crag666
- 15 skills
- 0 followers
- 3 hours ago last updated
- ▌ Literature Review · crag666 bundleConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
- ▌ Polars · crag666 bundleHigh-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.
- ▌ Markitdown · crag666 bundleConvert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
- ▌ Scientific Writing En · crag666 bundleUse whenever the user writes, drafts, revises, edits, polishes, or translates scientific or academic prose in ENGLISH - Q1 research articles, theses, dissertations, abstracts, introductions, methods, results, discussions, conclusions, acknowledgments, literature reviews, grant proposals, conference papers, or any IMRaD section. Triggers: "write the introduction", "draft the abstract", "help me with the discussion", "polish this scientific paragraph", "translate this paper to English", "this sounds like AI, rewrite it", "write the methods section", "I need phrases for...", "academic English", "make this sound more academic", "make this Q1-ready".
- ▌ Senior Dev Principles · crag666STRICT structure-and-complexity layer for non-trivial code work: designing systems, writing new modules, refactoring, implementing algorithms, or making structural decisions. Complements code-style-defaults (form of the output) and python-native (Python stdlib): this skill decides how code is structured and how fast it runs — target big-O before writing, single-responsibility grain, policy constants, testability, and per-language defaults for TypeScript, C, C++, and SQL. Triggers: "design X", "refactor this", "implement an algorithm/feature/service", "optimize this", "review this code", "what's the best way to structure X", or any task involving architecture, complexity reasoning, or multi-file changes. SKIP for trivial edits (rename, typo, single-line fix), config tweaks, and documentation edits.
- ▌ Redaccion Cientifica Es · crag666 bundleUsar siempre que el usuario escriba, redacte, revise o traduzca texto científico/académico en ESPAÑOL: artículos, papers, tesis, abstracts, introducciones, metodologías, resultados, discusión, conclusiones, agradecimientos, revisiones de literatura, defensas, propuestas de investigación o cualquier sección IMRyD. Aporta más de 5000 frases "precocinadas" idiomáticas y formales para cada sección estándar de un documento científico, evitando la prosa robótica/IA. Disparadores: "escribe la introducción", "redacta el abstract", "ayúdame con la discusión", "mejora este párrafo científico", "tradúceme este paper", "redacta la metodología", "necesito frases para...", "esto suena a IA, mejóralo".
- ▌ Seaborn · crag666 bundleStatistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.
- ▌ Inciteful · crag666 bundleCitation-network literature discovery via Inciteful (incitefulmed.com/academic). Find similar papers, key papers by PageRank, reviews, top authors/institutions/journals around seed papers, and shortest citation paths between two papers. Free, no API key.
- ▌ Matplotlib · crag666 bundleLow-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
- ▌ Scikit Bio · crag666 bundleBiological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
- ▌ Paper Search · crag666 bundleSearch for academic papers by keyword, or look up a specific paper by DOI or OpenAlex ID. Powered by OpenAlex (250M+ works, free, no API key).
- ▌ Patent Search · crag666Prior art patent search via Google Patents' JSON endpoint and Lens.org, with PDF download. Use when the user asks to search patents, prior art, "anterioridad", "patentes ancla", freedom-to-operate, novelty context, or patent landscaping. Covers query syntax, CPC filtering, date/status filters, anchor-patent matrices, and downloading patent PDFs.
- ▌ Python Native · crag666 bundleSTRICT: stdlib idioms are mandatory — reinventing a stdlib feature is a defect, not a style choice. Apply whenever the user writes, refactors, optimizes, or reviews Python, including one-liners and code-review feedback. MANDATORY: check references/ locally first, then WebFetch docs.python.org for every non-trivial stdlib API before using it — memory alone is a defect. Replaces common reinventions: manual dict counters with `Counter`, `dict.setdefault` loops with `defaultdict`, `isinstance` chains with `singledispatch` or `match`/`case`, hand-rolled memoization with `functools.cache`, `os.path.join` with `pathlib.Path`, `sorted(...)[:k]` with `heapq.nlargest`, manual class boilerplate with `dataclass(slots=True, frozen=True)`, `zip(lst, lst[1:])` with `itertools.pairwise`. Covers Python 3.9-3.14 via references/python-3.X.md. Trigger phrases: "write a Python function", "refactor this Python", "Pythonic way to X", "optimize Python code", "implement X in Python", or any task whose answer involves Python source.
- ▌ Code Style Defaults · crag666Personal defaults for any generated or edited code, any language (incl. Typst/LaTeX) – files, patches, chat snippets, scripts, config, notebooks: check for an existing library first, then emit the smallest correct code with no AI filler (no unrequested comments, docstrings, demos, defensive scaffolding). KISS/YAGNI/DRY/SRP; less code is less debt. Governs the form of the output, not the architecture. Precedence: user instruction > file convention > this list. Skip only on explicit user contradiction or strong local convention.
- ▌ Ml Science Discipline · crag666 bundleEnforces rigorous scientific methodology for machine learning experiments intended to support publication-grade claims (Q1 journals, conference papers, regulated decisions). Use this skill when designing an ML pipeline, splitting datasets, evaluating performance, selecting features, tuning hyperparameters, comparing models, quantifying uncertainty, validating externally, or preparing results for a paper. Consult it for any task where experimental validity, reproducibility, or publication standards (TRIPOD+AI, CLAIM, STARD-AI, CONSORT-AI) are in scope. Routine "train a model" or "compute accuracy" requests do NOT automatically trigger this skill unless results will be reported, compared, or acted on.