Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Use when building Python AI agents with Pydantic AI, configuring model providers, implementing typed tools/dependencies, running evals, or integrating MCP servers. Keywords: pydantic-ai, agents, evals, MCP, Logfire.
Solves single- and multi-objective optimization problems in Python with pymoo, using NSGA-II, NSGA-III, MOEA/D, SPEA2, RVEA, GA, DE and PSO. Covers custom problems (Problem, ElementwiseProblem, FunctionalProblem), constraint handling, mixed-variable problems, ZDT/DTLZ/WFG benchmarks, genetic operators, parallel evaluation, Pareto front visualization and multi-criteria decision making. Use when finding Pareto-optimal trade-offs between conflicting objectives. Use when defining a constrained or mixed-variable problem and choosing an evolutionary algorithm. Use when benchmarking algorithms on standard test problems. Use when customizing crossover or mutation operators. Use when picking one solution from a Pareto front. Not for gradient-based or convex solvers.
Sets up static type checking for a Python package — choosing mypy, pyright, basedpyright or ty, strict configuration, per-module overrides, shipping py.typed — and fixes type-check errors. Use when the user says 'add type checking', 'set up mypy', 'pyright errors', 'make this package typed'. Not for lint or format failures, failing tests, runtime bugs, or the CI workflow that runs the checker.
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
Organizes PyTorch training code with the lightning package (PyTorch Lightning): LightningModule, LightningDataModule, Trainer, callbacks such as ModelCheckpoint and EarlyStopping, loggers (TensorBoard, W&B, MLflow, Comet, CSV), and multi-GPU/TPU strategies (DDP, FSDP, DeepSpeed). Use when structuring a PyTorch model into training, validation and test steps. Use when configuring a Trainer for multi-GPU or TPU runs. Use when writing a LightningDataModule for data loading. Use when adding checkpointing, early stopping or experiment logging to a training run. Use when choosing between DDP, FSDP and DeepSpeed for a model size. Not for plain PyTorch loops without Lightning.
Perform comprehensive code audits of Ruby on Rails applications based on thoughtbot best practices. Use this skill when the user requests a code audit, code review, quality assessment, or analysis of a Rails application. The skill analyzes the entire codebase focusing on testing practices (RSpec), security vulnerabilities, code design (skinny controllers, domain models, PORO with ActiveModel), Rails conventions, database optimization, and Ruby best practices. Outputs a detailed markdown audit report grouped by category (Testing, Security, Models, Controllers, Code Design, Views) with severity levels (Critical, High, Medium, Low) within each category.
Use when planning or reviewing production database migrations, adding columns, indexes, constraints, backfills, renames, table rewrites, or concurrent operations. Covers phased rollouts, lock behavior, rollback strategy, strong_migrations compliance, and deployment ordering for schema changes.
Use when writing new Rails code for a project using the PostgreSQL + Hotwire + Tailwind CSS stack. Covers stack-specific patterns only: MVC structure, ActiveRecord query conventions, Turbo Frames/Streams wiring, Stimulus controllers, and Tailwind component patterns. Not for general Rails design principles — this skill is scoped to what changes based on this specific technology stack.
Use when choosing the best first failing RSpec spec or vertical slice for a Ruby on Rails change. Covers request vs model vs service vs job vs engine spec selection, system spec escalation, smallest safe slice planning, and Rails-first TDD sequencing. Trigger words: where to start testing, what test to write first, RSpec, test-driven development, TDD, first failing test.
Build and maintain Raycast extensions using the Raycast API. Triggers on @raycast/api, List, Grid, Detail, Form, AI.ask, LocalStorage, Cache, showToast, and BrowserExtension. Use this repo's references/api/*.md files as the primary source of truth for component specs and API usage.
Unified handling of address space conversion: determining PIE/ASLR base addresses, RVA/VA conversion, loader offset (firmware load address vs link address), cross-tool address alignment (Ghidra/angr/frida/gdb). Triggers: PIE, ASLR, base address, RVA, VA, loader offset, address conversion, relocated address, computing addresses in gdb, angr addresses.
Write tests using React Native Testing Library (RNTL) v13 and v14 (`@testing-library/react-native`). Use when writing, reviewing, or fixing React Native component tests. Covers: render, screen, queries (getBy/getAllBy/queryBy/findBy), Jest matchers, userEvent, fireEvent, waitFor, and async patterns. Supports v13 (React 18, sync render) and v14 (React 19+, async render). Triggers on: test files for React Native components, RNTL imports, mentions of "testing library", "write tests", "component tests", or "RNTL".
Migrate Vuelidate form validation to Regle. Use when porting forms that import from `@vuelidate/core`/`@vuelidate/validators` or call `useVuelidate` over to `useRegle`/`useScopedRegle`, including rules, validation properties, `v-model` bindings, nested/scoped validation, and parent-child form propagation.
Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.
Review a GitCode pull request from a PR number or URL when `oh-gc` must fetch PR metadata, diff, and comments, local repository code must be inspected for context, and the output should be concrete findings or a GitCode submission draft. Use for GitCode PR review or comment-submission requests that depend on `oh-gc`. Do not use for generic local review, GitHub/GitLab flows, or automatic submission without explicit user confirmation.
