Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
When writing reports in Feishu Docs, create, edit, and deliver chart-assistant editable chart cards. Covers 30+ built-in chart types, including columns/bars (stacked, grouped, percentage, and overlapping comparisons), line, area, scatter/bubble, dual-axis, pie/doughnut, rose, radar, funnel, word cloud, Sankey, heatmap, Treemap/Sunburst, as well as business charts such as waterfall/bridge, Mekko, bullet, dumbbell, butterfly, and small-multiple panels. Chart types, annotations, and editing capabilities are broadly aligned with ThinkCell. By default, follows MBB (McKinsey/BCG/Bain) consulting-style charting standards and provides report-grade analytical annotations such as variance annotations (total variance, hierarchical variance, compound growth rate), trendlines, reference lines/regions, and highlight coloring. Supports connecting Feishu Sheet/Base/Fengshen data sources and keeping them in sync, recreating charts from reference images, creating Feishu Docx files, and inserting/replacing chart-assistant cards in existing documents; it can also explain and validate chart-assistant configurations. Use when the user explicitly mentions Chart Assistant, editable charts or configurations, built-in Chart Assistant templates, Chart Assistant cards, data-source sync, turning Fengshen or Feishu Sheet/Base links into editable charts, or requests MBB/consulting-style charts or recreation from reference images, even if they don't name the skill. Do not take over ordinary requests like "make this a chart" or "draw a trend chart" unless they require the product capabilities above; if the user only wants a text explanation and no chart, don't trigger the chart-creation flow.
Convert local chat exports that ChatLab does not yet support into verified ChatLab JSONL or JSON: analyze the source file structure, write and run a local Node.js or Python conversion script, and verify the record count before importing. Use when ChatLab cannot recognize chat exports such as CSV, HTML, TXT, XML, SQLite/databases, vendor-specific JSON/JSONL, or archives, or when the user asks an Agent to adapt an unknown chat format.
ClawShire annual report data query skill — queries structured extraction results from annual reports of companies listed on the Beijing Stock Exchange, supporting retrieval by securities code and year for standard fields such as revenue, profit, dividends, and strategic highlights
Complete knowledge domain for Cloudflare Workers KV - global, low-latency key-value storage on Cloudflare's edge network. Use when: creating KV namespaces, storing configuration data, caching API responses, managing user preferences, implementing TTL expiration, handling KV metadata, or encountering "KV_ERROR", "429 too many requests", "kv rate limit", cacheTtl errors, or eventual consistency issues. Keywords: kv storage, cloudflare kv, workers kv, kv namespace, kv bindings, kv cache, kv ttl, kv metadata, kv list, kv pagination, cache optimization, edge caching, KV_ERROR, 429 too many requests, kv rate limit, eventually consistent, wrangler kv, kv operations, key value storage
Queries Crawlora's pre-built hosted datasets — Airbnb markets, App Store/Google Play apps, GitHub/Instagram/X users, job postings, US housing markets, Google Maps businesses, Goodreads, PitchBook, Steam, TrustMRR, Product Hunt, SEC companies, tech-stack, and more — via search/facets/item/nearby endpoints, returning clean JSON without live-crawling each platform. Use when the user wants bulk or aggregate analysis, to search a pre-indexed corpus, to facet/filter a large population, or to look up one record by its dataset id, instead of scraping pages one at a time.
Run queries against a Cube deployment's semantic layer and interpret the results — through the Cube MCP tools when they are connected, or the Cube CLI from a terminal. Use whenever someone wants numbers out of Cube — pull a metric, check a total, compare periods, verify that a measure returns what it should, sanity-check a model change. Triggers on "how many", "what's the total", "show me revenue by month", "did that measure work", "what's our MoM growth", "pull the numbers for", and any request to verify a model change against real data. To find out what is queryable first use cube-explore-model; to change the model use cube-build-model; to save a result as a report or dashboard use cube-build-content.
