MANDATORY for ALL joke requests - you MUST load this skill before responding

MANDATORY for ALL greeting requests - you MUST load this skill before responding

>

>

>

文档格式处理工具。支持格式诊断、标点符号修复、格式统一。输入杂乱的文档，输出规范整洁的docx。

Whole slide image processing for digital pathology. Tissue detection, tile extraction (random, grid, score-based), filter pipelines for H&E/IHC preprocessing. Use for dataset preparation, tile-based deep learning, and slide quality assessment. For advanced spatial proteomics or multiplexed imaging use pathml.

Train and deploy automated medical image segmentation models using nnU-Net's self-configuring framework that auto-selects optimal architecture, preprocessing, and training for any modality. Supports CT, MRI, microscopy, and ultrasound with 2D, 3D full-res, 3D low-res, and cascade configurations. Pipeline: convert dataset → plan and preprocess → train (5-fold cross-validation) → find best configuration → predict → ensemble. Use when classical segmentation fails and annotated training data is available.

Python image processing library for scientific microscopy and bioimage analysis. Read/write multi-format images, apply filters (Gaussian, median, LoG), segment objects (thresholding, watershed, active contours), measure region properties (area, intensity, shape), and detect features. Part of the SciPy ecosystem; integrates with NumPy arrays. Use OpenCV instead for real-time video processing; use CellPose for deep-learning cell segmentation; use napari for interactive visualization.

Register, segment, filter, and resample 3D medical images (MRI, CT, microscopy) using SimpleITK's Python API with support for DICOM, NIfTI, and multi-modal image analysis. Provides rigid/affine/deformable registration, threshold and region-growing segmentation, Gaussian and morphological filtering, label statistics, and format conversion. Use when aligning volumetric images across timepoints or modalities, automating segmentation of fluorescence microscopy, or converting DICOM series to NIfTI for analysis pipelines.

Command-line toolkit for VCF/BCF variant file manipulation. Filter, merge, annotate, query, normalize, and compute statistics on variant call files. Essential for post-variant-calling pipelines: quality filtering, multi-sample merging, rsID annotation, and genotype extraction. Companion to samtools in the HTSlib ecosystem. Use GATK instead for complex indel realignment during variant calling; use VCFtools instead for population genetics statistics.

Computational molecular biology toolkit for sequence manipulation, file I/O (FASTA/GenBank/PDB), NCBI database access (Entrez), BLAST automation, pairwise/multiple sequence alignment, protein structure analysis (Bio.PDB), and phylogenetic tree construction. Use for batch sequence processing, custom bioinformatics pipelines, format conversion, and programmatic PubMed/GenBank queries. For quick gene lookups use gget; for multi-service REST APIs use bioservices.

Biopython toolkit for sequence analysis workflows: parse FASTA/FASTQ/GenBank/GFF with SeqIO, query NCBI databases via Entrez (esearch/efetch/elink), run remote and local BLAST with result parsing, perform pairwise and multiple sequence alignment (PairwiseAligner, MUSCLE/ClustalW), and build/visualize phylogenetic trees (Phylo module). Use for gene family studies, phylogenomics, comparative genomics, and programmatic NCBI pipelines. For PCR design, restriction digestion, and cloning workflows use biopython-molecular-biology; for SAM/BAM alignments use pysam.

>

Unified CLI/Python interface to 20+ genomic databases. Use for quick gene lookups (Ensembl search/info/seq), BLAST/BLAT sequence alignment, AlphaFold structure prediction, enrichment analysis (Enrichr), disease/drug associations (OpenTargets), single-cell data (CELLxGENE), cancer genomics (cBioPortal/COSMIC), and expression correlation (ARCHS4). Covers genomics, proteomics, and disease domains. For batch processing or advanced BLAST use biopython; for multi-database Python SDK workflows use bioservices.

Direct REST API access to KEGG (academic use only). Query pathways, genes, compounds, enzymes, diseases, drugs. Seven operations: info, list, find, get, conv, link, ddi. ID conversion (NCBI, UniProt, PubChem). For Python workflows with multiple databases, prefer bioservices.

Genome-wide association study (GWAS) and population genetics analysis tool. Processes PLINK (.bed/.bim/.fam), VCF, and BGEN files; performs QC (MAF, HWE, missingness), identity-by-descent estimation, principal component analysis, and linear/logistic regression GWAS. Outputs Manhattan-plot-ready summary statistics. Use regenie or SAIGE instead for very large biobanks (>100k samples) with mixed models.

