times it provides very useful feedback to adjust the rules and no longer violate them.
Another piece of advice I can give is to clear your context window often! Early in my start in this I was letting the context window auto compact but this is bad! Your model is it's freshest and "smartest" when it has a fresh context window.
> I'm a bit of a control freak so I'll usually explicitly direct claude to "load the wireframe-skill" and then do X.
You shouldn't do this, it's generally considered bad practice.
You should be optimizing your skill description. Often times if I am working with Claude Code and it doesn't load I skill, I ask it why it missed the skill. It will guide me to improving the skill description so that it is picked up properly next time.
This iteration on skill description has allowed skills to stay out of context until they are needed rather predictably for me so far.
There are different ways to use the tool. If you chat with the model, you want it to naturally pick the right tool to use based on vibes and context so you don’t have to repeat yourself. If you are plugging a call it Claude code within a larger, structured workflow, you want the tool selection to be deterministic.
So there seems to be some confusion around fingerprinting related to identifying characteristics and tracking. These are two different things. Setting your timezone to UTC, masks that one characteristic of your "identity". But there are better signals for location than timezone, like GeoIP. Same with hiding capabilities. All this does is make the web harder for you but it doesn't make your untrackable. Trackability comes from a combination of factors both within and out of your browser's control. If you share your IP with a family of 4, and you go changing your request headers you are only making yourself MORE trackable. The fact that one request comes across with UTC as a timezone and others come back with EST or other timezones, means I now can track a single user on this single IP. This is made worse if you and your family are using different browsers or different devices.
So what do we care about? If you care about being untrackable, then you have a couple of options, rotate VPNs, or cycle your public facing IP often. Additionally, every request you make MUST change up the request headers. You could cycle between 50 different sets of headers. Combine these two and you will likely be very hard to fingerprint.
If you only care about being identified, use Tor + the Tor browser which makes A LOT of traffic look identical.
I have a Bosch as well, i sprinkle a bit of powder on the door. It has a pre-wash run which goes quick.
The manual is likely referring to not hand rinsing dishes before loading them which was very common 30 or 40 years ago. I had to train my Mother to stop doing that.
This! I mean, at least get all of the low-hanging fruit with a quick, needle-spray pass of hot water. And to do so while the plates are still fresh so that stuff hasn’t had the time to dry.
Like, we’re talking about powering through table settings for a half-dozen people at a family dinner in less than 60 seconds. Plates, bowls, cups, silverware; everything done in about 10s per person. This isn’t any kind of a deep scrub; it’s removing everything that will come off easily as fast and expediently as possible before the dishes go into the washer.
JWP Connatix is the most comprehensive independent video technology and monetization platform, helping broadcasters, publishers, and advertisers deliver premium streaming and online video experiences while maximizing video revenue across all screens. The company offers an end-to-end platform that streamlines live and on-demand video with hybrid monetization models, unique data and insights, unmatched customer service, and the largest independent premium video marketplace, providing the entire media ecosystem with enhanced scale, transparency, and revenue.
We are looking for a skilled and adaptable AI Engineer to join our AI Proof of Concepts team at JWP Connatix. You'll be responsible for implementing AI-First development methodologies, integrating sophisticated AI tools into our software pipeline, and rapidly building MVP prototypes that demonstrate innovative solutions. This role offers the opportunity to work at the cutting edge of AI-integrated development while delivering high-impact prototypes in a fast-paced, iterative environment. The ideal candidate thrives in rapid prototyping environments, has hands-on experience with AI tool integration, and enjoys the challenge of quickly turning concepts into working demonstrations for stakeholder validation. Candidates should also know, and work with AI code generation tools (Claude Code, Cursor, Copilot, etc).
If this sounds like something you'd be interested in please apply!
Completely agree, but I think companies need to be aware of the AWS risks with third parties as well. Many services were unable to communicate with customers.
Hosting your services on AWS while having a status page on AWS during an AWS outage is an easily avoidable problem.
JWP Connatix is the most comprehensive independent video technology and monetization platform, helping broadcasters, publishers, and advertisers deliver premium streaming and online video experiences while maximizing video revenue across all screens. The company offers an end-to-end platform that streamlines live and on-demand video with hybrid monetization models, unique data and insights, unmatched customer service, and the largest independent premium video marketplace, providing the entire media ecosystem with enhanced scale, transparency, and revenue.
We are looking for a skilled and adaptable AI Engineer to join our AI Proof of Concepts team at JWP Connatix. You'll be responsible for implementing AI-First development methodologies, integrating sophisticated AI tools into our software pipeline, and rapidly building MVP prototypes that demonstrate innovative solutions. This role offers the opportunity to work at the cutting edge of AI-integrated development while delivering high-impact prototypes in a fast-paced, iterative environment. The ideal candidate thrives in rapid prototyping environments, has hands-on experience with AI tool integration, and enjoys the challenge of quickly turning concepts into working demonstrations for stakeholder validation. Candidates should also have know and work with AI code generation tools (Claude Code, Cursor, Copilot, etc).
If this sounds like something you'd be interested in please apply!
reply