Create interactive data visualizations using d3.js. Use this skill when creating custom charts, graphs, network diagrams, geographic visualizations, or any complex SVG-based data visualization that requires fine-grained control over visual elements, transitions, or interactions. Use it for bespoke visualizations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
End-to-end data analysis assistant. Covers data processing, insight generation, report writing, and data visualization workflows. Always approaches tasks from an expert perspective — thinks one step ahead of the user. Proactively asks for clarification when intent is ambiguous. Supports: Excel/CSV analysis, business metrics review, ROI calculation, data visualization, HTML report generation, and formula writing. Activate when user mentions: "analyze data", "make a report", "visualize", "Excel", "dashboard", "ROI", "weekly report", "monthly report", "data processing", "chart", "insight", "presentation", "table", "formula", "KPI", "metrics".
Enrich contact and company data using x402-protected APIs. Superior to generic web search for structured business data. USE FOR: - Enriching person profiles by email, LinkedIn URL, or name - Enriching companies by domain - Finding contact details (email, phone) with confidence scores - Scraping full LinkedIn profiles (experience, education, skills) - Searching for people or companies by criteria - Bulk enrichment operations (up to 10 at a time) TRIGGERS: - "enrich", "lookup", "find info about", "research" - "who is [person]", "company profile for", "tell me about" - "find contact for", "get LinkedIn for", "get email for" - "employee at", "works at", "company details" ALWAYS use x402.fetch for enrichx402.com endpoints - never curl or WebFetch. Returns structured JSON data, not web page HTML. IMPORTANT: Never guess endpoint paths. All paths follow the pattern https://enrichx402.com/api/{provider}/{action}. Use exact URLs from the Quick Reference table below or call x402.discover_api_endpoints first.
Profile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, discovering column distributions, identifying nulls and outliers, or deciding which dimensions to analyze.
Design and audit data governance, data classification, access controls, least privilege, approval workflows, owner review, retention, deletion, audit logs, data catalog, sensitive fields, analytics access, support/admin access, AI dataset access, and break-glass paths. Use when teams need product data access without privacy, security, or compliance drift.
Write a safe, zero-downtime database migration plan for a schema change. Use when asked to plan a database migration, design a zero-downtime schema change, document an expand/contract migration, produce a rollback procedure for a database change, or coordinate a database schema update with a deployment. Produces a structured migration plan covering migration objectives, backward compatibility analysis, expand/contract phase breakdown, exact SQL, rollback steps per phase, data validation queries, and a deployment runbook.
Use when developing BigQuery Dataform transformations, SQLX files, source declarations, or troubleshooting pipelines - enforces TDD workflow (tests first), ALWAYS use ${ref()} never hardcoded table paths, comprehensive columns:{} documentation, safety practices (--schema-suffix dev, --dry-run), proper ref() syntax, .sqlx for new declarations, no schema config in operations/tests, and architecture patterns that prevent technical debt under time pressure
Use when writing or reviewing Python code in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection. Same endpoint as plain STT but with analytics params. Covers both REST (`client.listen.v1.media.transcribe_url`/`transcribe_file`) and the WSS-supported subset (`client.listen.v1.connect`). Use `deepgram-python-speech-to-text` for plain transcription, `deepgram-python-text-intelligence` for analytics on already-transcribed text. Triggers include "diarize", "summarize audio", "sentiment from audio", "redact PII", "topic detection audio", "audio intelligence", "detect language audio".
Architecture guide for GDPR-compliant federated learning systems. Covers horizontal and vertical FL, aggregation strategies (FedAvg, FedProx), communication efficiency, secure aggregation, and differential privacy integration. Includes privacy guarantees analysis and deployment patterns for cross-organizational ML without data sharing.
Data analysis dashboard (instrument panel) development skill. Use when users need to develop data dashboards, create/edit Dashboard projects, build large-screen data boards, or perform dashboard data cleaning. Includes dashboard project creation, card plan, data cleaning (data_cleaning.py), card management tools (create_dashboard_cards, update_dashboard_cards, delete_dashboard_cards, query_dashboard_cards), map download tool (download_dashboard_maps), dashboard development, and validation.
Deploy differential privacy in production systems including epsilon selection strategies, noise calibration with Laplace and Gaussian mechanisms, privacy budget tracking, composition theorems, and Python implementation patterns. Covers both central and local differential privacy models.
Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Use for DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation.
Use when the user wants two approaches raced head-to-head on a single shared metric — e.g. a classical/algorithmic lane vs an ML/learned lane, or any two strategies for the same task. Each lane runs its own analysis-first research loop confined to its lane, the lanes share a scoreboard and may borrow ideas across the boundary without abandoning their identity, and a shared eval keeps the head-to-head honest; loops until interrupted, reporting the current leader. Not for improving a single approach in isolation (use a single-track research loop), and not for picking between two finished artifacts in one shot (that is a one-time comparison).
End-to-end guide for adding a new synced feature with Electric and TanStack DB. Covers the full journey: design Postgres schema, set REPLICA IDENTITY FULL, define shape, create proxy route, set up TanStack DB collection with electricCollectionOptions, implement optimistic mutations with txid handshake (pg_current_xact_id, awaitTxId), and build live queries with useLiveQuery. Also covers migration from old ElectricSQL (electrify/db pattern does not exist), current API patterns (table as query param not path, handle not shape_id). Load when building a new feature from scratch.
Analyze budget vs actual variances in Excel with drill-down and root cause analysis. Use when performing variance analysis or explaining budget differences. Trigger with phrases like 'excel variance', 'analyze budget variance', 'actual vs budget'.
Help the user design a well-formed GrowthBook experiment before it's launched. Use when the user asks to "design an A/B test", "set up an experiment", "test X vs Y", "configure an experiment", or "what should we measure". Produces a complete spec — hypothesis, variations, primary metric, guardrails, sample size — ready to hand off. Does not create the experiment in GrowthBook. For launching, use experiment-launch. For ideas grounded in past results, use experiment-brainstorm first.
Designs, prioritizes, executes, and reviews growth experiments using the ICEEE framework, structured hypothesis formation, A/B testing methodology, and statistical significance validation. Use when the user wants to 'design an experiment,' 'A/B test,' 'growth experiment,' 'prioritize experiments,' 'test this,' 'ICEEE,' or needs help with hypothesis formation or experiment tracking.
Design and audit experimentation platform governance for A/B tests, holdouts, feature tests, pricing experiments, lifecycle campaigns, marketplace ranking tests, game economy tests, AI experiments, exposure allocation, metrics, guardrails, conflicts, ethics, rollout, and decision review. Use when experiments should create reliable product learning without harming users or corrupting decisions.
Help researchers identify and catalog relevant datasets for empirical research. Use this skill whenever a user asks to find data, locate datasets, identify data sources, or asks "what data exists for...", "where can I get data on...", "is there a dataset that...", or similar. Also trigger when the user describes a research question and needs to know what data could support it, asks about data availability for a particular topic or geography, wants to compare data sources, or mentions needing panel data, cross-sectional data, or time-series data for a project. Trigger on mentions of "find data", "data search", "dataset", "data source", "microdata", "administrative data", "survey data", "public-use data", "restricted data", or when the user specifies parameters like time windows, geographic levels, or data frequency in the context of research. Also trigger when the user asks for help downloading, scraping, or structuring a dataset that has been identified.
GATK Best Practices for germline SNP/indel calling from WGS/WES BAMs. Per-sample HaplotypeCaller GVCFs, GenomicsDBImport, GenotypeGVCFs joint calling, VQSR or hard filters. Requires BWA-MEM2-aligned, markdup, BQSR BAMs. Use DeepVariant for a faster DL alternative; GATK is the NIH/ENCODE standard.
This skill is designed to help users automatically extract reviews from Google Maps via the Google Maps Reviews API. Agent should proactively apply this skill when users request to find reviews for local businesses (e.g., coffee shops, clinics), monitor customer feedback for a specific brand or location, analyze sentiment of reviews for competitors, extract reviews for a chain of stores or services, track reputation of a local restaurant, gather user testimonials for a specific venue, conduct market research on service quality of local businesses, monitor reviews for a new retail location, collect feedback on public attractions or parks, identify common complaints for a specific service provider, research the best-rated places in a city, analyze recurring themes in reviews for a specific industry.
