Tag: agent skills

Choose one workflow, try it on a real task, and check what your assistant actually used.

How I revised agent workflows to preserve decisions, failed checks, and unfinished work—and what limited checks across Codex, Claude, and Antigravity actually showed.

Two recent preprints make the practical case for quarantining, pinning, reviewing, and testing third-party agent skills before installation.

A critical guide to README.md, AGENTS.md, CLAUDE.md, SKILL.md, .agents, and .claude patterns for teams that want coding agents to follow repo rules without stuffing every workflow into one giant prompt.

A repo-ready operating contract for agent skills that prevents prompt bundles from drifting into unsigned, over-permissioned, unreviewed production dependencies.