Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
French State open data platform (data.gouv.fr) — search catalog, dataset metadata, organizations, download files, query tabular CSV rows (Tabular API), usage metrics (Metrics API), discover external APIs (dataservices). Use for consumption, analysis, or MCP-assisted exploration. Optional producer coaching (documentation/quality before publication on the platform).
DeepKnow knowledge and retrieval assistant — manage and import knowledge; search internal materials, professional literature, food standards, and policies on controlled official websites; read summaries and full text as needed; and query real data from 食品伙伴网 and tables.
TikTok Shop e-commerce data assistant. Search products, find trending items, analyze influencers, explore shops, track video performance, and get ad insights via ecomseer.com. Triggers: 找商品, 搜商品, 爆品, 带货, TikTok电商, 达人分析, 视频带货, 店铺分析, 广告素材, 销量榜, 跨境电商, search products, find trending, TikTok Shop, influencer analysis, shop data, ad creatives, sales ranking, e-commerce analytics, product research.
Configure ShapeStream and Shape to sync a Postgres table to the client. Covers ShapeStreamOptions (url, table, where, columns, replica, offset, handle), custom type parsers (timestamptz, jsonb, int8), column mappers (snakeCamelMapper, createColumnMapper), onError retry semantics, backoff options, log modes (full, changes_only), requestSnapshot, fetchSnapshot, subscribe/unsubscribe, and Shape materialized view. Load when setting up sync, configuring shapes, parsing types, or handling sync errors.
Operate Feishu Bitable, supporting management of data tables, records, fields, and assets. When to use: when the user says "飞书多维表格"/"飞书表格"/"bitable", or needs to read and write table records, manipulate data table structure, manage fields, or upload assets.
Compose polished charts (timeseries, bar, line, area, pie, scatter, or anything else the data calls for) from tabular data using the chartkit primitives, producing PNG, SVG, or self-contained interactive HTML. Use when the user asks to chart, graph, plot, or visualize data and wants something better than raw matplotlib defaults.
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
Use when building Jigx apps that integrate with Acumatica ERP, including probing an instance, using SOAP/UI probes to understand screens, choosing between generic inquiries and contract REST for mobile, reading a screen's built-in logic and reconciling it with the customer's instance, selector and cascade rules, on-demand and delta reads, custom endpoint creation, REST and OData functions, Acumatica config values, acuerp access tokens, .value payload wrappers, lookup sync, expand selection, local-first sync, command queue retry, file uploads, PDF attachment, and service order submission.
Multi-step KEGG bioinformatics workflows — pathway enrichment from gene lists, drug-target investigation, cross-species metabolic comparison, and compound-reaction network exploration. Guides Claude through the full analytical pipeline using KEGG MCP tools.
Compile documents, notes, web content, transcripts, research materials, or code repositories into an evidence-grounded, visualization-ready knowledge graph with semantically typed entity nodes, statement-level provenance, and typed relationship edges. Use with ov compile to create or incrementally refresh `entities/*.md` node artifacts and a root `relations.jsonl` edge file for people, organizations, groups, animals, places, products, projects, systems, services, modules, datasets, standards, documents, events, and other identifiable things.
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
Use when working with AdonisJS Lucid ORM and SQL layer: database configuration, migrations, schema generation, schema classes, models, CRUD operations, model query builder, query scopes, hooks, serialization, relationships, transactions, pagination, debugging, validation rules, model factories, seeders, or database query builders. Trigger for tasks involving @adonisjs/lucid, database/schema.ts, app/models, database/migrations, database/factories, database/seeders, db service queries, Lucid relationships, or model behavior.
When the user wants to optimize markdown strategy, price optimization for clearance, or minimize inventory markdowns. Also use when the user mentions "markdown," "clearance pricing," "price elasticity," "promotional pricing," "discount optimization," "sell-through," "inventory liquidation," or "dynamic pricing." For initial allocation, see retail-allocation. For promotional planning, see promotional-planning.
