Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Institutional-quality equity research initiation reports for A-share companies. Covers company analysis, financial modeling, valuation, chart preparation, and final report assembly. Adapted from the original initiating-coverage skill for Chinese market conventions, CAS accounting, and AkShare data sources. Triggers on "A股首次覆盖", "首次评级", "initiate coverage China", "initiate on [company]", "A股研究报告", or "start research on [company]".
Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.
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
Dual skill for deploying scientific models. FastAPI provides a high-performance, asynchronous web framework for building APIs with automatic documentation. Streamlit enables rapid creation of interactive data applications and dashboards directly from Python scripts. Load when working with web APIs, model serving, REST endpoints, interactive dashboards, data visualization UIs, scientific app deployment, async web frameworks, Pydantic validation, uvicorn, or building production-ready scientific tools.
This skill should be used when the user asks to "validate FHIR resources", "check HL7 messages", "validate healthcare data format", "parse FHIR", "HL7 v2 messages", "FHIR R5 validation", "CDA documents", "healthcare data interchange", "FHIR resource schema", "HL7 specifications", or mentions FHIR validation, HL7 message parsing, CDA validation, healthcare data format compliance, or Fast Healthcare Interoperability Resources standards.
Gather business context from connected or provided sources so downstream analysis starts with the right framing. Use when an analytical question depends on missing context, such as what a metric means, what changed recently, or which sources should be checked. If the same prompt asks for diagnosis, recommendation, or a deliverable, gather context first and continue to the focused skill.
Score a stock's current valuation/trend health using the GF-DMA Health Index, combining fundamental growth speed, 20/50/100/200DMA trend speed, price-to-DMA divergence, ATR divergence, escape ratio, and estimate revisions. Use when the user provides a ticker or asks for GF-DMA scoring, valuation health, trend health, healthy momentum, overheated/escape risk, or whether a rising/falling stock is fundamentally supported.
Google Search Console API integration for search analytics, URL inspection, sitemap management, and site verification. Use when working with search performance data, checking indexing status, managing sitemaps, or analyzing SEO metrics.
When the user wants to know what queries drive traffic to their site, which pages are indexed, click-through rates, organic search performance, or technical indexing issues. Trigger on "Search Console," "GSC," "what keywords am I getting traffic for," "what queries," "impressions," "click-through rate," "indexing issues," "is my page indexed," or "organic performance."
Provides cryptocurrency trading data analytics including smart money tracking, whale monitoring, market data queries, and trader statistics. Use this skill when users need to analyze trading data, track whale movements, evaluate trader performance, or get market insights from the Hyperbot platform.
Guide for using Microsoft MarkItDown - a Python utility for converting files to Markdown. Use when converting PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs, Jupyter notebooks, RSS feeds, or Wikipedia pages to Markdown format. Also use for document processing pipelines, LLM preprocessing, or text extraction tasks.
Analyzes sensor configurations and creates inertial fusion filters in MATLAB Navigation Toolbox. Manages filter selection (imufilter, ahrsfilter, complementaryFilter, insfilterMARG, insfilterAsync, insfilterNonholonomic, insfilterErrorState, insEKF, insCF), construction, tuning, and fusion loops. Use when fusing IMU/AHRS/INS/GPS+IMU data, estimating orientation or pose, or choosing a filter. Do NOT use for vision-only SLAM, Simulink fusion, or IMU simulation.
Parse documents, extract structured content, and run OCR using the Mixedbread Parsing API. Use when parsing PDFs, Word documents, PowerPoint slides, or images, extracting tables or form fields, running OCR on scanned documents, converting documents to markdown or HTML, or extracting structured chunks with element-level bounding boxes and confidence scores.
Molecular docking pipeline using AutoDock Vina for structure-based drug discovery. Triggers on docking, AutoDock Vina, receptor preparation, ligand preparation, PDBQT, grid box, virtual screening, binding affinity, pose prediction, structure-based virtual screening, "redocking RMSD", "Vina score", "docking pose", "prepare receptor", "ligand library screening".
Pipeline skill for multi-omics data processing and integration. Use when the user asks to map gene IDs between HGNC Ensembl and UniProt, convert between omic data formats, run batch correction with ComBat or ComBat-seq, perform GSEA or over-representation analysis on multi-omic results, run consensus clustering on integrated data, execute MOFA2 in R or mofapy2 in Python, build a multi-omics ETL pipeline, harmonize feature identifiers across omics layers, or run clusterProfiler enrichment. Triggers include "map Ensembl to HGNC", "ID mapping omics", "ComBat code", "run MOFA2", "mofapy2", "GSEA Python", "fgsea R", "consensus clustering", "multi-omics pipeline", "gseapy", "biomaRt", "clusterProfiler", "mixOmics DIABLO".
