How Do I Know an Agent Skill Is Actually Helping?
Three checks guide my Agent Skill updates: procedural adherence, final task outcome, and human review.
I build practical AI systems, automate repetitive work, and write down what I learn.
Latest writing
Three checks guide my Agent Skill updates: procedural adherence, final task outcome, and human review.
I wanted to watch my bias through a whole group performance, even when there was no individual fancam.
About the project →I wanted a repeatable workflow for translating videos, correcting subtitles, and keeping the segments worth sharing.
About the project →I use a support ticket to examine Jev, the System One name, and the limits of typed decisions, probabilities, and published evaluations.
I break agent memory into writing, storage, retrieval, assembly, and forgetting, then outline a minimal implementation path that starts with a durable event log.
A Skill teaches an agent how to work, a Tool lets it act, MCP connects it to external capabilities, and a Plugin packages the pieces for installation.
A reading note on abductive reasoning, interactive simulation, and what current world models can and cannot do.
Curated reading on systems that recur across the projects.
Field notes on using roles, tools, loops, and checks to make agent workflows useful.
Field notes on separating transcription, translation, vision, and rendering into inspectable media stages.
Field notes on moving useful scripts and AI systems from one machine to dependable cloud services.