llm-as-judgeCross-model verification for complex tasks. Spawn a judge subagent with a different model to review plans, code, architecture, or decisions before execution....
autoresearch-skill-optimizerAuto-improve any OpenClaw skill using Karpathy's autoresearch loop. Runs skill repeatedly against test inputs, scores against a yes/no checklist, makes one t...
x-thread-readerFetch full text or generate a PDF from any X/Twitter thread using twitter-thread.com. Use when asked to "get the full thread", "read this tweet", "save this...