Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Manages microscopy image data on an OMERO server via the OMERO Python API (BlitzGateway) — access images, retrieve datasets, read pixel data, manage ROIs and annotations, and batch-process. Use when connecting to an OMERO server, pulling microscopy images or datasets, analyzing pixels, managing ROIs/annotations, or running high-content screening and microscopy workflows. Part of the AlterLab Academic Skills suite.
Query the Open Targets Platform GraphQL API for target-disease associations, tractability and safety data, genetics/omics evidence, and known drugs. Use when identifying or prioritizing therapeutic drug targets, assessing target druggability/safety, or gathering target-disease evidence for drug discovery. Part of the AlterLab Academic Skills suite.
Access the RCSB Protein Data Bank (PDB) for EXPERIMENTALLY determined 3D structures (X-ray, cryo-EM, NMR) of proteins and nucleic acids — searching by text, sequence, or structure similarity and downloading coordinates in PDB/mmCIF format with metadata. Use when retrieving a structure by PDB ID, running sequence or structure similarity searches, or obtaining experimental coordinates for structural biology and drug discovery; for AI-PREDICTED structures of proteins lacking experimental data prefer alterlab-alphafold-db, and for protein sequences, annotations, or accession ID mapping prefer alterlab-uniprot instead. Part of the AlterLab Academic Skills suite.
Fast in-memory DataFrame analytics with Polars — lazy evaluation, parallel execution, and an Apache Arrow backend for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory, for 1-100GB datasets, ETL pipelines, or a faster pandas replacement. For larger-than-RAM data prefer dask or vaex. Part of the AlterLab Academic Skills suite.
Queries the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biomedical relationships across genes, drugs, diseases, phenotypes, pathways, and biological processes. Use when exploring drug-disease or gene-disease links, building disease-centric knowledge subgraphs, or sourcing relations for drug repurposing and precision-medicine analyses; also points to OptimusKG, the maintainers' successor graph, for new work. Part of the AlterLab Academic Skills suite.
Query PubChem via the PUG-REST API and PubChemPy across 119M+ compounds, searching by name, CID, or SMILES and retrieving molecular properties, bioactivity, and similarity/substructure matches. Use when looking up a chemical compound, converting names/SMILES to CIDs, fetching physicochemical properties, or running cheminformatics structure searches. Part of the AlterLab Academic Skills suite.
Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom PufferEnv tasks, or integrating game environments (Atari, Procgen, NetHack, PettingZoo). For standard single-agent algorithm implementations (PPO/SAC/DQN) or quick prototyping prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.
Reads, writes, and manipulates DICOM (Digital Imaging and Communications in Medicine) medical imaging files with the pydicom Python library. Use when reading/writing/modifying DICOM data, extracting pixel data from CT, MRI, X-ray, or ultrasound images, anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM to other formats, handling compressed DICOM, or processing medical imaging datasets for PACS systems, radiology workflows, and healthcare imaging applications. Part of the AlterLab Academic Skills suite.
Develops, tests, and validates clinical machine learning models with the PyHealth 2.x healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, length of stay, drug recommendation), medical coding systems (ICD, NDC, ATC, CCS), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare (RETAIN, SafeDrug, GAMENet, Transformer, GAT/GCN). Part of the AlterLab Academic Skills suite.
Multi-objective optimization with pymoo — NSGA-II, NSGA-III, MOEA/D, Pareto-front computation, constraint handling, and standard benchmarks (ZDT, DTLZ). Use when solving multi-objective or constrained optimization problems, computing Pareto-optimal trade-offs, or tackling engineering design problems with competing objectives. Part of the AlterLab Academic Skills suite.
Loads Therapeutics Data Commons (TDC, PyTDC) AI-ready drug-discovery datasets and benchmarks — ADME, toxicity, drug-target interaction (DTI), scaffold splits, and molecular oracles for therapeutic ML and pharmacological prediction. Use when fetching a standardized benchmark dataset, applying scaffold or cold-split evaluation, or sourcing labeled molecules for ADMET, toxicity, or DTI modeling. Sources data, splits, and oracles only — defer molecular featurization (ECFP/fingerprints), model training, and transformers to alterlab-deepchem or alterlab-molfeat. Part of the AlterLab Academic Skills suite.
Scalable deep-learning training with PyTorch Lightning — organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, build data pipelines and callbacks, log to W&B or TensorBoard, and run distributed training (DDP, FSDP, DeepSpeed). Use when structuring PyTorch training loops, scaling neural-network training across GPUs/TPUs, or adding checkpointing, logging, and distributed strategies. Part of the AlterLab Academic Skills suite.
