Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm install). Full TypeScript support, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, human approval. Use for: JavaScript integration, TypeScript, Node.js, React, Next.js, frontend apps. Triggers: javascript sdk, typescript sdk, npm install, node.js api, js client, react ai, next.js ai, frontend sdk, @inferencesh/sdk, typescript agent, browser sdk, js integration
Best practices and usage guide for the JAW SDK (@jaw.id/core, @jaw.id/wagmi, @jaw.id/ui). Use this skill when writing code that uses jaw-sdk or @jaw.id packages, integrating JAW smart accounts into an application, configuring JAW SDK features (passkeys, permissions, gas sponsoring, ENS), building with JAW wagmi hooks, implementing headless/server-side smart account operations, debugging JAW SDK issues, or when asked about JAW SDK patterns, APIs, or best practices.
Enforces purposeful JSDoc on complex or non-obvious TypeScript code—algorithms, invariants, side effects, edge cases, and public contracts—without restating types or narrating simple code. Use when writing or reviewing TypeScript, adding documentation comments, cleaning noisy JSDoc, documenting public APIs, or when the user says jsdoc, JSDoc, document this, or add docs comments.
Use this skill when starting a new project and defining baseline repository rules, especially for optional devcontainer setup, mise-first tooling, pnpm security settings, Vite+ workflows, kiso.css adoption, pre-push test gates, and project-local post-edit lint/format hooks that run after AI agent file edits.
Use this skill when the user provides MySQL DDL, CREATE TABLE statements, table structure screenshots, or asks you to fill in Kysely database types, DB interfaces, Insertable / Updateable types, bulk inserts, bulk updates, upsert, or query/modify methods. The focus is accurately converting DDL into this repository's Kysely types and corresponding service methods, avoiding mistakes in ToGenerated, null/default checks, and camelCase/snake_case mapping.
Smart Label Capture (Scandit `LabelCapture`) in Cordova / PhoneGap projects — extracting multiple fields (price, expiry date, serial or lot number, weight) from a label in one scan, using barcode fields plus text fields with regex patterns. Use for integration, label-definition configuration, captured-label handling, the Validation Flow, and SDK version migration.
Interact with Litefuse and access its documentation. Use when needing to (1) query or modify Litefuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Litefuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Litefuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative
macOS application architecture patterns covering App protocol (@main), Scene types (WindowGroup, Window, Settings, MenuBarExtra), multi-window management, NSApplicationDelegateAdaptor for AppKit lifecycle hooks, Info.plist configuration (LSUIElement for menu bar apps, NSAccessibilityUsageDescription), entitlements for sandbox/hardened runtime, and project structure conventions. Use when scaffolding a new macOS app, configuring scenes and windows, setting up menu bar apps, or resolving macOS-specific lifecycle issues. Corrects the common LLM mistake of generating iOS-only app structures.
Receive and secure Mailchimp webhooks. Use when setting up Mailchimp webhook handlers, responding to Mailchimp's GET URL validation, securing the endpoint with a URL secret, or handling audience events like subscribe, unsubscribe, profile, upemail, cleaned, and campaign.
Use when creating or iterating on a project after the Make App requirements proposal is confirmed. Decide whether to generate the My Approvals navigation by default based on business entry, edit-and-save, or approval-processing capabilities. Also covers BPM, bpmDefinitionKey, approval creation fields, save and submit, submit and save, process status, and approval tags in detail titles. Handles generation conditions, runtime initiation configuration, saving and first initiation, and status display in business lists and details. Does not cover cancel/recall, installing the My Approvals npm package or implementing the task center, approval processing, approval history, the process designer, or Console approval management.
Common style patterns, layer configurations, and recipes for typical mapping scenarios including restaurant finders, real estate, data visualization, navigation, and more. Use when implementing specific map use cases or looking for proven style patterns.
Import PyTorch, ONNX, or Keras 3 / TensorFlow 2.16+ deep learning models into MATLAB as dlnetwork objects. Use when importing .pt2 exported programs, traced .pt files, .onnx models, or Keras 3 models via matlabsaver. Covers importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromKeras, importNetworkFromTensorFlow, torch.export.export, PyTorchInputSizes, InputDataFormats, matlabsaver, tf_keras downgrade, numeric validation against PyTorch or ONNX Runtime, and placeholder/custom layer implementation. Applies when user mentions any of these functions, file formats, or encounters import errors, unsupported operator warnings, 0 learnables, or uninitialized networks.
