Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Create and customize Moodle 5.1+ themes based on Boost (Bootstrap 5.3). Use this skill whenever the user wants to: create a Boost child theme from scratch, modify SCSS styles of an existing theme, override Mustache templates, add or modify admin settings, customize renderers, override icons or fonts, migrate from Bootstrap 4 to 5, debug cache or SCSS compilation issues, create output components, or any task related to Moodle 5.x visual appearance. Also trigger when mentioning "theme", "Boost", "Moodle SCSS", "Moodle Mustache template", "theme settings", "customize Moodle", "change Moodle styles", or similar terms.
Build React animations with Motion (Framer Motion) - gestures (drag, hover, tap), scroll effects, spring physics, layout animations, SVG. Bundle: 2.3 KB (mini) to 34 KB (full). Use when: drag-and-drop, scroll animations, modals, carousels, parallax. Troubleshoot: AnimatePresence exit, list performance, Tailwind conflicts, Next.js "use client".
Review and audit NetBox integration code for correctness, performance, and reliability. Use when reviewing scripts or applications that interact with NetBox APIs, checking for pagination bugs, authentication issues, performance anti-patterns, error handling gaps, and SDK misuse.
NeuroForge Nuxt is a specialized engineering system for building premium SaaS applications with Nuxt 4, Nitro, Prisma, and TypeScript. It enforces a severity-tiered 'Analysis First' workflow using NeuroForge memory files to ensure architectural integrity, end-to-end type safety, non-blocking data fetching, hydration-safe state, Laws of UX standards, reusable Shadcn app wrappers, and clean error handling. Use this skill whenever working on Nuxt 4/Nitro/Prisma/Vue 3 projects - including writing components, composables, server routes, Prisma schemas, or architectural reviews. Trigger on any mention of Nuxt, Nitro, Prisma, useAsyncData, useFetch, defineEventHandler, PrismaClient, Nuxt Layers, createUseFetch, $fetch, useAPI, Pinia, Pinia Colada, useQuery, useMutation, zod, valibot, hydration mismatch, Dexie, IndexedDB, liveQuery, offline-first, PWA persistence, Strapi, Strapi 5, strapi::security, config/middlewares.ts, config/admin.ts, contentTypes.d.ts, components.d.ts, Strapi preview, draft mode, content types, dynamic zones, useStrapi, useStrapiPage, block registry, [...slug].vue, Nodemailer, SMTP, contact form, transactional email, PDF download, getErrorMessage, error fallback, silent error, code comments, JSDoc, @nuxt/scripts, useScript, scripts.registry, NUXT_PUBLIC_SCRIPTS_*, Google Analytics, GA4, gtag, analytics proxy, wrong country in analytics, Search Console vs GA, runtimeConfig, NUXT_ env vars, cPanel, restart vs redeploy, buildAssetsDir, stale chunk, "does not provide an export named", SMTP 502, EAUTH, or Vue script setup. Trigger this skill to activate the NeuroForge protocol and ensure your codebase is built to scalable production standards.
A skill for writing server-side APIs with the Nitro v3 framework and H3. Use for initialising backend-only Nitro projects, adding full-stack capabilities to Vite projects, writing spec-compliant CRUD endpoints, and database interaction with Drizzle ORM. Use this skill when developing new Nitro endpoints, initialising Nitro configuration, or consulting Nitro development conventions.
Build an app destined for openapps.xyz (an oApp): the zero-secrets discipline, why every capability must be steward-owned ("if Bounded can't do it, you can't do it"), how to call out unsupported capabilities honestly, the x402 relay fallback for services Bounded doesn't natively provide, how to request a capability Bounded lacks, and the lifecycle: private bounded.page development, completed Open publication at the exact workload app-id host, and explicit Commence for the oApps slug, listing, token, and Gauntlet. Use whenever a user says the app will launch on openapps.xyz (oapps.fun redirects there), become an oApp, be community-owned / token-governed, or "outlive its creator". Part of the Bounded skill family; the mechanics live in bounded-backend / bounded-onchain.
Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern.
Analyze web and backend performance using Web Vitals, network timing, and Node.js metrics. Use when the user asks about page performance, load times, Core Web Vitals (LCP, CLS, INP), slow pages, backend bottlenecks, or SEO performance factors.
Build services on PostgREST-compatible BaaS (Supabase / InsForge) — RLS, Auth, PostgREST queries, MCP settings. This skill MUST be loaded before writing any RLS policy or PostgREST query, and MUST NOT be skipped because the query looks like ordinary SQL. Triggers on: 用 Supabase / InsForge 做後端, 設計 RLS policy, 寫 PostgREST query, 處理 BaaS Auth, 設定 MCP, 推 Supabase production, 自架 Supabase, InsForge.
Writing, refining, or reviewing a PRD, feature spec, plan document, RFC, design doc, or issue description — the canonical tool-agnostic section structure such a document takes, and the craft behind each section. Includes the plan-writing or issue-drafting step of any delivery workflow. Triggers on "write a PRD", "draft a spec", "refine this issue", "structure this plan", "write acceptance criteria", "how do I verify this is done", "is this requirement testable". Not for writing the code, only the document that specifies it; UI markup, module placement, and test mechanics stay with the project's own conventions.