Medical image segmentation with nnU-Net's self-configuring framework — auto-selects architecture, preprocessing, training for any modality. CT, MRI, microscopy, ultrasound in 2D, 3D full-res, 3D low-res, cascade. Pipeline: convert → plan/preprocess → train (5-fold CV) → best config → predict → ensemble. Use when classical segmentation fails and annotated data exists.
Computer vision for bio-image preprocessing, feature detection, real-time microscopy. Color conversion, morphology, contour/blob detection, template matching, optical flow on fluorescence/brightfield. 10-100× faster than pure Python via C++. Use scikit-image for scientific morphometry/regionprops; OpenCV for real-time, video, classical feature extraction.
When the user wants to build optimization models, solve mathematical programming problems, or find optimal solutions. Also use when the user mentions "linear programming," "integer programming," "mixed-integer programming," "constraint optimization," "mathematical optimization," "operations research," "optimal solution," or "decision optimization." For network design specifically, see network-design. For routing, see route-optimization.
Use when: you need to analyze user feedback and comments, assess user satisfaction, collect product improvement suggestions, or perform sentiment analysis. Do NOT use when: there is very little user feedback data, or only collection is needed without analysis
Use when: you need to analyze the user conversion funnel, diagnose churn causes, generate optimization suggestions, or improve user conversion rates. Do NOT use when: the user conversion path is already very clear, or only single-metric monitoring is needed without full-funnel analysis
Pipeline skill for computing HEDIS quality measures from claims and clinical data. Use when the user asks to calculate HEDIS measure rates, check continuous enrollment, build denominator/numerator logic, detect care gaps, compute utilization rates, identify high-cost claimants, or score risk stratification indices. Triggers include "calculate HEDIS", "measure rate", "continuous enrollment check", "care gap detection", "denominator query", "numerator logic", "utilization rate", "high-cost claimant", "Charlson score", "LACE score", "claims analysis", "quality measure SQL".
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Plan Fireworks post-training from a task-shaped goal — recommend a method, cookbook entry, data plan, and eval from what the user already said, ask only decision-critical questions, and hand off to configure when ready to train. Use when the user describes a problem in plain language, is unsure which method or dataset fits, needs public dataset ideas, or wants to explore before committing. Read-only — does not create jobs or upload data. For explicit train requests with known model and data, use configure; for failures use debug.
Implementation guide for Syncfusion Windows Forms Bullet Graph control for compact data visualization. Use this when working with bullet graphs, performance indicators, KPI visualization, comparative measures, or qualitative ranges in WinForms. This skill covers dashboard gauges, target vs actual comparisons, and performance range visualization in Windows Forms desktop applications.
Implementation guide for Syncfusion WinForms Maps control - a geographical data visualization component that displays statistical and regional data using shape files, bubbles, markers, and interactive features. Use this when working with WinForms Maps, geographical maps in Windows Forms, shape file visualization, choropleth maps, or bubble maps. This skill covers map layers, zooming/panning, geographical data binding, ESRI shape files, and building location-based desktop applications with interactive maps.
Implement Syncfusion Windows Forms Sparkline controls for compact data visualization. Use this when working with sparklines, trend displays in condensed format, or high-density data visualization. This skill covers line, column, and WinLoss chart types, data point markers, high/low value highlighting, and lightweight graphical representations in Windows Forms applications.
Investigate distributed traces and spans in OpenSearch. Use this skill when the user wants to analyze traces, investigate slow spans, find error spans, track agent invocations, measure token usage, reconstruct trace trees, query service maps, or debug distributed systems through trace data. Activate even if the user says traceId, spanId, OpenTelemetry, OTel, distributed tracing, latency, span duration, service map, or trace investigation without mentioning OpenSearch.
Germline and somatic short-variant calling pipeline for Illumina short-read data. Use when the user mentions BWA, BWA-MEM2, GATK, HaplotypeCaller, Mutect2, VCF, GVCF, VQSR, variant calling, germline, somatic, SNV, or indel calling from FASTQ/BAM.
Use when marketing numbers are bad and you need to know WHY — diagnose across 5 layers from tracking, delivery, creative, landing page to audience quality, then produce a 48h action plan. Trigger when the user mentions 'so dang xau', 'CPMess cao qua', 'ROAS thap', 'chan doan root cause', 'tai sao khong ra don', 'ads dot tien'. Not for — auditing the ad account setup and scoring Health Score, use skill 21-audit-ads-performance; writing a report for others to read, use skill 07-bao-cao-marketing; diagnosing a single page, use skill 68-cro-audit-trang.
Use when you have raw data from Meta, TikTok, GA4, CRM, or Google Sheets and need to turn it into insights you can decide on — with a decision log recording the decision, the basis, the expected impact, and the review date. Trigger when the user mentions 'phan tich du lieu', 'doc so lieu nay', 'export data ra insight', 'so nay noi len dieu gi', 'lam decision log', 'cohort analysis'. Not for — diagnosing why ads are performing badly, use skill 03-danh-gia-hieu-suat; writing a presentation report, use skill 07-bao-cao-marketing.