Query the Reactome REST API for pathway analysis, over-representation/enrichment, gene-to-pathway mapping, disease pathways, molecular interactions, and expression analysis. Use when running pathway enrichment on a gene list, mapping genes to curated biological pathways, or exploring disease pathways for systems biology studies. Part of the AlterLab Academic Skills suite.
Classical machine learning in Python with scikit-learn — algorithms, preprocessing, pipelines, and best-practice reference documentation. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, feature preprocessing, or building ML pipelines. Part of the AlterLab Academic Skills suite.
Process-based discrete-event simulation in Python with SimPy — processes, queues, shared resources, and time-based events. Use when simulating systems where entities contend for shared resources over time, such as manufacturing systems, service operations, network traffic, or logistics. Part of the AlterLab Academic Skills suite.
Work with ArcGIS Knowledge graphs for storing, querying, and visualizing connected data using KnowledgeGraphLayer, LinkChartView, and openCypher queries. Use for graph databases, relationship visualization, and entity exploration.
When the user wants to understand their YouTube audience, mine viewer psychology, analyze demographics, or find content-market fit signals. Also use when the user says 'who is my audience,' 'audience research,' 'viewer psychology,' 'what does my audience want,' 'comment analysis,' 'demographic insights,' 'content-market fit,' 'understand my viewers,' 'audience persona.' For channel-level health check, see channel-audit. For generating ideas from audience insights, see idea-generation.
Guides users through bioinformatics analysis on AWS HealthOmics. Covers analysis type selection (alignment, variant calling, QC, interpretation), workflow generation in Nextflow or WDL, container sourcing from public registries, infrastructure setup (S3, ECR, IAM), workflow registration, parameter preparation, execution, and monitoring. Use when a user wants to run any bioinformatics pipeline on HealthOmics, set up genomics infrastructure on AWS, create a new analysis workflow, or run existing tools like BWA, GATK, DeepVariant, FastQC, or similar on HealthOmics. Triggers include "HealthOmics", "bioinformatics", "genomics pipeline", "Nextflow", "WDL", "BWA", "GATK", "DeepVariant", "FastQC", "variant calling", "alignment", "RNA-seq", "whole genome sequencing", "ECR pull-through", "workflow registration", "run cache"
BKN full-lifecycle orchestration entry point. Reads OpenBKN SDK / CLI operation references on demand. Whenever the task involves creating a BKN, extracting object relations from a PRD/document, generating or updating `.bkn`, data view binding, environment checks, test set generation, validation, or pushing, use bkn-creator first for workflow routing, stage gates, sub-skill orchestration, and result receipts. Applies to BKN create/read/update/delete/extract/copy/validate scenarios, skill package capability gap-filling / skill draft generation scenarios, and usage feedback inspection and improvement scenarios (scheduled task triggers, Agent conversation quality anomalies, feedback_brief input, continuous knowledge network optimization). Not for pure data semantic queries, which should be handled by data-semantic.
MANDATORY — invoke this skill BEFORE making any Blockscout MCP tool calls or writing any blockchain data scripts, even when the Blockscout MCP server is already configured. Provides architectural rules, execution-strategy decisions, MCP REST API conventions for scripts, endpoint reference files, response transformation requirements, and output conventions that are not available from MCP tool descriptions alone. Use when the user asks about on-chain data, blockchain analysis, wallet balances, token transfers, contract interactions, on-chain metrics, wants to use the Blockscout API, or needs to build software that retrieves blockchain data via Blockscout. Covers all EVM chains.
Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring. Automatically invoke when the user mentions "BPA rule", "Best Practice Analyzer", or asks to "create a BPA rule", "audit BPA rules", "recommend BPA rules", "set up BPA for my team", "check model for best practices", "validate BPA rules", "improve a BPA expression".
Pull human-input logs from CawPlan (by product, user/member, date range, count, or session), preprocess prev/assistant context like production classify, and open a local web editor to annotate expected category/topic labels for prompt eval fixtures. Use when: building or extending a labeled human-input sample JSON for classify prompt testing — e.g. "pull 20 turns from spx's Slack session last week and label them", "sample human inputs for core-product". NOT for: running classify accuracy against cloud labels (use cawplan-internal-qa-coding-humaninputs-test), classifying a single sentence (use cawplan-internal-qa-coding-humaninputs), or submitting coding reports.
