Explorar skills
2.905 skills encontradas
claude-api
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
bio-data-visualization-sequence-logos
Build sequence logos from aligned DNA, RNA, or protein motifs using ggseqlogo (R), Logomaker (Python), or WebLogo with explicit bits vs probability encoding, background-frequency correction, custom alphabets, and multi-logo stacking. Use when visualizing motif PWMs (TF binding, splice sites, CRISPR spacers), aligned-position composition, or comparing two motif sets.
bio-seq-objects
Create and manipulate Seq, MutableSeq, and SeqRecord objects using Biopython. Use when creating sequences from strings, modifying sequence data in-place, or building annotated sequence records.
api-vs-selfhost-skill
Avalia a economia de LLMs entre API e auto-hospedagem, e o ROI de fine-tuning, aproveitando o contexto do usuário, preços de GPU e API em tempo real, e rankings de qualidade para calcular VRAM, horas faturadas e CAPEX e assim tomar decisões ótimas.
bio-metagenomics-visualization
Visualize metagenomic profiles using R (phyloseq, microbiome) and Python (matplotlib, seaborn). Create stacked bar plots, heatmaps, PCA plots, and diversity analyses. Use when creating publication-quality figures from MetaPhlAn, Bracken, or other taxonomic profiling output.
api-route-design
Use para projetar endpoints de API RESTful em projetos FastAPI ou Python, cobrindo a criação de endpoints GET/POST/PUT/DELETE, validação de requisições com Pydantic, formatação de respostas JSON, seleção de códigos de status, paginação, filtragem e ordenação. Não é para APIs GraphQL, manipuladores WebSocket ou endpoints não-RESTful.
describe-design
Reverse-engineer existing codebases and produce architectural documentation with Mermaid diagrams (C4, sequence, ER, deployment). Use this skill whenever the user asks to document a codebase, explain how a system works, create architecture diagrams, build onboarding documentation, generate a system overview, map dependencies, or describe the design of an existing project. Also trigger when someone
datamol
Um wrapper Pythonic para RDKit com interface simplificada e padrões sensatos, ideal para descoberta de fármacos padrão, incluindo análise de SMILES, padronização, descritores, impressões digitais, agrupamento, conformadores 3D e processamento paralelo. Retorna objetos rdkit.Chem.Mol nativos; para controle avançado, use o RDKit diretamente.
deseq2-differential-expression
Bulk RNA-seq DE with R/Bioconductor DESeq2. Negative binomial GLM, empirical Bayes shrinkage, Wald/LRT tests, multi-factor designs, Salmon tximeta import, apeglm LFC shrinkage, MA/volcano/heatmap viz. R gold standard. Use pydeseq2-differential-expression for Python; use edgeR for TMM normalization.
python-packaging
Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI. Use when packaging Python libraries, creating CLI tools, or distributing Python code.
bio-sequence-properties
Calculate sequence properties like GC content, molecular weight, isoelectric point, and GC skew using Biopython. Use when analyzing sequence composition, computing physical properties, or comparing sequences.
snakemake-workflow-engine
Python-based workflow manager for reproducible, scalable pipelines. Define rules with file-based dependencies; Snakemake resolves execution order and parallelism. Runs local, SLURM, LSF, AWS, GCP via profiles; per-rule conda/Singularity envs. For NGS pipelines, ML training, and multi-step file processing. Use Nextflow for Groovy dataflow or nf-core integration.