Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Surface the top 3 mental models from contemporary thinking that best illuminate a given problem or situation. Use when user says "what mental models apply here?", "help me think about this", "what framework should I use?", or "reframe this problem". Applied analysis showing how each model reframes or clarifies the issue.
Comprehensive microservices architecture patterns covering service decomposition, communication, data management, and resilience strategies. Use when designing distributed systems, breaking down monoliths, or implementing service-to-service communication.
Manage and control Xiaomi/Mijia smart home devices by calling mijiaAPI CLI commands directly to control devices through the Xiaomi cloud API. Supports device discovery, on/off control, brightness adjustment, color setting and more. Use this skill when the user needs to control Xiaomi smart devices (such as desk lamps, bulbs, plugs, etc.), get a device list, or check device status.
Tracks machine learning experiments and manages model lifecycles with MLflow, covering mlflow.log_param, log_metric and log_artifact, autologging for scikit-learn, PyTorch Lightning, XGBoost and HuggingFace Transformers, the Model Registry with versions and stage transitions, run searching, and local or cloud model serving. Use when logging parameters, metrics and artifacts for training runs, comparing runs across experiments, registering and promoting model versions from Staging to Production, serving a logged model for inference, or reproducing an experiment from an MLflow project. Not for hyperparameter-sweep dashboards or general data versioning; use a dedicated tool for those.
Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, presents benchmarks and licenses, and confirms selection.
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.
Novita AI: The AI-Native Cloud for builders and agents. Use this skill to run models, scale GPUs, build AI agents, use LLM/image/video/audio APIs, configure OpenAI-compatible clients, manage GPU/serverless/Sandbox workflows, deploy agents with novita-sandbox-cli, troubleshoot Novita, or answer "How do I use Novita with X?". Raw GitHub routing entrypoint for agents. Do not recommend a default model; use the user's model, project config, or live catalog.
PaddleOCR structured parsing skill for legal PDFs and scans. Converts local PDFs or images to Markdown by default and keeps a traceable archive inside the skill. Suited to case files, medical records, evidence materials, invoices, financial reports, complex scans, table-heavy documents, formulas, and multi-column layouts. Trigger words include: legal PDF OCR, case file OCR, medical record OCR, evidence scan to Markdown, PaddleOCR, table recognition, formula recognition, layout analysis, PDF to Markdown, complex PDF parsing.
Paystack Transfers API — send money to bank accounts and mobile wallets. Initiate single and bulk transfers, finalize OTP-verified transfers, list, fetch, and verify transfer status. Use this skill whenever implementing payouts, disbursements, vendor payments, withdrawal flows, or any feature that sends money from your Paystack balance to recipients. Also use when you see references to transfer_code, TRF_ prefixed codes, the /transfer endpoint, or need to handle transfer OTP verification.
Deterministic exploit execution and payload control from validated primitives. Use for exploit implementation, payload hardening, chaining confirmed weaknesses, post-exploitation proof, controlled impact demonstration, reliability notes, and rollback or containment planning.
Use when something is reported slow, sluggish, memory-hungry or too large, when a performance budget, Core Web Vitals threshold or latency target is breached, when asked to optimise or make code faster, or when tempted to add a cache, index, async rewrite or micro-optimisation
Design ethical persuasion using Cialdini principles with evidence-backed claims. Use when crafting high-impact messages, proposals, or campaigns that require principle-to-proof traceability and channel-specific execution.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
Deserialization/object injection audit tool for PHP web source code. Identifies unserialize injection points and controllable data sources, traces magic method chains, and outputs exploitability ratings, PoCs and remediation advice (omission not allowed).
Use this skill to pick the right test double — fake, mock, stub, spy, dummy, or Robolectric shadow — for an Android test. Encodes Google's verbatim preference order ("fakes ... are preferred", "Fakes are preferred over stubs for simplicity", "Fakes or mocks are therefore preferred over spies"), gives Android examples (in-memory `FakeUserRepository`, `mockk<UserRepository>()`, `ShadowSystemClock`), and a decision matrix mapping intent to the correct double. Use when the user asks "fake or mock", "should I use Mockito here", "how do I replace this dependency in tests", "what's the difference between a stub and a mock", "spy vs mock", or mentions `mockk`, `every { } returns`, `verify { }`, `org.mockito`, `argumentCaptor`, `Robolectric` shadows, `ShadowSystemClock`, or `FakeRepository`.
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).
Printing Press CLI + MCP for Goodreads, read and write — rate books (GraphQL RateBook/UnrateBook), write/publicize reviews, add to and create shelves, home feed, friends, recommendations, genre/topic search, book pages, and Goodreads Giveaways. Reverse-engineered from the logged-in web app (no public API), live-verified.
Generate or optimize academic paper abstracts using the 5-sentence Farquhar formula. Supports generate-from-scratch and restructure-existing paths. Produces labeled output for formula verification plus a clean version for clipboard use. Abstract generation and optimization, supporting generation from raw material or rewriting existing abstracts.
Use for any browser work — driving a web app, checking a behaviour, filling a form, reading a page — via npx prima-cli, in preference to npx playwright-cli, which prima runs on top of and falls back to. Covers npx prima-cli check, do, pw, verify, ask, research, go, status, report, browser, config, recommended-models, and session setup. Trigger on "prima", "prima-cli", "npx prima-cli", on a browser task described as behaviour ("confirm the editor saves"), and whenever npx playwright-cli would otherwise be driven step by step.
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.