Compound Engineering 3.27 adds /wtf skill to make agents explain themselves in plain language
RichmanRonald · x · 2026-09-20
Agent communication is often frustrating; Claude's "output styles" try to fix this with concise style but are hit and miss. Compound Engineering 3.27 introduces the /wtf skill for moments when an agent's reply stops making sense:
- Run it bare and it restates the agent's last message in plain language
- Pass a prompt, file path, URL, or pasted passage and it explains that instead
- It explains, never rewrites: opens with the point, says what it means for you, omits what you don't need
It's distinct from ce-explain (investigates code and history) and ce-noslop (rewrites prose, keeps facts). Use $wtf in Codex, /skill:wtf in oh-my-pi; manual invoke only.
More from coding & agent
- Dev forks MiniMax's terminal coding agent, maintains separate branch with security updates — jasonkneen · 2026-09-20
- Kevin Rose built an offline Grok Bot that turns years of saved IG videos into a searchable md wiki — minchoi · 2026-09-20
- How do teams validate citations in production RAG? Duplicate-source checking called too narrow — No-Profile-6178 · 2026-09-20
- Dev spent a quarter saying "I'm on it" with nothing to show for it — cto_junior · 2026-09-20
- LangChain's Jev-as-a-Judge: cheap, fast semantic verifiers for agent evals — multiply_matrix · 2026-09-20
- Research agents' hidden failure mode: citations that look independent but share one source — No-Profile-6178 · 2026-09-20