We Vetted 2000 AI Skills Before They Reached Developers — Lucas Palma, Nubank
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → skills are executable dependencies with supply-chain risk. This is a working gate design: deterministic checks for destructive commands, an LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → pass for the context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → they miss, then scoped permissions and human approval before anything reaches a marketplace.