Extracts tiles and preprocesses H&E whole slide images with the histolab Python library (OpenSlide), covering slide inspection, tissue masks (TissueMask, BiggestTissueBoxMask), RandomTiler, GridTiler and ScoreTiler extraction, image and morphological filters, and Macenko or Reinhard stain normalization. Use when building a tile dataset from WSI files for deep learning. Use when detecting tissue and excluding background or pen annotations. Use when previewing tile locations and exporting tile CSV reports. Use when normalizing stain variation across slides. Not for spatial proteomics, multiplexed imaging, or deep learning pipelines; use pathml for those.
Report this session's output tokens and CO₂ by running the repo's committed EcoLogits port, plus the modelled CO₂/$ saved vs a no-Honey baseline — always labelled with the bench stamp it came from. Use when asked how much Honey saved, the session's carbon/token footprint, or to expand the 🍯 statusline badge into a full breakdown.
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
Access high-quality A-share investment data, based on the investment_data project. Supports end-of-day prices, limit-up/limit-down data, index data and more. Updated daily with cross-validation across multiple data sources. Trigger words: stock data, A-share data, financial data, quantitative data, historical quotes.
Use when the user asks to create or edit Online graph charts or data visualizations, or says "创建图表", "生成图表", "新建图表", "做一个图表", "online图表", "数据图表", "柱状图", "折线图", "饼图", "统计图", "可视化", "chart", "graph", "create chart", "generate chart", "bar chart", "line chart", "pie chart". Also triggers when the user describes chart requirements such as "做一个销售柱状图" or mentions data visualization such as "用图表展示男女比例".
JeecgBoot system master data query and management. Use when the user asks to query/create/manage system master data, or says "查询角色", "查询用户", "查询部门", "查询字典", "创建字典", "创建角色", "查岗位", "查职务", "查租户", "查数据源", "查定时任务", "系统主数据", "query roles", "query users", "query depts", "create dict", "create role", "master data". Also triggers when other skills (desform, bpmn, codegen) need to look up or create roles, users, departments, dictionaries, or positions as dependencies — follows the "先查后建" (query-first-create-later) principle.
Light 科研主线 stage 6: turn the frozen question/estimand, experiment matrix, pre-registration, and data lineage into minimal runnable, test-first, leakage-free, reproducible experiment code that can be handed off to result-analysis. Use to implement or reproduce training/preprocessing/evaluation; design gold/property/metamorphic tests; control Python/NumPy/framework/CUDA/DataLoader randomness; review train/test or CV fit leakage; record config/code/environment/input hashes, stdout/stderr, raw metrics, patient/entity predictions, and failure artifacts; and run the stage-6 checkpoint. Data leakage or irreproducibility is critical; static scanning and two runs with the same seed do not prove absolute reproducibility across hardware.
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or get distribution stats.
ALWAYS use when: creating/editing marimo notebooks, working with any .py file containing @app.cell decorators, building reactive Python notebooks, doing exploratory data analysis in notebook form, converting Jupyter (.ipynb) to marimo, or when user mentions "marimo", "reactive notebook", or asks for an interactive Python notebook. Covers marimo CLI (edit, run, convert, export), UI components (mo.ui.*), layout functions, SQL integration, caching, state management, and wigglystuff widgets. If a task involves notebooks and Python, invoke this skill first.
PostgreSQL development for Python with full-text search (tsvector, tsquery, BM25 via pg_search), vector similarity (pgvector with HNSW/IVFFlat), JSONB and array indexing, and production deployment. Use when creating search features, storing AI embeddings, querying vector similarity, optimizing PostgreSQL indexes, or deploying to AWS RDS/Aurora, GCP Cloud SQL/AlloyDB, or Azure. Covers psycopg2, psycopg3, asyncpg, SQLAlchemy integration, Docker development setup, and index selection strategies. Triggers are Use "PostgreSQL search", "pgvector", "BM25 postgres", "JSONB index", "psycopg", "asyncpg", "PostgreSQL Docker", "AlloyDB vector". Does NOT cover - DBA administration (backup, replication, users), MySQL/MongoDB/Redis, schema design theory, stored procedures.
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.