Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use this skill when the user asks to publish, upload, sync, pull, push, diff, or maintain a MoviePilot local plugin in a GitHub repository. Covers using the configured MoviePilot GitHub token, PLUGIN_LOCAL_REPO_PATHS local plugin repositories, package.json/package.v2.json/package.v3.json metadata, plugins/plugins.v2/plugins.v3 layouts, safe file exclusion, diff preview before publishing, incremental GitHub Contents API updates, and syncing local plugin changes back from GitHub. Includes asking whether to use an existing repository or create a new public repository when no target repository is available. Also use for Chinese requests mentioning 插件发布, 插件维护, 推送插件到 GitHub, 从 GitHub 拉取插件, 同步本地插件仓库, 增量发布插件, 插件仓库维护.
Create, configure, and deploy PubNub Functions 2.0 event handlers, triggers, and serverless endpoints. Covers Before/After Publish, On Request, On Interval; built-in modules (kvstore, xhr, vault, pubnub, crypto, jwt, ugc, jsonpath, advanced_math, codec/*); chaining (depth caps, Chaining vs Forking, kvstore state sharing); runtime quirks (independent per-module execution budgets, cold start, request.path normalization, vault availability, sendFile message); DB-trigger patterns; and bundling/TypeScript workflow (esbuild externals, bundle size guard, __require shim stripping, default-export shape). Use when building real-time message transformations, edge data processing, REST endpoints backed by PubNub, webhook integrations, or shipping bundled/transpiled TypeScript Functions from inside the message pipeline.
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.
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.
Quiz the user on code changes, a spec, or an implementation plan to verify genuine understanding before committing, building, or approving. Especially valuable when working with AI-generated code or spec-driven development. Use when the user says "quiz me", "/quiz-me", "test my understanding", "quiz me before I commit", "quiz me on this spec", "quiz me on the plan", "make sure I understand this", or anything suggesting they want to verify comprehension of a diff, design doc, or architectural plan.
Use when investigating a bug, error, or regression in a Ruby on Rails codebase. Creates a failing RSpec reproduction test, isolates the broken code path, and produces a minimal fix plan. Trigger words: debug, broken, error, regression, stack trace, failing test, RSpec, bug report, Rails app.
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".
Sync the commits of the current development branch (usually dev) to the main branch via git rebase, push to the remote, then switch back to the original branch. Use this skill when the user mentions keywords such as "sync to main", "rebase to main", "update main", "push to the main branch", or "merge dev into main". Even if the user does not explicitly say rebase, trigger this skill whenever the intent is to sync the development branch's content to main.
Use when building ANYTHING - the universal reference-first system that routes every task to proven reference implementations instead of generating from assumptions. Covers API design, database schemas, testing strategies, CI/CD pipelines, code patterns, DevOps, and any other domain where professional reference implementations exist
Create or audit requirements-to-design-to-code-to-test traceability. Builds a traceability matrix (REQ → design/ADR → implementation files → tests → evidence) and flags gaps (unimplemented requirements, untested changes, undocumented decisions). Use when you need a requirements traceability check for a PR/release, regulated/compliance work, or when requirements are drifting from implementation.
Reads RHDH Jira and owns the mechanics every other RHDH Jira skill needs: `acli` flags and their traps, JQL for RHIDP, RHDHPLAN, RHDHBUGS and RHDHSUPP, custom field IDs, GraphQL and REST fallbacks, board and sprint IDs, the component catalog, and the workflow states with their exit criteria. Use to look up an issue such as RHIDP-1234, to write or debug a JQL query, to answer "which field is Story Points", "why is my search returning 30 rows", or "what does Release Pending require". Reading and query mechanics only — deciding what to file, judging readiness, or changing an issue belongs to the Jira skill that owns that verb.
This skill should be used when the user asks to "execute Lua code in Roblox Studio", "run code in Studio", "test Lua script", "connect to Studio Hub", "manage Studio instances", "check Studio status", "install Studio Hub", "setup Studio Hub service", or mentions Roblox Studio remote execution, Studio Hub API, or Lua code testing.
Use Rozenite for Agents through `@rozenite/agent-sdk` in Node.js or TypeScript code. Trigger this skill when Codex needs to write or run scripts, wrappers, automations, benchmarks, or agent runtimes that call Rozenite programmatically instead of driving the `rozenite agent` CLI directly.
Provides comprehensive guidance for Rspack bundler including configuration, plugins, loaders, optimization, and Webpack compatibility. Use when the user asks about Rspack, needs to configure Rspack, optimize build performance, or migrate from Webpack.
Move Rust game monsters, items, loot, effects, spawn weights, level gates, and balance numbers into validated data files using Serde-friendly schemas. Use when replacing hard-coded spawn functions, adding RON or JSON content templates, or making game content editable without recompiling.
