Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Create and maintain a simple task progress memo in docs/tasks/task-description.md by default, or in an explicit task directory supplied by the user or another active skill. Use when the user wants a plan, TODO steps, acceptance criteria, checkbox syncing, status updates, or progress tracking that stays in sync while the agent works. Treat git commits as required recovery checkpoints: each meaningful change must be committed and the commit id must be written into the matching step note.
Prefers `fd` (https://github.com/sharkdp/fd) over `find` for filesystem searches in shell snippets. `fd` is faster on large trees, has saner defaults (respects `.gitignore`, smart case, regex by default), and a more ergonomic CLI. Falls back to `find` when `fd` is not available on the host.
Guides creation and modification of domain feature systems organized under a systems/ directory. Covers directory layout, API service layer patterns, TanStack Query hooks (queries, mutations, optimistic updates), React context and XState store conventions, hook organization, and public API barrel exports. Use when adding a new domain system, extending an existing one, or fixing bugs in a system-layer codebase. Don't use for generic React component work, backend API implementation, or codebases not organized around a systems/ domain pattern.
Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Implement approved, production-quality Flutter interfaces with adaptive layout, complete states, project-native architecture, accessibility, and proportionate verification. Use when visual direction and behavior are sufficiently defined and the user asks to build, change, polish, or refactor Flutter UI code.
Use this skill as the frontend entrypoint for the Svelte 5 app in ClientApp — adding routes, creating feature slices, writing Svelte components, applying TypeScript conventions, using shared UI/formatter components, handling accessibility, or adding frontend tests. The legacy Angular app still powers most of the current site in ClientApp.angular, but all new frontend development should be Svelte UI only unless the user explicitly asks for Angular or legacy UI changes.
World-class frontend engineering - React philosophy, performance, accessibility, and production-grade interfacesUse when "frontend, react, vue, svelte, next.js, nuxt, component, state management, redux, zustand, client side, spa, ssr, hydration, bundle size, web vitals, accessibility, a11y, responsive, css, tailwind, frontend, react, typescript, performance, accessibility, components, state, architecture" mentioned.
Comprehensive game MVP interviewer and planner. Interviews you in progressive groups, researches genre conventions and reference games, then produces an actionable MVP First Draft with starter project files. Use when starting a new game project from scratch.
Numerically balances engine-agnostic weapons, units, encounters, progression, loot, difficulty, and economies using measurable targets, spreadsheets, curves, probability, simulation, telemetry, and playtests. Use for tuning values and distributions; defer mechanic ideation to game-mechanics-design and cross-system structure to game-systems-design.
Consolidated game developer for story execution, code implementation, code review, QA/test authorship, and sprint orchestration. Use when the user asks to talk to Link Freeman, the Game Developer, the Game QA, or the Game Scrum Master.
Diagnose and fix the problem of a Git repository not seeing all remote branches, restoring a restricted fetch refspec to a wildcard pattern so git fetch can pull all remote branches. Use this skill when the user mentions keywords such as "can't see remote branches", "branches are incomplete", "only master/main", "fetch all branches", "complete branches for a shallow clone", "--single-branch fix", "remote branches missing", or "get all branches". Even if the user does not explicitly mention refspec or a shallow clone, trigger this skill whenever the intent is to let the repository see and pull all remote branches.
Software development engine for coding. A production-grade skills system for web apps and mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline and specialist skills to help generate secure, scalable, maintainable, high-performance software systems
Generates commit messages following the gitmoji convention (https://gitmoji.dev) — picks the right emoji for the intent of the change and writes a well-formed message. Use when asked to "write a gitmoji commit", "add an emoji to my commit message", "which gitmoji should I use", "gitmoji this change", or when a project uses gitmoji-style commit messages. Works from a git diff, staged changes, or a plain description of the change. Generates the message only — does not run git commands.
Frontend visual replication skill. Explores a target website’s publicly visible pages via Playwright MCP or agent-browser, captures screenshots and layout information, then generates a static or client-side frontend replica that approximates the original’s visual appearance and page structure. This skill replicates FRONTEND PRESENTATION ONLY — it does not reproduce backend logic, server-side behavior, databases, or any non-public content. The user is responsible for ensuring they have proper authorization (ownership, license, or explicit permission) before replicating any website. Authorization gate: Before starting, the agent MUST confirm with the user that they have the legal right to replicate the target site. If the user cannot confirm, the skill MUST refuse to proceed.
Adapt fragment shaders or runtime-shader snippets into standard GLSL, render them with glslViewer in headless mode, and inspect PNG output for shader debugging. Use when Codex needs to validate SDFs, gradients, masks, edge contours, or intermediate shader math by producing reproducible preview images from `.frag` files or translated shader snippets.
Build document Q&A and searchable knowledge bases with Google Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats (PDF, Word, Excel, code), configure semantic search, and query with natural language. Use when: building document Q&A systems, creating searchable knowledge bases, implementing semantic search without managing embeddings, indexing large document collections (100+ formats), or troubleshooting document immutability errors (delete+re-upload required), storage quota issues (3x input size for embeddings), chunking configuration (500 tokens/chunk recommended), metadata limits (20 key-value pairs max), indexing cost surprises ($0.15/1M tokens one-time), operation polling timeouts (wait for done: true), force delete errors, or model compatibility (Gemini 2.5 Pro/Flash only).
Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, asks for a design interview, or uses trigger phrases such as "grill me", "grill this", "stress test this plan", "poke holes", or "challenge this design".
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.