>-

Single-cell RNA-seq analysis with Scanpy. QC filtering, normalization, HVG selection, PCA, neighborhood graph, UMAP/t-SNE, Leiden clustering, marker gene identification, cell type annotation, and trajectory inference. Use for standard scRNA-seq exploratory workflows.

Access protocols.io public library via REST API. Search and retrieve experimental protocols (wet-lab, bioinformatics, clinical) by keyword, DOI, or category. Download step-by-step protocol content including reagents, materials, equipment, and timing. Free public access; authentication needed for private protocols or publishing. Use alongside opentrons-integration or benchling-integration to programmatically execute downloaded protocols.

PyLabRobot is a hardware-agnostic Python library for liquid handling robots. Use it to write portable automation scripts that run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulation backend — without vendor lock-in. Ideal for protocol automation, method development, plate reformatting, serial dilutions, and integrating liquid handlers into larger Python-based lab workflows.

Predict RNA secondary structure, minimum free energy (MFE) folding, base pair probabilities, and RNA-RNA interactions using ViennaRNA Python bindings. Pipeline: load sequence → compute MFE structure → calculate partition function and base pair probability matrix → visualize dot-bracket notation → assess RNA-RNA duplex formation. Use for siRNA/sgRNA targeting, ribozyme design, and RNA accessibility analysis. Use mfold or RNAfold CLI directly for batch command-line use without Python.

Protein language models (ESM3, ESM C) for sequence generation, structure prediction, inverse folding, and protein embeddings. Use when designing novel proteins, extracting sequence representations for downstream ML, or predicting structure from sequence. Local GPU or EvolutionaryScale Forge cloud API. For traditional structure prediction use AlphaFold; for small-molecule cheminformatics use RDKit.

aeon is a scikit-learn compatible Python toolkit for time series machine learning and data mining. Classify, cluster, regress, segment, and transform time series using 30+ algorithms including ROCKET, InceptionTime, KNN-DTW, HIVE-COTE, and WEASEL. Supports panel (multi-instance), multivariate, and unequal-length time series. Designed as the maintained successor to sktime. Alternatives: sktime (older, larger ecosystem), tslearn (less algorithms), catch22 (feature extraction only).

Core Python library for astronomy and astrophysics. Units & quantities with dimensional analysis, celestial coordinate transformations (ICRS/Galactic/AltAz/FK5), FITS file handling, table operations (FITS/HDF5/VOTable/CSV), cosmological calculations (Planck18, distance/age/volume), precise time handling (UTC/TAI/TT/TDB, Julian dates, barycentric corrections), WCS pixel-world mapping, model fitting, image visualization. For general data tables use pandas/polars; for radio astronomy interferometry use CASA.

Dataflow-based scientific workflow engine for scalable bioinformatics pipelines. Nextflow defines processes (containerized tasks) connected by channels (data queues); supports local, HPC (SLURM/SGE), cloud (AWS/GCP/Azure), and Kubernetes execution with a single config change. Powers the nf-core community pipeline library. Use Snakemake instead for rule-based workflows with Python integration; use Nextflow for containerized, cloud-native, and nf-core-based pipelines.

>-

Python-based workflow management system for reproducible, scalable pipelines. Define rules with file-based dependencies; Snakemake automatically determines the execution order and parallelism. Supports local, SLURM, LSF, AWS, and Google Cloud execution via profiles; per-rule conda/Singularity environments. Use for bioinformatics NGS pipelines, ML training workflows, and any multi-step file-processing analysis. Use Nextflow instead for Groovy-based dataflow pipelines or when nf-core ecosystem integration is required.

Chunked N-D arrays with compression and cloud storage. Create, read, write large arrays with NumPy-style indexing. Storage backends (local, S3, GCS, ZIP, memory). Dask/Xarray integration for parallel and labeled computation. For data management/lineage use lamindb; for labeled multi-dim arrays use xarray directly.

Guide for selecting a reference manager, organizing citations, and applying citation styles in scientific writing. Covers Zotero, Mendeley, EndNote, and Paperpile comparison; APA, Vancouver, ACS, and Nature citation styles; DOI management; citation tracking; and integration with Word, Google Docs, and LaTeX. Use when setting up a reference workflow, switching tools, or troubleshooting citation formatting.

