tiny_researchers

Search HuggingFace Hub for datasets by keyword. Use when the user wants to find training data, benchmarks, or evaluation datasets for ML/NLP/CV research.

Fetch the FULL TEXT of an arXiv paper (all sections — introduction, method, results, conclusion). Use when you need to read beyond the abstract into the paper's actual content. Only works for arXiv papers. For metadata/abstract only, use paper-read. For local PDFs, use paper-read-pdf.

Two-layer memory system with grep-based recall for research sessions.

Track specific scientific claims across the literature over time — who made it, who replicated it, who challenged it, whether it still stands. Use when verifying a key assumption before building on it, or when checking whether a published result has been updated or superseded.

Scan papers for conflicting empirical claims, methodological disagreements, or opposing conclusions on the same topic. Use when writing discussion sections, evaluating conflicting results, or checking if a claim is contested before building on it.

Synthesize findings across multiple papers into a coherent narrative, structured comparison table, or temporal evolution. Use after collecting papers via survey or paper-search. Goes beyond summarizing individual papers to produce insights that only emerge when reading across the corpus as a whole.

Full end-to-end deep research pipeline on a topic. Use when the user wants thorough, rigorous research — not just a survey. Orchestrates all research skills in sequence: collect → synthesize → critique claims → grade evidence → find gaps → assess reproducibility → optionally reproduce → write report.

Evaluate the strength of evidence behind scientific claims based on study design, replication status, venue quality, sample size, and recency. Use when deciding how much weight to put on a finding, or when calibrating how confidently to write about a result.

Find research gaps and suggest future directions. Analyzes a literature corpus to identify what has NOT been studied, contested, or resolved — surfacing research gaps, contradictions left unaddressed, and methodological blind spots.

Audit a paper's reproducibility before building on its results or before submitting your own work. Checks for missing details (seeds, hyperparameters, dataset splits, hardware), code/data availability, and scores against venue-specific reproducibility standards (NeurIPS, ICML, Nature, etc.).

Conduct a systematic literature survey on a research topic. Collects papers, reads key works, synthesizes findings, detects contradictions, identifies gaps, and produces a structured report.

Read and extract text from a local research paper PDF file. Use when the user has a PDF file on disk (e.g. downloaded from a conference or journal) and wants to read its content, extract specific sections (abstract, methodology, results, conclusion), or understand the paper's structure. Requires the [pdf] optional dependency group.

Brainstorm research ideas, questions, and hypotheses.

Generate professional research reports (survey, proposal, technical).

Reproduce experiments from academic papers — parse paper, setup environment, find datasets, generate code, run and verify.