查找技能

Scientific research engine for hypothesis testing, literature gap analysis, experimental validation, and data-driven discovery. Enforces adversarial review (Reviewer 2), 32 quality gates, tree search over hypotheses, confounder harness for quantitative claims, and serendipity detection. TRIGGER when: user asks to analyze scientific data, test hypotheses, validate findings, search for research gaps, design experiments, or investigate results. DO NOT TRIGGER when: pure code review, documentation writing, devops tasks, general conversation, or non-scientific data transformation.

中文简介正在准备中。当前显示原文说明。

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.

中文简介正在准备中。当前显示原文说明。

Scientific research in serendipity mode. Infinite loops until discovery, rigorous tracking, adversarial review.

中文简介正在准备中。当前显示原文说明。

Scientific research engine with adversarial review, tree search, and serendipity detection. Use when: exploring hypotheses, validating findings against literature, running computational experiments with quality gates, or hunting for unexpected discoveries. Do NOT use for simple Q&A, code editing, or non-research tasks.

中文简介正在准备中。当前显示原文说明。

Scientific research engine v6.0 NEXUS — adversarial review (Reviewer 2), 32 quality gates, tree search, serendipity tracking, confounder harness, cross-session learning. Use for ANY scientific analysis, hypothesis testing, data validation, literature review, or task where correctness > speed.

中文简介正在准备中。当前显示原文说明。

Use when preparing or writing any committable deliverable (phase closeout, status report, skill file, wave spec, README section, summary document, CHANGELOG entry, or any markdown file declaring completion or pass/fail status). Applies before the write happens, not after. Without this discipline, agents ship 60% deliverables and declare closure prematurely.

中文简介正在准备中。当前显示原文说明。