I love that it's made with AI/LLM, maybe even claude itself. Even the site that lists the flaws of the system is made with that system. Simply shows me that people are not scared off by all those flaws.
I tried a bunch of "open" tools last week, but turns out they are a paid tool in disguise most of the time. I eventually paid for CleanShotX for my work and have peace of mind because it just works. OBS is IMO much more stable and aimed at live streaming anyway.
ShareX has been around for ever but just updated the UI and now super easy to do capture work with annotations and cam output etc (no studio but it's light weight)
btw I use OBS virtual camera its one of my fav features with masking etc for a video avatar vlogger effect
I have a project-specific prompt saved as a text file. It is very basic, just focusing on the app's most important security issues. I kept it broad, so as not to over-specify.
Something along the lines of: "Please run a full security analysis on the entire project. Make sure user documents are secure."
Just something like that prompt found a vector in my web app's MCP server that I never would have considered. It was very much an edge case, but it did exist.
Being broad allows the model and harness to do the work. Giving too many instructions can apparently work against you in many cases.
Of course, when dealing with new PRs, I use the /security-review and /code-review skills.
It's rather broad right now. I started reverse engineering a mac app and it started reading some binary data and then quickly told me to switch to Opus 4.8 to continue, because the guardrails kicked in.
reply