Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
codeck entry point. Scans local files for materials, shows pipeline dashboard with diagnostic intelligence, guides user to the next step. Use when the user says "codeck", "new deck", "make a presentation", "make a deck", "new slides", "build a presentation", "export", "speech", "script", or wants to start or continue a presentation project. /codeck is the user-facing entry; legacy sub-skills are internal modules.
Concise communication mode. Cuts ~60-70% of output tokens while keeping natural, readable English. Drops filler, hedging, and pleasantries but maintains grammar and sentence flow. Elaborate on request -- ask for detail and get it, then auto-return to concise. Use when user says "concise mode", "be concise", "less verbose", or invokes /concise. Also triggers when user requests token efficiency with readability.
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored instructions, hallucinations, tool misuse) — "what's failing in my agent", "surface error patterns", "why are the responses bad", "find the common failure modes", "what should I fix next". Covers scoping to one use case, finding failing traces by whichever signal fits the context (code errors, metric outliers, trace-type slices, manual review, existing-eval spikes, clustering), and reading them into a ranked failure taxonomy.
Set up or modernize code-quality tooling for JavaScript and TypeScript projects. Use when creating a project, adding code-health or CI quality checks, making a repository agent-ready, or consolidating dead-code, duplication, architecture, dependency, and changed-code analysis. Do not use for formatting-only, lint-rule-only, or TypeScript type-error tasks. Do not use to run an analysis of a project that is already set up; use the fallow skill for that.
Guides creation of a W3C-compliant token system via an interview, generates a structured ZIP of JSON token files organized by collection tier (Primitives, Theme, Semantic, Component), and relies on a separate Figma plugin that imports them in dependency order.
The repo front-door for a Flutter/Dart app — the cross-cutting house rules (feature-first layered MVVM, immutable state with a single write path, Riverpod 3.x for state + DI, typed Result/Failure errors, dumb widgets, injected side effects, complexity limits) plus a routing table that sends each task to its deep-dive skill and a recommended feature build order. Use at the start of any Flutter/Dart work, before writing or reviewing a feature, when deciding which layer or package code belongs in, when unsure which skill governs a task (architecture, state, widgets, persistence, testing, i18n, design), or when onboarding to the conventions.
Rewrite website content to maximize AI citability — remove hedge language, add data support, improve self-containment, and optimize structure for AI engines. Use when the user asks to improve content for AI, fix citability, rewrite for AI, remove hedge words, or make content more citable.
Correct usage of context.Context in Go: propagation, cancellation, timeouts, deadlines, values, and common anti-patterns. Use when: "context usage", "context.Context", "context cancellation", "timeout", "context.WithTimeout", "context.WithCancel", "context values", "context propagation". Not for: concurrency beyond context (go-concurrency-review), HTTP middleware (go-api-design), or error handling (go-error-handling).
Agent-callable Google Contacts tools — create, find, update, and delete contacts, manage contact groups (labels) and membership, and read auto-saved other contacts. Use when the user mentions Google Contacts or wants to look up, save, or organize people — including requests that don't name Google Contacts explicitly, e.g. add Jane to my contacts, find Bob's email.
Turn a product, a feature or an idea into a finished one-minute explainer video in any look: a script (hook, benefit, quick tutorial, try it), a voice whose words are the clock, HTML scenes drawn from that one clock and rendered frame by frame at 2×, and an edit in Fil's video editor over MCP with captions, music, sound effects and chapters. The look is an input, read from the person's site or a named style, so the same film can wear any type, colour, corners and motion. The shape is an input (4:3, 16:9, 1:1, 9:16). No camera by default: a voice-led film whose scenes fill the frame; ask for a camera and it adds record slots, layouts by keyframes and a teleprompter. Use when someone wants an explainer, a feature video, a product walkthrough, an onboarding video, a how-it-works video or a launch video, wants one in their own brand, or wants it without filming anything.
Guides porting existing Android 2D apps to Meta VR and Horizon OS, including input adaptation, panel layout, and design requirements. Use when adapting a mobile Android app for Meta VR. For UI design decisions, use hz-panel-designer if available. Build path: Standard Android; use hz-quest-verify-first if the build path is unclear.
Master fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluation methods. Use when adapting models for specialized applications, reducing inference costs, or improving domain-specific performance.
Enforces an on-device reminder engine where the local database is the only source of truth and the OS pending-notification set is a disposable cache reconciled through one idempotent syncNotifications() entrypoint; keeps flutter_local_notifications behind a single NotificationGateway port, all scheduling math pure and Clock-injected, recurring schedules stored as wall-clock + recurrence rule (never UTC instants) and resolved to a TZDateTime in tz.local for DST correctness, inexact-alarm default with SCHEDULE_EXACT_ALARM as an opt-in, iOS ~64-cap budgeting, isolate-safe @pragma('vm:entry-point') tap handlers, and Android boot re-arm. Use when writing or editing notification_gateway.dart, fln_notification_gateway.dart, reminder_scheduler.dart, recurrence_rule.dart, syncNotifications, zonedSchedule wiring, snooze or mark-done re-anchoring, or diagnosing missed or wrong-hour notifications.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Build complete product scenes using PolyHaven assets — HDRI environment, textured ground/pedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model.
Qiaomu skill and workflow for downloading a WeChat Channels / 视频号 video or generated live replay when the user provides a weixin.qq.com/sph share link. Use when asked to download, save, parse, or extract a 视频号 video/replay. Prefer no-install public link resolution, then use a verified, on-demand local wx_channels_download backend only when required. Protect the user's login state, root certificate, system proxy, existing VPN/proxy, and downloaded files; restore network settings on every exit path
Integrate, customize, and contribute to react-bits (github.com/DavidHDev/react-bits) — the largest and most creative library of animated React components. It covers Vite, Tailwind CSS v4, Three.js/Fiber, GSAP, and Framer Motion integrations. Use when the user asks about react-bits, animated React components, jsrepo registry, or contributing new animated components to the react-bits repository.
React 19+ patterns, performance optimization, and component architecture. Covers hooks, state management decision trees, data fetching with use() API, Server Components, React Compiler, bundle optimization, and re-render elimination. Use when building components, optimizing re-renders, fetching data, managing state, handling forms, structuring frontends, or reviewing React code.
Design, implement, and validate Rust tests, including unit, integration, doctest, compile-fail, property, fuzz, benchmark, coverage, async, concurrency, process, daemon, IPC, terminal, platform, and hardware-facing test strategies. Use when users ask for Rust test architecture, flaky-test diagnosis, coverage gates, benchmarks, trybuild, cargo-nextest, real-process tests, or failure-path verification.
Performs a structured security code review against OWASP ASVS 4.0.3 verification requirements and CWE Top 25. Auto-invoked on pull request reviews, when code touching authentication, authorization, cryptography, or input handling is shared. Produces findings mapped to ASVS controls and CWE identifiers with severity ratings and specific remediation guidance.
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.