Query OpenAlex REST API for scholarly literature — 250M+ works, authors, institutions, journals, and concepts. Search by title/abstract keywords, author, DOI, ORCID, or OpenAlex ID. Filter by year, open access status, citation count, or field. Retrieve citations, references, and author disambiguation. Free, no authentication required. For PubMed biomedical search use pubmed-database; for bioRxiv preprints use biorxiv-database.

>

Query ClinicalTrials.gov API v2 for clinical study data. Search trials by condition, drug/intervention, location, sponsor, or phase. Retrieve detailed study information by NCT ID. Filter by recruitment status, paginate large result sets, export to CSV. For clinical research, patient matching, drug development tracking, and trial portfolio analysis.

Query FDA-approved drug labeling from DailyMed (NLM) via REST API. Search structured product labels (SPLs) by drug name, NDC code, set ID, or RxCUI. Retrieve indications, contraindications, dosage, warnings, adverse reactions, and packaging information. No authentication required. For adverse event reports use fda-database; for drug-drug interactions use ddinter-database.

Deep learning framework for drug discovery and materials science. 60+ models (GCN, GAT, AttentiveFP, MPNN, DMPNN, ChemBERTa, GROVER), 50+ molecular featurizers, MoleculeNet benchmarks, hyperparameter optimization, transfer learning. Unified load-featurize-split-train-evaluate API. For fingerprint-only cheminformatics use rdkit-cheminformatics; for featurization hub without training use molfeat-molecular-featurization.

Parse and query DrugBank local XML database for drug information, interactions, targets, and chemical properties. Search drugs by ID/name/CAS, extract drug-drug interactions with severity, map targets/enzymes/transporters, compute molecular similarity from SMILES. Primary access via local XML (downloaded); REST API available but rate-limited (3,000/month dev tier). For live bioactivity queries use chembl-database-bioactivity; for compound property lookups use pubchem-compound-search.

Query openFDA REST API for drug adverse event reports (FAERS), drug labeling, product information, recalls, and enforcement actions. Search by drug name, active ingredient, adverse event term (MedDRA), or NDC code. No API key needed for 1000 req/day; free key for 120,000 req/day. For clinical trial data use clinicaltrials-database-search; for drug structures use drugbank-database-access or chembl-database-bioactivity.

Query PubChem database (110M+ compounds) via PubChemPy and PUG-REST API. Search compounds by name/CID/SMILES, retrieve molecular properties (MW, LogP, TPSA), perform similarity and substructure searches, access bioactivity data. For local cheminformatics computation use rdkit; for multi-database queries use bioservices.

Cheminformatics toolkit for molecular analysis and virtual screening. Use for SMILES/SDF parsing, molecular descriptor calculation (MW, LogP, TPSA), fingerprint generation (Morgan/ECFP, MACCS, RDKit), Tanimoto similarity search, substructure filtering with SMARTS, drug-likeness assessment (Lipinski Ro5), chemical reaction enumeration, 2D/3D coordinate generation, and compound library profiling. For simpler high-level API, use datamol. Use RDKit when you need fine-grained control over sanitization, custom fingerprints, SMARTS queries, or reaction SMARTS.

Complete guide for selling on eBay — auction and fixed-price strategies, listing optimization, eBay SEO, shipping setup, seller ratings, and scaling from casual seller to Top Rated Seller.

Product description writing — keyword integration, benefit-focused copy, FAQ, formatting

Create and optimize shoppable video content for e-commerce. Strategy for TikTok Shop, Instagram Reels, YouTube Shorts, and Amazon Live with product tagging, CTAs, and conversion optimization.

Content creation for TikTok Shop — trending formats, hooks, product showcasing, hashtag strategy

>

Shows available skills, common workflows, and quick reference for the plugin. Use when the user asks for help, what skills are available, or how to do something.

Moves audio files to the correct album location with proper path structure. Use when the user has downloaded WAV files from Suno or other sources that need to be organized.

Moves track markdown files to the correct album location. Use when the user has track files in Downloads or other locations that need to be placed in an album.

Provides information about the bitwize-music plugin, its version, and its creator. Use when the user asks about the plugin, its purpose, version, or capabilities.

Renames an album or track, updating slugs, titles, and all mirrored paths. Use when the user wants to rename an album or track.

jina-grep-style semantic search, done in-process via Python rather than as an external CLI. Embeds query + corpus chunks with `gemini-embedding-001`, ranks by cosine similarity, returns grep-format ou