Scrape, crawl, map, search, parse, and extract web data with fastCRW — the open-source, self-hostable Firecrawl alternative (single Rust binary, ~14 MB RAM, Firecrawl-compatible /v1 + /v2 API). Use whenever the user needs page content, site-wide extraction, URL discovery, web search, PDF parsing, structured JSON from pages, or change tracking. Also use when the user mentions Firecrawl, Tavily, Crawl4AI, or "scrape/crawl/map/fetch/get the page/read this site/search the web" — crw is a drop-in for the Firecrawl SDKs.
End-to-end R data analysis pipeline — exploration → cleaning → regression → publication-ready tables and figures. Use when user says "analyze this dataset", "run a regression on X", "explore this CSV", "full analysis workflow", "get me summary stats and a regression", or points at a `.csv`/`.rds`/`.dta` and asks for empirical results. Produces numbered R scripts in `scripts/R/` and outputs to `output/`.
Use when designing databases for data-heavy applications, making schema decisions for performance, choosing between normalization and denormalization, selecting storage/indexing strategies, planning for scale, or evaluating OLTP vs OLAP trade-offs. Also use when encountering N+1 queries, ORM issues, or concurrency problems.
Designs embedding strategies that combine semantic (text-based) and structural (graph-based) information at node, edge, path, and subgraph levels for knowledge graphs. Use when selecting embedding granularity, choosing complementary semantic and structural approaches, designing fusion strategies (concatenation, attention, contrastive alignment), or when user mentions node embeddings, embedding fusion, vector representations for graphs, or combining text and graph signals.
Analyze user conversion funnels, calculate step-by-step conversion rates, create interactive visualizations, and identify optimization opportunities. Use when working with multi-step user journey data, conversion analysis, or when user mentions funnels, conversion rates, or user flow analysis.
Analyze user conversion funnels, calculate step-by-step conversion rates, create interactive visualizations, and identify optimization opportunities. Use when working with multi-step user journey data, conversion analysis, or when user mentions funnels, conversion rates, or user flow analysis.
Immediate trigger conditions: the user mentions "building a website with HAP", "HAP front-end project", "HAP as a database", "corporate website", "official website", "building via HAP", "making a website with HAP", "HAP website", "building an official website", "front-end/back-end separation", "content management system", "HAP front end", "HAP official website". Provides a complete guide to building a HAP + front-end project, including HAP back-office configuration, front-end project structure, API integration, and data rendering.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new node in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when ingesting a new entity through CIQ - no relationship creation, no updates to existing nodes, no deletes.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new relationship between two existing nodes in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when wiring two existing entities together through CIQ - no new nodes, no relationship updates, no deletes.
Review dead letter queue implementations for completeness using the Lenses MCP server. Checks DLQ topic existence, configuration, monitoring, metadata preservation, retry logic, reprocessing paths and connector DLQ alignment. Use when user says "review dead letter queues", "check DLQ setup", "DLQ audit" or asks about error handling, message failures or reprocessing. Do NOT use for reprocessing DLQ messages or managing consumer offsets.
Run raw ClickHouse SQL against KubeSense logs and traces via execute-sql / validate-sql — the queryable column set, the $__timeFilter/$__clusters macros, @attr access, and the joins, CTEs and window functions the analyze-* tools cannot express.
Best practices for Kuroco API design and content management. Covers endpoint design, authentication (Cookie, dynamic token, static access token), CORS, rate limiting, caching, error handling (401/403/429), content CRUD via the Topics API (list / details / insert / update / delete / bulk_upsert), filter queries, pagination, multilingual support (langs_open_flg), extended fields (ext_col), file upload and CSV import, and EC points (ECPoint). Use for implementing API calls, login API and token authentication, resolving authentication and permission errors, and questions about fetching, creating, updating, deleting, and filtering content.
Use this skill when the user says 「填入数据」「补数据」「同步数据」「更新统计表」「数据填一下」「同步」. The core action is **batch syncing**: scan `01-内容生产/待发布的内容/中短视频/`, and for every video with complete YAML data, write it into the data statistics table in one go and archive it to `02-已发布内容/`. The data source is the YAML in the script file itself (the user has already filled in the platform data there), so the user does not need to report the numbers again in the conversation. Should not trigger: analyzing patterns / retrospectives / viral-hit analysis (use li-analyzer), or logging new topics (use li-recorder). Use when the user wants to "sync platform data" or "fill in stats" — the skill scans the pending folder and processes every video whose YAML is complete.
Product analytics instrumentation and strategy covering event taxonomy design, tracking plans, user behavior analysis, activation/retention metrics, and marketing attribution. PostHog-first with multi-platform support (Pendo, Amplitude, Mixpanel, Heap).
Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.