Use when judging a produced open-source prior-art SEARCH, EXTRACT, or SYNTHESIS artifact — a keyword map (typed search vocabulary), a per-angle search output (coverage cells + candidate repositories), a per-repo extraction, or a synthesis report + borrow-index — to decide whether it is sound enough to feed the survey's downstream stages. An acceptance gate, not authoring: a twenty-two-condition bar single-sourced with the producer, covering the keyword map and search (1–11), proportionality (12), extraction due-diligence (13–18) and synthesis (19–22), delegating the deterministic schema checks to the producer's validator. Emits exactly one verdict — a terminal VERDICT: approve|revise line, or the caller's named equivalent — with condition-named findings. Review-only; no false-revise — a thin-but-honest result meets the bar. Keywords: prior art review, keyword map review, search coverage review, extraction review, synthesis review.
Use when building or auditing Roblox monetization — Developer Products (Robux purchases via ProcessReceipt), Gamepasses, gem/currency bundles, or anything touching real Robux. Covers the idempotency + rollback pattern that prevents "charged but got nothing" and money-duplication bugs, plus DevProduct/Gamepass setup.
Covers classical machine learning in Python with scikit-learn (sklearn): classification and regression estimators, clustering and dimensionality reduction, preprocessing, Pipeline and ColumnTransformer, cross-validation, metrics, and GridSearchCV hyperparameter tuning. Use when training or comparing classifiers and regressors on tabular or text data, clustering data and choosing the cluster count, building leakage-free preprocessing pipelines, evaluating models with cross-validation and metrics, or tuning hyperparameters. Not for deep learning; use a dedicated neural network framework instead.
Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform a fixed fair SGLang benchmark against the requested comparison framework set, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed requested framework under the same workload and SLA.
Manages shadcn-svelte components and projects — adding, updating, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn-svelte, the CLI, design-system presets, or any project with a components.json file. Also triggers for "shadcn-svelte init", "add component", or registry URLs.
Install and use shadcn/ui with Tailwind v4 and Next.js (App Router), Vite, or manual setup; configure components.json, add components via CLI, theming with CSS only. Use when adding shadcn/ui, installing shadcn, using Button, Card, Dialog, Form, or other shadcn components, or when the user mentions shadcn, shadcn/ui, or Radix UI with Tailwind.
Write Node.js/TypeScript Sinch Functions with `@sinch/functions-runtime`. Use when writing or editing `function.ts`: answering and controlling calls with Voice API v2, IVR menus, placing or bridging calls, SMS/WhatsApp/RCS webhooks, custom HTTP endpoints, cache/storage/database, auth and `setup()` hooks. Run and deploy with the sinch-cli skill.
Use when writing SpacetimeDB Rust clients, generated Rust bindings, connection code, subscriptions, cache access, reducer invocation, callbacks, or identity handling. Triggers on: Rust client, Rust SDK, generated Rust bindings, Rust subscription, Rust reducer call, Rust callbacks.
Comprehensive guidance for building web apps with opinionated defaults for tech stack, design system, and code standards. Use when user wants to create a new web application, dashboard, or interactive interface. Provides tech choices, styling guidance, project structure, and design philosophy to get users up and running quickly with a fully functional, beautiful web app.
Help set up and troubleshoot rendering for task files and glossary files. Use when the user asks about PlantUML, AsciiDoc, VS Code, Cursor, other VS Code-based IDEs, JetBrains, preview rendering, Java, or Graphviz needed to review rendered task or glossary files.
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
Manage subscriptions with PayKit's unified subscribe API, handle upgrades, downgrades, cancellations, resumptions, checkout flows, payment URLs, and subscription status transitions. Use when users need to implement subscription flows or understand PayKit's subscribe semantics.
Contributing to the Twenty codebase itself (twentyhq/twenty server internals), not for building apps on top of Twenty. Implement action handlers for executing workspace migrations in Twenty. Use when creating database operations for syncable entities, implementing universal-to-flat entity transpilation, or handling create/update/delete actions in the runner layer.
Comprehensive guide for implementing Syncfusion ASP.NET Core Calendar components including Calendar, DatePicker, DateRangePicker, DateTimePicker, and TimePicker. Use this skill ALWAYS and immediately when the user asks about any Syncfusion ASP.NET Core calendar, date picker, date range picker, time picker, datetime picker, calendar views, multi-selection, Islamic calendar, date range restriction, week numbers, day cell customization, renderDayCell, date selection, range selection, date formatting, date masking, globalization, localization, strict mode, accessibility, or any related calendar/date/time UI in ASP.NET Core tag helper applications.
Implements Syncfusion Flutter Slider controls (SfSlider, SfRangeSlider, SfRangeSelector) for numeric value selection and range inputs. Use when working with single-value sliders, range selection, or chart-range controllers in Flutter apps. This skill covers thumb and tooltip customization, ticks, dividers, RTL support, drag modes, and chart integrations.
Learn how to implement and configure the Syncfusion TypeScript AppBar control for navigation bars, app headers, and UI toolbars. This skill covers responsive positioning, color modes, sizing, styling, and component integration. Use when building navigation solutions that require flexible layout and styling options.
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.