The AI Skill I Rely On Daily — Priscila Andre de Oliveira, Sentry
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.
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
If you use coding agents in a large, mature codebase, the real bottleneck is comprehension, not generation — this shows how to build a reusable 'catch me up' agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → with modes for architecture, conventions, feature traces, testing, and history so the 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 →'s mental model is right before it plans or implements.
Key quotes
“since December uh 2025, I haven't coded anymore. I'm only prompting”
Priscila Andre de Oliveira
“67% of my AI usage was comprehension and only 2% code generation”
Priscila Andre de Oliveira
“the biggest unlock from AI in a large code base isn't generation. It's comprehension.”
Priscila Andre de Oliveira
“AI is the teammate who never gets tired of your questions. So, there is no dumb questions. It's the cheapest senior engineer out there.”
Priscila Andre de Oliveira
“don't ship slop code into the code base that pays your salary. Ship keynote code.”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
