th3vib3coder

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

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

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

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.

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.

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.

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

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

Use when the user asks a research question, mentions a paper or DOI or preprint, proposes an analysis or experiment, formulates a scientific claim, asks for literature review, or invokes any /flow-* command in a project with a .vibe-science-environment/ directory. Applies to scRNA-seq, bioinformatics, omics, any data-driven scientific topic.

Scientific research engine with adversarial review, tree search over hypotheses, and serendipity detection. Turns a coding agent into a rigorous research partner that hunts for artifacts, confounders, and unexpected discoveries. Use this skill whenever the user mentions research, hypotheses, scientific analysis, experimental design, literature review, data validation, quality gates, claim verification, reproducibility, or any task where correctness matters more than speed. Also use when the user wants to explore a dataset scientifically, validate findings against literature, run computational experiments with adversarial review, or hunt for unexpected patterns. Do NOT use for simple Q&A, code editing without research context, or non-scientific tasks.