Hacker News
HumanLayer's /show-me Skill Forces Coding Agents to Answer in Diagrams Instead of Prose
HumanLayer published the /show-me agent skill on August 12, framing verbose agent output as a usability regression: 'agents got more intelligent on paper, but the experience of using them got noticeably worse.' Invoking it directs the agent to reply in component trees, call stacks, diagrams, file layouts, pseudocode, type signatures, or HTML mockups rather than explanatory text. It runs natively in HumanLayer and installs elsewhere via `npx skills add humanlayer/skills --skill show-me` — a small, copyable pattern for anyone whose agent buries the answer in paragraphs.
↳ Follow the thread