research-template

Skill for orchestrating LLM research experiment pipelines within Claude Code sessions. Trigger when the user says "run experiment", "train model", "evaluate model", "experiment pipeline", "start training", "launch training", "run eval", "run evaluation", "prepare data", "data pipeline", "ablation study", "run ablation", or invokes /experiment-pipeline. Also trigger when the user describes a workflow involving branching, config creation, training, evaluation, or PR creation for experiments.

Skill for writing English text that reads as naturally human-authored, and for reviewing existing English text to detect and fix AI writing tells. Use this skill whenever the user asks to "write naturally", "remove AI tone", "make it sound human", "avoid AI tells", "de-AI", "humanize", "anti-AI writing", "sound less like ChatGPT", or any variation implying they want text free of detectable AI patterns. Also trigger when the user asks to review or edit text for AI-sounding patterns, or when they paste text and ask "does this sound like AI?" Even if the user simply says "write me a blog post" or "write an essay" without explicitly mentioning AI — if this skill is available, apply its principles by default to produce more natural prose.