Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
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.
Deploy a free VLESS proxy/VPN node on Cloudflare Pages using edgetunnel. Automates code download, UUID generation, Pages deployment, free domain registration (DNSExit), DNS configuration, custom domain binding, and client setup for Shadowrocket/v2rayN/Clash. Uses Cloudflare Pages (not Workers) because Pages supports CNAME-based custom domains from any DNS provider, avoiding the need to host DNS on Cloudflare.
Discounted cash flow (DCF) valuation model for A-share equities. This alias skill redirects to china-dcf, which provides comprehensive DCF modeling adapted for Chinese market conventions. Triggers on "A股DCF模型", "DCF估值", "DCF model China", "现金流折现", "discounted cash flow A-share", or "DCF [company]".
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".
Chinese KYC (Know Your Customer) and AML (Anti-Money Laundering) rules for financial services. Adapts the original kyc-rules skill for Chinese regulatory requirements and domestic compliance. Triggers on "A股KYC规则", "中国反洗钱", "AML rules China", "KYC compliance China", "反洗钱规定", or "KYC requirements".
Net asset value (NAV) reconciliation and tie-out for Chinese funds and investment portfolios. Adapts the original nav-tieout skill for A-share holdings, Chinese fund accounting standards, and domestic custody arrangements. Triggers on "A股净值核对", "NAV计算", "NAV tie-out China", "基金净值", "net asset value [fund]", or "portfolio valuation [date]".
Entry point for frontend design. Use WHENEVER building or touching the look of any web UI — components, pages, dashboards, landing pages, React/Vue/HTML-CSS — and whenever the user says "make this look better/nicer", "fix the spacing/layout", or mentions styling, color, typography, fonts, responsive design, polish, or aesthetics, even without the word "design". Load design-thinking for direction; design-system for implementation; design-spatial for layout; design-philosophy for visual philosophy or art-direction.
Write idiomatic application code with the ClickHouse Node.js client (`@clickhouse/client`). Use this skill whenever a user is *building* against the Node.js client — configuring the client, pinging, inserting rows in JSON or raw formats, selecting and parsing results, binding query parameters, managing sessions and temporary tables, working with data types or customizing JSON parsing. Do NOT use for browser/Web client code.
Interview coaching system. Activates for any coaching command: prep, round, sync, strategy, stories, mock, outreach, thankyou, analyze, progress, practice, research, decode, fit, apply, feedback, reflect, salary, negotiate, hype, pitch, resume, linkedin, present.
Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, .NET, Java, C, C++, Rust, Ruby, PHP, and Dart/Flutter. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, and generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, or generating review checklists
Manage custom business configuration in an Adobe Commerce app. Use when the user wants to add, modify, or remove merchant-configurable settings (config fields, admin config, store configuration) exposed through Commerce Admin. Creates typed config fields (text, password, email, url, tel, boolean, list) in businessConfig.schema. Requires a base app initialized with commerce-app-init.
Use confluence-cli (NPM package) to manage Confluence content, pages, and spaces from the command line. Ideal for documentation workflows, bulk content operations, page migration, and when users request CLI-based Confluence interactions. Trigger on requests like "use Confluence CLI", "create Confluence pages via CLI", "migrate Confluence content", "automate documentation workflows", or when users want to script Confluence operations.
Anthropic's method for training harmless AI through self-improvement. Two-phase approach: supervised learning with self-critique and revision, then RLAIF (RL from AI Feedback). Use for safety alignment and reducing harmful outputs without human labels. Powers Claude's safety system
Use this skill to drive the Compose test clock by hand with MainTestClock — currentTime, autoAdvance, advanceTimeByFrame, advanceTimeBy(milliseconds, ignoreFrameDuration), and advanceTimeUntil. Explains the 16 ms frame delay used by TestMonotonicFrameClock, the per-frame ordering where withFrameNanos awaiters resume before recomposition, and how the recomposer and MainTestClock share one TestCoroutineScheduler. Covers v1 versus v2 entry-point dispatcher differences (UnconfinedTestDispatcher vs StandardTestDispatcher) and when an explicit runCurrent or advanceTimeBy(0) is required after migration. If the user mentions MainTestClock, mainClock.advanceTimeBy, mainClock.advanceTimeByFrame, mainClock.advanceTimeUntil, ComposeTimeoutException, frame delay, TestCoroutineScheduler, "test clock vs wall clock", or "v2 createComposeRule queues tasks", use this skill.
When organizing project structure, establishing patterns, or reducing configuration overhead. Use when the user says "how should I organize this," "what's the convention," "too much config," "project structure," "naming pattern," or "standardize this." For code-level structure, see separation-of-concerns.
Build, refactor, debug, or review a Convex backend inside a Next.js app. Use when the user mentions Convex, `convex/nextjs`, `npx convex dev`, `NEXT_PUBLIC_CONVEX_URL`, `useQuery`, `useMutation`, `usePaginatedQuery`, schema/indexes, auth, App Router server components/actions, realtime data, chat, notifications, collaborative features, or deploying Convex with Vercel. Also use when deciding whether Convex is a good fit for a Next.js app that needs reactive shared state. Do not use for generic frontend-only Next.js work or non-Convex backends unless the task is specifically about adopting, migrating to, or evaluating Convex.
