Why skills matter: consistency, accumulation, and optimization as code
dbreunig · x · 2026-11-05
dbreunig argues for creating skills (and eventually mature code workflows), with his article excerpt explaining three benefits of turning a workflow into an artifact:
- Consistency: a few words or a slash-command stand in for the entire workflow text.
- Accumulation: shortcomings found in use have a place to live — ask the agent to update the skill.
- Optimization: once the procedure firms up, test it on smaller models and peel off parts (or all) into code — the most overlooked benefit.
He develops skills with frontier models but runs his personal agent's workflows on the much smaller GLM 5.3 Flash plus a couple of Python scripts; captured requirements survive model changes. "We shouldn't employ Fable to sort our emails, just as we wouldn't hire a McKinsey consultant to mow our lawn."
Related event: Drew Breunig: Most Agent Work Will Solidify into Coded Workflows(3 posts)→
More from coding & agent
- Dev finds pi coding tool defaults to Opus 4.8 on a fresh install — lucasmeijer · 2026-11-05
- Kylon puts whole teams and agents in shared rooms, with a Neon branch per app draft — jefrankle · 2026-11-05
- "Evals > vibes": agent workflow debates are just guessing without eval stats — annetgriffin · 2026-11-05
- OpenAI hackathon winner joins YC, launches Raven, an agent-first phone — ycombinator · 2026-11-05
- Open-source Cicada brings real-time translation and AI meeting notes to any Mac call, free 50h/month — dotey · 2026-11-05
- IBM launches AI coding assistant named "Bob", devs can't stop laughing — zeeg · 2026-11-05