Finish and package small Rust games with MVP lock, playability checks, resource packaging, release builds, smoke tests, and disciplined post-MVP polish. Use when preparing a Rust game prototype for sharing, packaging bracket-lib assets, or deciding what finishing work belongs before release.
Design and review Rust roguelike procedural maps, map-builder traits, generator harnesses, field-of-view, spatial memory, Dijkstra/pathfinding, and simple monster AI. Use when adding dungeon generation, FOV, map memory, chasing behavior, or visibility-constrained AI to a Rust game.
Design and review Rust tile maps, map indexing, collision checks, map builders, camera-relative rendering, layered drawing, and tile themes. Use when building 2D grid worlds, roguelike maps, tile cameras, or bracket-lib style rendering systems.
Build and review turn-based Rust game flow using turn-state enums, phase-specific schedules, intent messages, movement resolution, combat resolution, wait actions, and win/loss states. Use when implementing roguelike turns, tactical action order, ECS message entities, or decoupled input and action systems.
This skill should be used when users request code review, refactoring, or code quality improvements for Ruby codebases. Apply Sandi Metz's four rules for writing maintainable object-oriented code - classes under 100 lines, methods under 5 lines, no more than 4 parameters, and controllers instantiate only one object. Use when users mention "Sandi Metz", "code quality", "refactoring", or when reviewing Ruby code for maintainability.
SDD fast path. Runs the full pipeline — analyse → plan → implement → review → archive — with a single confirmation gate before implementation begins. Stops automatically if Critical or Major issues are found in review. Use when you want to ship a well-understood feature with minimal interruptions.
Write secure-by-default Node.js and TypeScript applications following security best practices. Use when: (1) Writing new Node.js/TypeScript code, (2) Creating API endpoints or middleware, (3) Handling user input or form data, (4) Implementing authentication or authorization, (5) Working with secrets or environment variables, (6) Setting up project configurations (tsconfig, eslint), (7) User mentions security concerns, (8) Reviewing code for vulnerabilities, (9) Working with file paths or child processes, (10) Setting up HTTP headers or CORS.
Configure the Serena MCP server — its global defaults and a repo's per-project settings. Use when the user says "configure serena", "set up serena for this repo", "serena project config", "serena global config", "tune serena for this codebase", "edit serena_config.yml", "edit project.yml", "monorepo serena", "serena picked the wrong language", "serena is indexing vendor/node_modules", "make serena read-only here", "serena contexts and modes", "what context for claude-code", "disable serena memory/onboarding", "point serena at my installed language server", "ls_specific_settings", "ls_path", "SERENA_HOME", or "move the .serena folder". Routes per-repo `.serena/project.yml` questions to `references/project-config.md` and machine-wide `~/.serena/serena_config.yml` (settings, contexts, modes, language-server tuning) to `references/global-config.md`. Do NOT use for general "use serena to find / edit X" routing — that is an MCP-routing concern, not configuration.
Apply Whispering service-boundary patterns for UI-free capabilities, explicit inputs, Result fallibility, Live objects, lifecycle factories, and platform variants. Use when creating or refactoring services, contracts, provider dispatch, or the `$lib/services` barrel.
Use when starting work in a terminal session—opening a project or directory, connecting to a session by name, cloning a repo to work in, or running a command or coding agent somewhere other than the current shell. Sesh resolves names and directories to sessions across tmux, zoxide, config, and tmuxinator. Use instead of `tmux new-session`, `tmux new-window`, `tmux attach`, or `tmux send-keys`.
Shopify platform development. Stack: Shopify CLI, GraphQL/REST APIs, Polaris UI, Liquid templating. Capabilities: app development (OAuth), checkout UI extensions, admin UI extensions, POS extensions, theme development, webhooks, billing API, product/order/customer management. Actions: build, extend, customize, integrate Shopify apps/themes. Keywords: Shopify, Shopify CLI, GraphQL Admin API, REST API, Polaris, Liquid, checkout extension, admin extension, POS extension, theme, webhook, billing API, OAuth, app bridge, metafields, product, order, customer, storefront, hydrogen, oxygen. Use when: building Shopify apps, customizing checkout, creating admin interfaces, developing themes, integrating payments, managing store data via APIs, extending Shopify functionality.
Sinch Functions, the beta serverless platform for voice, SMS and conversation apps. Use for platform questions: what it is, how deployment works, choosing Node.js or C#, install and auth, FunctionContext, handlers, the Voice v2 call lifecycle and `call.*` events, voice services and `VOICE_SERVICE_ID`, and SVAML. Runtime code lives in sinch-functions-node and sinch-functions-dotnet.
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.