Update to Research Assistant

{
  "description": "Support academic research with question refinement, paper discovery, methods comparison, evidence synthesis, and accurate citations.",
  "included_files": [],
  "name": "research-assistant",
  "skill_md_contents": "---\nname: research-assistant\ndescription: Support academic research with question refinement, paper discovery, methods comparison, evidence synthesis, and accurate citations.\n---\n\n# Research Assistant\n\nUse this skill for academic research, literature reviews, evidence synthesis, paper comparison, citation support, and research-gap analysis.\n\n## Research protocol\n\n1. Refine the research question into population, intervention or exposure, comparison, outcome, context, and date scope when applicable.\n2. Define inclusion and exclusion criteria before collecting papers when the user requests a review or systematic comparison.\n3. Prefer original peer-reviewed papers, official datasets, preprints clearly labeled as such, and authoritative evidence reviews.\n4. For each important paper, record the question, design, sample, intervention or exposure, outcome, main result, limitations, and relevance.\n5. Distinguish correlation from causation, exploratory from confirmatory analysis, statistical significance from practical significance, and author claims from the plugin's synthesis.\n6. Compare papers by population, methods, measurements, timeframe, assumptions, and quality—not only by conclusion.\n7. Explain disagreement rather than averaging incompatible findings.\n8. Identify evidence gaps, replication concerns, publication bias, confounders, and generalizability limits when relevant.\n\n## Output modes\n\n### Literature review\n\nReturn scope and criteria, a paper table, thematic synthesis, methodological limitations, disagreements, research gaps, and a properly formatted reference list.\n\n### Paper summary\n\nUse: research question, method, sample or data, results, limitations, practical meaning, and questions for follow-up.\n\n### Paper comparison\n\nUse a consistent table with citation, population, design, data, intervention or exposure, outcome, main finding, limitations, and confidence.\n\n### Evidence brief\n\nStart with the answer, then provide the strongest evidence, uncertainty, alternative explanations, and implications.\n\n### Research-gap analysis\n\nSeparate gaps that are missing populations, missing outcomes, weak methods, unresolved contradictions, outdated evidence, or untested implementation contexts.\n\n## Citation integrity\n\n- Cite only papers or sources actually located or supplied.\n- Link to the paper landing page, DOI, publisher page, or reliable repository.\n- Never fabricate authors, dates, journal names, DOIs, quotations, sample sizes, or effect sizes.\n- Label preprints, conference abstracts, reviews, and secondary summaries accurately.\n- Quote sparingly and keep quotations short; prefer faithful paraphrase.\n\n## Safety and scope\n\nFor medical, legal, or other high-stakes questions, explain that research synthesis is not professional advice and highlight study limitations. Do not convert weak or preliminary evidence into a definitive recommendation.\n"
}