Processament de dades
Transformació i anàlisi sintàctica de dades
tooluniverse-image-analysis
mims-harvard
Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ/CellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV/TSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area/circularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.
tooluniverse-chemical-compound-retrieval
mims-harvard
Retrieves chemical compound information from PubChem and ChEMBL with disambiguation, cross-referencing, and quality assessment. Creates comprehensive compound profiles with identifiers, properties, bioactivity, and drug information. Use when users need chemical data, drug information, or mention PubChem CID, ChEMBL ID, SMILES, InChI, or compound names.
tooluniverse-multiomic-disease-characterization
mims-harvard
Comprehensive multi-omics disease characterization integrating genomics, transcriptomics, proteomics, pathway, and therapeutic layers for systems-level understanding. Produces a detailed multi-omics report with quantitative confidence scoring (0-100), cross-layer gene concordance analysis, biomarker candidates, therapeutic opportunities, and mechanistic hypotheses. Uses 80+ ToolUniverse tools across 8 analysis layers. Use when users ask about disease mechanisms, multi-omics analysis, systems biology of disease, biomarker discovery, or therapeutic target identification from a disease perspective.
tooluniverse-clinical-guidelines
mims-harvard
Search and retrieve clinical practice guidelines across 12+ authoritative sources including NICE, WHO, ADA, AHA/ACC, NCCN, SIGN, CPIC, CMA, CTFPHC, GIN, MAGICapp, PubMed, EuropePMC, TRIP, and OpenAlex. Covers disease management, cardiology, oncology, diabetes, pharmacogenomics, and more. Use when users ask about clinical guidelines, treatment recommendations, standard of care, evidence-based medicine, or drug-gene dosing recommendations.
setup-tooluniverse
mims-harvard
Install and configure ToolUniverse with MCP integration for any AI coding client (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, Antigravity, OpenCode, etc.). Covers uv/uvx setup, MCP configuration, API key walkthrough, skill installation, and upgrading. Use when setting up ToolUniverse, configuring MCP servers, troubleshooting installation issues, upgrading versions, or when user mentions installing ToolUniverse or setting up scientific tools.
tooluniverse-metabolomics-analysis
mims-harvard
Analyze metabolomics data including metabolite identification, quantification, pathway analysis, and metabolic flux. Processes LC-MS, GC-MS, NMR data from targeted and untargeted experiments. Performs normalization, statistical analysis, pathway enrichment, metabolite-enzyme integration, and biomarker discovery. Use when analyzing metabolomics datasets, identifying differential metabolites, studying metabolic pathways, integrating with transcriptomics/proteomics, discovering metabolic biomarkers, performing flux balance analysis, or characterizing metabolic phenotypes in disease, drug response, or physiological conditions.
tooluniverse-immunotherapy-response-prediction
mims-harvard
Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Given a cancer type, somatic mutations, and optional biomarkers (TMB, PD-L1, MSI status), performs systematic analysis across 11 phases covering TMB classification, neoantigen burden estimation, MSI/MMR assessment, PD-L1 evaluation, immune microenvironment profiling, mutation-based resistance/sensitivity prediction, clinical evidence retrieval, and multi-biomarker score integration. Generates a quantitative ICI Response Score (0-100), response likelihood tier, specific ICI drug recommendations with evidence, resistance risk factors, and a monitoring plan. Use when oncologists ask about immunotherapy eligibility, checkpoint inhibitor selection, or biomarker-guided ICI treatment decisions.
tooluniverse-cancer-variant-interpretation
mims-harvard
Provide comprehensive clinical interpretation of somatic mutations in cancer. Given a gene symbol + variant (e.g., EGFR L858R, BRAF V600E) and optional cancer type, performs multi-database analysis covering clinical evidence (CIViC), mutation prevalence (cBioPortal), therapeutic associations (OpenTargets, ChEMBL, FDA), resistance mechanisms, clinical trials, prognostic impact, and pathway context. Generates an evidence-graded markdown report with actionable recommendations for precision oncology. Use when oncologists, molecular tumor boards, or researchers ask about treatment options for specific cancer mutations, resistance mechanisms, or clinical trial matching.
higress-wasm-go-plugin
alibaba
Develop Higress WASM plugins using Go 1.24+. Use when creating, modifying, or debugging Higress gateway plugins for HTTP request/response processing, external service calls, Redis integration, or custom gateway logic.
apify-ecommerce
apify
Scrape e-commerce data for pricing intelligence, customer reviews, and seller discovery across Amazon, Walmart, eBay, IKEA, and 50+ marketplaces. Use when user asks to monitor prices, track competitors, analyze reviews, research products, or find sellers.
seo-coach
akseolabs-seo
Beginner-first SEO coaching for people who want to learn by doing one safe, verifiable step at a time. Use for SEO 陪跑、學 SEO、逐步檢查網站、看懂 Search Console／GA4、零付費工具的手動無痕 SERP、關鍵字與搜尋意圖、 內容差距、基礎網站架構、content brief、四篇 SEO 寫作實作、流量或排名問題教學， 以及 robots.txt、sitemap、title、canonical、Core Web Vitals 等概念與操作問題。 Do not use for a one-shot full-site audit report or health score, ghostwritten content delivery, PBN/site building, or paid-ad-only advice.
axolotl
davila7
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
evaluating-code-models
davila7
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
llamaindex
davila7
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
ray-data
davila7
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
deepspeed
davila7
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
model-pruning
davila7
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
moe-training
davila7
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
evaluating-llms-harness
davila7
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
immune
Mathews-Tom
'Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).'
prompt-lab
Mathews-Tom
'LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.'
manuscript-provenance
Mathews-Tom
'Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).'
mongodb-usage
fcakyon
This skill should be used when user asks to "query MongoDB", "show database collections", "get collection schema", "list MongoDB databases", "search records in MongoDB", or "check database indexes".
agent-browser
EveryInc
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".