NEW RUNTIME

Topic hub

Agent Skills

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent skills.

Short answer

  • Agent Skills is tracked here as an evidence-linked topic, not as a static glossary entry.
  • The page connects raw observations to pattern hypotheses, longer analysis, and public sources.
  • Use it as the canonical landing page before drilling into individual records.

Pattern memory

Current hypotheses

1 patterns
  1. medium

    Skills become a portable capability layer

    Agent skills are emerging as a portable capability layer, but their value depends on progressive disclosure, provenance, security review, and behavioral evaluation.

Raw signals

Recent observations

4 signals

  1. Agent skills need behavioral evals, not prose review

    Benchmarks show that expert-authored skills can help while self-generated skills can underperform a no-skill baseline.

  2. Improve routes architecture and execution to different models

    The Improve skill audits a repository with a stronger planning model and delegates bounded fixes to cheaper executors.

  3. Large-task planning moves from chat into a ticket graph

    Matt Pocock's workflow turns discovery, specification, tickets, implementation, and review into durable linked artifacts.

  4. Pydantic AI loads capabilities only when needed

    A capability can bundle instructions, tools, model settings, and hooks while exposing only a compact description until activation.