Find and query PI assets using MATLAB's Industrial Communication Toolbox. Two paths: (1) direct PI tag lookup via piclient + tags when user provides a tag name or description (R2022a+), (2) Asset Framework navigation via afclient when user needs element/attribute hierarchy (R2026a+). Use when working with PI AF servers, PI Data Archive tags, asset hierarchies, element templates, attribute lookup, or historical data from OSIsoft PI systems.
When the user wants to apply machine learning to supply chain problems, build ML models, or use AI for predictions. Also use when the user mentions "machine learning," "deep learning," "neural networks," "AI supply chain," "predictive models," "classification models," "regression models," "anomaly detection," "computer vision," or "NLP for supply chain." For traditional forecasting, see demand-forecasting. For optimization, see optimization-modeling.
Patterns for ingesting data into NetBox using the Diode SDK (Python and Go). Use when building network discovery, bulk import, or automated data population integrations that write data to NetBox via gRPC. Covers SDK setup, entity construction, batch ingestion, chunking, reconciler behavior, error handling, and when to use Diode vs the REST API.
Methodology for migrating data into NetBox from spreadsheets, legacy IPAM/DCIM systems, CMDBs, and unstructured sources. Use when planning or executing a data migration — covers assessment, cleaning, dependency ordering, import strategy selection, validation, and post-migration verification with Discovery and Assurance.
When the user wants to combine machine learning with optimization, use ML predictions in optimization models, or integrate AI with mathematical programming. Also use when the user mentions "ML-optimization hybrid," "predict-then-optimize," "learning-augmented optimization," "neural network in optimization," "end-to-end learning," or "ML for optimization parameters." For pure optimization, see optimization-modeling. For pure ML, see ml-supply-chain.
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.
DB schema extraction skill. Extracts the current database state into per-table DDL files and saves them in the schema/ folder. Triggered by keywords such as "extract schema", "update schema", "extract-schema", "sync DB schema", "refresh schema files", "inspect DB structure", "extract DDL", "update schema". Use this skill when the schema files may differ from the actual database state.
Full lifecycle management skill for dbmate migrations. Handles status checks, up, down, and creating new migrations. Triggered by keywords such as "run migration", "DB up", "DB down", "migration status", "create migration", "dbmate", "migration", "apply table changes", "apply schema", "DB rollback". Use this skill for any request related to DB migrations.
Full workflow skill for Mermaid ERD. One-stop handling from installing MCP → generating mmd → browser preview → saving PNG/SVG. Triggered by keywords such as "update ERD", "preview ERD", "save ERD", "draw an ERD", "add table", "change relationship", "visualize DB design", "add column to ERD", "edit erd.mmd". Use this skill when the intent is to visualize a DB schema or table structure.
Etsy niche research whose scores come with their evidence attached — seeded search, honest confidence, and a local store that turns repeat research into trends. Trigger phrases: `research the dad shirt niche on Etsy`, `is this Etsy niche low competition`, `find low-competition Etsy sub-niches under dad`, `what tags do winning Etsy listings use for this niche`, `size up the competitors in this Etsy niche`, `use everbee`, `run everbee`.
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Turn a bibliography or literature corpus into a knowledge graph of papers, authors, venues, topics and citation links, then analyze it (citation clusters, key papers, bridging work, research gaps) or export it to Neo4j, Gephi, NetworkX, Obsidian or Markdown-graph tools such as graphify. Use when mapping a research field, building a citation network, finding influential or bridging papers, or visualizing how a literature connects. Zero-dependency builder with optional OpenAlex enrichment.
Analyses sprint delivery data and produces a structured retrospective brief. Use when asked to run a retrospective, analyse sprint data, prepare a retro brief, or turn sprint metrics into discussion prompts. Produces a data-grounded retrospective brief with completion stats, pattern analysis, Start/Stop/Continue prompts, and one concrete experiment for next sprint.
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.