Builds and debugs notifications with Courier. Load it first whenever a task involves Courier or its API, SDKs, CLI or MCP, before searching the docs: it holds the rules and traps the docs search won't surface. Covers sends on email, SMS, push, inbox, Slack, Teams or WhatsApp; templates, journeys, digests, preferences, providers, webhooks, tenants
Designing anatomically plausible, visually distinctive creatures that communicate threat, personality, and role through form - from terrifying bosses to collectible companionsUse when "creature design, design a creature, design a monster, monster design, boss design, enemy creature, companion creature, pet design, wildlife design, alien creature, fantasy creature, horror monster, cute creature, pokemon style, creature anatomy, creature silhouette, creature movement, hybrid animal, ecosystem creatures, creature family, mount design, dragon design, beast design, creature, monster, boss, enemy, companion, wildlife, horror, cute, pokemon, anatomy, silhouette, locomotion, ecosystem, hybrid, fantasy, sci-fi, kaiju, cryptid" mentioned.
Search CUDA-X library documentation (cuBLAS, cuTENSOR, cuTensorNet, cuSOLVER, etc.) to find API symbols, functions, and types. Use when you need to look up CUDA library APIs, discover available functions, or find documentation URLs for specific operations.
Database Lookup provides unified programmatic access to 78+ scientific and public databases spanning chemistry (PubChem, ChEMBL), biology (UniProt, COSMIC, Ensembl), clinical (ClinicalTrials.gov, FDA), economics (FRED, World Bank), and intellectual property (USPTO, EPO).
Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a small pointer instead of real data; when an analysis needs a machine-readable record of how each output was produced so it can be re-executed; or when publishing a dataset to siblings such as a GitHub repository plus a storage remote. Also use to decide between DataLad and plain Git for a data-carrying repository.
Use when the user wants to design a new domain model from scratch — phrases like "help me model X", "what's the bounded context for Y", "design a domain for this feature", "we need a domain model". Walks the user through ubiquitous language, bounded context, aggregate identification, and then routes to the relevant pattern skills. Do NOT use for code generation (route to ddd-implement) or refactoring existing code (route to ddd-refactor).
Use when modeling significant domain occurrences — phrases like "domain event", "OrderPlaced", "PaymentSettled", "something the business cares happened", "decouple these two aggregates", "eventual consistency across aggregates". Defines domain events, their naming (past tense, business-meaningful), and how they coordinate work across aggregates without violating aggregate boundaries
Use when the user is modeling something whose identity matters beyond its attributes — phrases like “entity”, “this thing has an ID”, “two of these are the same if their IDs match”, “tracked over time”, “lifecycle”. Distinguishes entities from value objects by identity continuity. Pairs with ddd-value-object (the opposite distinction).
Provides comprehensive guidance for event-driven architecture including domain events, event sourcing, CQRS, and event patterns. Use when the user asks about event-driven architecture, needs to implement event-driven systems, or work with domain events.
Use when establishing or auditing a domain's shared vocabulary—phrases like “ubiquitous language”, “what should we call this concept”, “the team uses different words for the same thing”, “the code uses different names than the business”. Defines what a ubiquitous language is, how to grow one, and the smell tests that reveal a missing one. Do NOT use for code generation; this is a process/language skill.
Deep research with hyperresearch, for Claude Code and OpenAI Codex. Use when the user asks for deep research, a research report, a literature review, or a multi-source analysis with verified citations. Checks that the hyperresearch CLI is installed, sets it up in the current project for the agent you are running in, then hands off to the hyperresearch pipeline (a tier-adaptive 16-step pipeline with a persistent source vault). Not for quick lookups one or two searches can answer.
Covers DeepSpeed for distributed deep learning training and I/O: ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8 training, 1-bit Adam, sparse attention, and DeepNVMe (aio_handle, gds_handle, async_io and gds operators, ds_nvme_tune, ds_report) for fast transfers between NVMe storage and host or GPU tensors. Use when configuring ZeRO stages for large-model training, enabling mixed precision or 1-bit Adam, offloading parameters or optimizer state to NVMe with ZeRO-Infinity, writing or reading tensors to files with blocking or non-blocking DeepNVMe calls, or tuning NVMe I/O settings such as block size, queue depth and parallelism. Not for plain PyTorch DistributedDataParallel without DeepSpeed.
Guidance for Microsoft Defender for Cloud Apps (MDA) — the CASB for SaaS discovery, app governance, session controls, and threat detection. Covers Cloud Discovery via Defender for Endpoint integration, OAuth app governance, Conditional Access App Control (reverse-proxy session policies), and SaaS security posture (SSPM). WHEN: Defender for Cloud Apps, MDA, CASB, shadow IT discovery, cloud app governance, OAuth app risk, session control, Conditional Access App Control, SaaS security posture management, SSPM, sanction or unsanction app, Cloud App Catalog, app connectors. DO NOT USE for IaaS / PaaS posture (use defender-for-cloud-hardening), endpoint EDR (use defender-for-endpoint), or DLP (use purview-dlp-policy).
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.