Pstack's principle skills: short rules agents must name when they use them
- Source
- x.com
- Date
perhaps one of the most durable parts of pstack are its engineering principles: very concise skills (~10-20 loc) that distill down good practices into its core. as models get smarter, i expect most of pstack skills to compress into short principles or workflows (a generic list of steps) and that i will be able to delete a few of them. how it works is that /poteto-mode contains a short index of available principles and tells agents "In your reply, name each principle that shaped a decision and the specific choice it changed." this is why you'll often see a Principles Named or Used section at the end of the agent's response many of these principles were extracted from my sessions correcting agents since the start of this year. some are inspired by problems i see people talk about, like Attack the Premise, inspired by @VictorTaelin's post https://t.co/qTGVfoKSyD you can also use the principles as skills if you want greater control, by invoking /principle-<name> https://t.co/wuTWsflVN3
Shows a lightweight way to steer coding agents: 10-20 line principle skills plus a rule that the names the principle behind each decision, making its use of guidance auditable.
- Pstack's principles are deliberately tiny skills of roughly 10 to 20 lines each, and the author says many were extracted from sessions spent correcting agents since the start of this year.
- The /poteto-mode holds a short index of principles and tells agents to name each principle that shaped a decision and the specific choice it changed, which is why replies end with a Principles Named or Used section.
- Each principle can also be invoked directly as /principle-<name> for tighter control, and the author expects many longer pstack skills to compress into short principles or generic workflows as models get smarter.
- distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
- 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.
Checking sign-in…
Loading comments…