academic

Identify relevant benchmarks and generate experiment plans for ML papers. Use when asked to "find benchmarks", "what datasets should I use", "experiment plan", "baseline comparison", "standard evaluation", "what to compare against", or "evaluation protocol". Searches arXiv for benchmark papers and extracts evaluation protocols.

Interactive decision tree for finding the right Research Agora skill. Use when asked to "which skill should I use", "what skill do I need", "find me a skill for", "I want to do X what skill helps", "help me pick a skill", "what can the Agora do for", "I need help with X", "recommend a skill", or "what skills exist for". Maps a natural-language task description to the most relevant skills with confidence scores and example invocations.

Sync ML experiment results to paper drafts. Use when asked to "update results", "sync experiments", "pull latest metrics", "update tables from code", "experiment to paper", "refresh results", or "sync paper with repo". Extracts metrics from code/logs and updates paper sections.

Scans the current directory and recommends the single fastest Research Agora "wow moment". Use when asked for "quick start", "what should I run first", "fastest result", "show me something useful", "I want to try this", "give me a demo", "what can I do right now", "get me started fast", "what's the best first thing to try", or "impress me". Auto-detects project contents and returns THE single best skill to run right now, with the exact command using the user's actual filenames.

Write related work sections and discover relevant literature for ML papers. Use when asked to "write related work", "find related work", "literature review", "survey the field", "find papers on [topic]", "build bibliography", "survey prior work", "position the paper", or "what papers should I cite". Supports both guided mode (provide papers to include) and autonomous mode (multi-query arXiv searches with paper approval workflow).

Academic paper writing skills for ML conferences (NeurIPS, ICML, ICLR, AAAI).