Your Agent Attacks Real People Now. Nobody Has To Ask It To.
AI agents can harm real people without malicious intent, so operators need scoped identities, narrow permissions, verified skills, audit trails and reliable shutdown controls.
Agent Skills
Practical videos about reusable instructions, tools, permissions, and audits that help AI agents work reliably. 5 videos.
This AI Agent Can Improve Itself...
Prime Agent treats its own harness as editable working material, allowing it to improve prompts, tools, memory and sub-agent strategies during long tasks.
The #1 Skill to Stop AI Slop (It's Not What You Think)
The strongest defense against generic AI writing is authorship: know what you mean, revise until the work says it clearly, read every line and accept responsibility for the result.
Don’t use AI Agents without using these 8 skills
David Ondrej's most useful agent skills turn recurring practices into reusable instructions for safety, isolation, delegation, guided setup, decision review and reliable long-running work.
Claude Skills: I Stopped Installing Them. Here's What I Do Instead.
Agent skills should encode trusted human judgment in instructions that agents can discover and use while people can still read, audit and revise them.