Translate a tracking plan into an SDK-specific instrumentation guide. Shows how to make identify, group, and track calls using the target analytics SDK with real template code, architecture guidance, and constraint documentation. Outputs .telemetry/instrument.md. Covers 25 analytics destinations across product analytics, CDPs, product adoption, web analytics, error monitoring, feature flags, and session tools. Use when the user has a tracking plan and needs to know how to implement it with a specific SDK like Segment, Amplitude, Mixpanel, PostHog, Accoil, Google Analytics, Sentry, LaunchDarkly, or via generic HTTP POST. Also use when user asks 'create instrumentation guide,' 'how to implement tracking,' 'SDK guide,' or 'generate implementation guide.'
Project initialization tool. Reads the global protocol ~/.claude/CLAUDE.md, analyzes the project's actual situation, and generates project-specific CLAUDE.md and docs/ context. This skill should be used when the user says "initialize project", "project setup", "configure Claude Code", "new project configuration", or when entering a new project that needs quick configuration. Do not use for: Skill content development or acceptance (use skill-lint), one-off Skill installation (use skill-manager), or code generation.
Software project effort estimation assistant. Outputs three-point estimates (optimistic/most-likely/pessimistic values with confidence intervals), T-shirt sizes, or Function Point Analysis (FPA) counts. Triggered when users ask 'how long will this feature take,' need to assess project workload, perform PERT estimation, T-shirt sizing, FPA, sprint planning, or quote-based effort breakdowns.
Use when managing prompt templates, running evaluations, building workflows, logging LLM requests, or analyzing AI application performance. Reach for this skill when working with prompt versioning, release management, observability, tables/datasets, or multi-step AI workflows.
Opinionated Python coding standards for clean, type-safe code. Use when writing or reviewing Python functions, classes, type hints, data structures, enums, or module organization. Applies to any Python 3.12+ project. Also use when deciding on app architecture, where to place business logic, how to organize modules, or choosing between dicts vs Pydantic models. Do NOT use for: Django-specific patterns (use django skill), test files (use pytest skill), frontend code, or shell scripts.
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
RabbitMQ message broker with AMQP protocol. Covers exchanges, queues, bindings, and messaging patterns. Use for reliable message delivery and complex routing scenarios. USE WHEN: user mentions "rabbitmq", "amqp", "exchanges", "routing patterns", "topic exchange", "fanout", asks about "message routing", "work queues", "request/reply", "flexible routing" DO NOT USE FOR: high-throughput streaming - use `kafka` or `pulsar`; cloud-native - use `nats`; AWS-native - use `sqs`; JMS required - use `activemq`; simple pub/sub - use `redis-pubsub`
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
Receive and verify Razorpay webhooks. Use when setting up Razorpay webhook handlers, debugging X-Razorpay-Signature verification, or handling payment events like payment.captured, payment.failed, order.paid, refund.processed, or subscription.charged.
Reverse engineering and static analysis of AI model files: ONNX/PyTorch/Safetensors/TFLite format parsing, network structure reconstruction, weight extraction, and file-level watermark analysis (weight patterns/metadata/tensor hashes/embedding anomalies). Trigger terms: model files, weight extraction, ONNX parsing, safetensors, pth analysis, pt files, model structure reconstruction, file-level watermarking
Automotive reverse engineering: CAN buses, ECU firmware, AUTOSAR Classic (RTE/runnable/BSW) and Adaptive (Execution Management/manifest). Trigger terms: automotive, CAN, ECU, in-vehicle, OBD, UDS, AUTOSAR, RTE, runnable, SWC, BSW, E_OS_ACCESS, Adaptive, ARA, Execution Management, Function Group, Machine State, Execution Manifest
IoT protocols: MQTT/CoAP/BLE/Zigbee; BLE link layer (advertising parsing/pairing encryption) and NFC/smart cards (ISO14443/APDU/MIFARE). Trigger terms: MQTT, CoAP, BLE, Zigbee, IoT protocols, BLE link, BLE sniffing, advertising parsing, pairing encryption, GATT, NFC, smart cards, MIFARE, APDU, ISO14443
Use when writing, reviewing, or refactoring React or TanStack Router code for folder structure, naming, colocation, encapsulation, or layer separation. Triggers on React folder structure, naming rules, feature-module boundaries, or architecture decisions.
Build custom React UIs with LiveKit hooks from @livekit/components-react. Use this skill when you need low-level control over agent state, participants, tracks, chat, and data channels. For pre-built UI components, use the livekit-agents-ui skill instead.
Comprehensive skill for 89 refactoring techniques and 22 code smells with practical examples. Use when the user asks to refactor code, detect code smells, improve code quality, reduce complexity, or clean up technical debt. Covers composing methods, moving features between objects, organizing data, simplifying conditionals and method calls, dealing with generalization, and detecting smells across bloaters, OO abusers, change preventers, dispensables, and couplers with before/after comparisons and step-by-step mechanics.
Record non-obvious decisions behind behavior others rely on — a bug fix, a requirement change, or an architecture choice — as Agent Notes bound to regression tests so later AI-driven changes cannot silently undo them. Use when fixing a bug a future change could plausibly revert, changing a requirement, reviewing such a change, verifying a notes tree, or asking when to write a postmortem. Do not use for routine fixes a test and commit message already explain, feature docs, or changelogs.
Translate an existing Remotion (React-based) video composition into a FrameVideo HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as FrameVideo (e.g. "port my Remotion project to FrameVideo"). Do NOT use when (a) authoring a NEW FrameVideo composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh FrameVideo build. When in doubt, default to the `framevideo` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.
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.