{"skill":{"slug":"deepagents-code-review","displayName":"Deepagents Code Review","summary":"Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or...","tags":{"latest":"1.0.1"},"stats":{"comments":0,"downloads":188,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":2},"createdAt":1773973978599,"updatedAt":1777360576434},"latestVersion":{"version":"1.0.1","createdAt":1776830949906,"changelog":"- Added explicit \"review gates\" with step-by-step evidence requirements for code review (Locate, Anchor, Classify, Runtime claims).\n- Each finding now must be tied to a specific code quote and file location rather than imports or names alone.\n- Findings about runtime errors or failures require in-code API evidence, removing speculative reasoning.\n- SKILL.md restructured to emphasize stepwise, evidence-bound review for repeatable and defensible output.\n- No changes to the core issue categories, but review process and documentation clarity significantly improved.","license":"MIT-0"},"metadata":null,"owner":{"handle":"anderskev","userId":"s17b1fzefm8nj8j1sdkzrze7gn83pfrg","displayName":"Kevin Anderson","image":"https://avatars.githubusercontent.com/u/17010022?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.prompt_injection_instructions"],"summary":"Detected: suspicious.prompt_injection_instructions","engineVersion":"v2.4.2","updatedAt":1777360576434}}