Diagnose and resolve ClickHouse grant and authentication errors, especially after upgrades. Use when queries fail with ACCESS_DENIED/NOT_ENOUGH_PRIVILEGES, AUTHENTICATION_FAILED/WRONG_PASSWORD/REQUIRED_PASSWORD, or ON CLUSTER privilege errors; when system.* or INFORMATION_SCHEMA access is denied; or when grant behavior changes after version upgrades.
Answers questions about what the Azure SQL Database container (Private Preview) can and cannot do, and WHY it differs from Azure SQL Database in the Microsoft Azure cloud. Use when a user asks "can I take a backup", "why does USE fail", "is X supported", "why can't I create a vector index", "why does SSMS error", "why isn't the image on Docker Hub", "what's different from the cloud", or hits behavior that does not match their Azure SQL Database expectations. Do NOT guess from general SQL Server / Azure knowledge: the container is a Private Preview product with specific gaps and a specific connection model. Read this skill, and link the user to the live Known limitations page for the current full list.
Scaffolds a NEW app (.NET Aspire, FastAPI, Next.js, NestJS) wired to the local Azure SQL Database container as its default dev database. Use when starting/bootstrapping/initializing a project that needs SQL Server or Azure SQL locally, or when adding "set up the database", "docker compose for the db", "create the local DB", ".env connection string", "first migration", or a data-access layer. Use this INSTEAD of the mssql/server SQL Server image, because this is the Azure SQL engine (EngineEdition 5). Triggers include "scaffold app with SQL", "spin up Azure SQL locally", "compose service for the database", "wire up Prisma/EF/SQLAlchemy/TypeORM to SQL Server". Reach for this even when the user only says "add a database" to a fresh project.
Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or clinical data; design a validation study; choose evaluation metrics; justify sample size; combine multi-omics signals; or assess clinical utility. Triggers include "discover a biomarker", "validate biomarker", "prognostic vs predictive", "feature selection", "LASSO vs elastic net", "nested cross-validation", "data leakage", "C-index", "time-dependent AUC", "decision curve analysis", "external validation cohort", "events per variable", "optimism-corrected", "multi-omics integration", "clinical utility of a biomarker", "is this biomarker ready".
Classifies a single piece of text (an AI-coding human input, optionally with its paired assistant reply and previous-assistant tail) into the current v2 human-input category + topic taxonomies, returning the primary category, the full priority-ordered categories array, one topic, topic_reason, and topic_confidence — a pure reasoning check against uid.core-product's classify rules (gpt-4o production prompt, postprocess off), no CawPlan data or API calls involved. Use when: asked to classify/categorize a specific sentence or human input against the current category and topic rules — e.g. "what category/topic is this: ...", "classify this with this assistant reply" — or as the per-row classification step used by cawplan-internal-qa-coding-humaninputs-test. NOT for: bulk/batch accuracy testing across many already-uploaded human inputs, or fetching data from CawPlan at all (use cawplan-internal-qa-coding-humaninputs-test for that), submitting reports, or creating tickets.
DL cell/nucleus segmentation for fluorescence and brightfield microscopy. Pre-trained models (cyto3, nuclei, tissuenet) and a generalist flow-based algorithm segment cells without retraining. Outputs label masks for morphology and tracking. Use scikit-image watershed for rule-based; Cellpose when DL generalization across staining is needed.
3D chart visualization with Swift Charts using Chart3D, SurfacePlot, interactive pose control, and surface styling — plus a 2D Swift Charts construction reference (marks, axes, selection, SectorMark, scrollable charts). Use when creating data visualizations with Swift Charts.
Cheminformatics pipeline for small-molecule property calculation, filtering, and similarity analysis using RDKit. Use when the user asks to compute molecular descriptors, filter compounds by Lipinski or Veber rules, detect PAINS, calculate fingerprint similarity, run matched molecular pair analysis, generate ADMET descriptors, or process SMILES. Triggers include "RDKit", "molecular descriptors", "Lipinski", "rule of five", "Veber", "PAINS", "pan-assay interference", "Morgan fingerprint", "Tanimoto", "fingerprint similarity", "matched molecular pair", "MMP", "mmpdb", "ADMET", "druglikeness", "SMILES", "cheminformatics", "compound filtering", "chemical similarity".
Pre-earnings analysis for A-share stocks. Builds scenario frameworks (actual vs consensus, beat/miss cases), identifies key metrics to watch, and prepares positioning notes before Chinese companies report quarterly results. Use instead of the original earnings-preview skill for A-share coverage. Triggers on "A股财报前瞻", "季报前瞻", "业绩前瞻", "earnings preview", "what to watch for [company] earnings", or "pre-earnings setup".
General ledger reconciliation for A-share companies. Adapts the original gl-recon skill for Chinese accounting standards, chart of accounts, and common reconciliation items. Triggers on "A股总账核对", "总账调节", "GL reconciliation China", "科目余额表", or "reconcile [company] accounts".
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.