Creates MATLAB interfaces to Python image processing and computer vision models from GitHub repositories or pip-installable packages using MPyReq. Use when asked to interface MATLAB with a Python CV/image model (segmentation, depth estimation, object detection, image generation, super-resolution, etc.), given a GitHub repo URL for an image/vision model, or asked to create an MPyReq demo for a deep-learning vision pipeline. Do NOT use for general-purpose Python-MATLAB interfacing, non-vision models (NLP, tabular, audio), model deployment/serving, or MATLAB-only image processing workflows.
Capacitor MatrixScan AR (Barcode AR, BarcodeAr) — scanning multiple barcodes at once with AR highlights and annotations, BarcodeArView attached to a DOM element, in Capacitor iOS/Android apps (not the plain-web sibling). Use for integration, symbology configuration, highlight and annotation providers, session handling, migration from BarcodeBatch/BarcodeTracking, or troubleshooting.
MatrixScan AR (Barcode AR, BarcodeAr) in Flutter projects (scandit_flutter_datacapture_barcode_ar) — scanning multiple barcodes at once with AR highlights and annotations over tracked barcodes. Use for integration, scan settings, highlight and annotation providers, migration from BarcodeBatch/BarcodeTracking, or troubleshooting.
MatrixScan AR highlights in iOS projects (Swift, UIKit/SwiftUI) — the shapes drawn over tracked barcodes. Use for adding highlights, customizing or modifying existing ones, or handling highlight tap interaction — pipeline setup belongs to matrixscan-ar-ios.
MatrixScan AR scanning pipeline in iOS projects (Swift, UIKit/SwiftUI) — BarcodeAr mode and settings, BarcodeArView, listener, feedback, camera and controls, plus migration from MatrixScan Batch (BarcodeBatch/BarcodeTracking). Use for integration, configuration, or troubleshooting — highlight and annotation work routes to the sibling skills matrixscan-ar-highlight-ios and matrixscan-ar-annotation-ios.
MatrixScan Batch (MatrixScan, BarcodeBatch, legacy BarcodeTracking) in Flutter projects (scandit_flutter_datacapture_barcode_batch) — tracking and scanning multiple barcodes at once. Use for integration, settings and symbologies, tracked-barcode handling, per-barcode brushes, advanced-overlay AR widgets, lifecycle, or troubleshooting.
MatrixScan Count (BarcodeCount) in Flutter projects — scandit_flutter_datacapture_barcode_count package. Multi-barcode counting and receiving workflows (scan-and-count, counting against a target list, status providers) with the BarcodeCountView widget. Use for integration, scan settings, result handling, UI customization, SDK version migration, or troubleshooting counting workflows.
Guidance for embedding web content in .NET MAUI apps using HybridWebView, including JavaScript–C# interop, bidirectional communication, raw messaging, and trimming/NativeAOT considerations. USE FOR: "HybridWebView", "JavaScript interop", "embed web content", "JS to C# interop", "C# to JavaScript", "web view interop", "raw message", "InvokeJavaScriptAsync", "web content MAUI". DO NOT USE FOR: deep linking from external URLs (use maui-deep-linking), REST API calls (use maui-rest-api), or Blazor Hybrid apps (different from HybridWebView).
Maintains repo-local action contracts and harness repositories where product CLI and MCP adapters stay thin over core libraries. Use when adopting or improving steward.yaml actions, capability-level adoption evidence, cold-start proof loops, probes, benchmarks, CLI/MCP/core parity, adapter refactors, packages/core boundaries, or sibling harness layout; use repo-quality-system-lifecycle first for general app/library/tool stewardship baselines.
Implements MercadoPago recurring subscriptions with preapproval plans in a React + Supabase Edge Functions stack. Covers the full lifecycle — creation, cancellation, plan changes, payment method changes, pause/reactivate, webhooks, and CRON sync. Use when building or modifying subscription billing, payment forms, edge functions for MercadoPago, or webhook handlers.
Use when building Cardano transactions with MeshJS SDK. Covers MeshTxBuilder API for sending ADA, minting NFTs and tokens, spending from Plutus scripts, staking, governance voting, DRep registration, and multi-sig patterns. Includes correct method ordering, coin selection, fee calculation, and troubleshooting common Cardano transaction errors.
Use when integrating Cardano wallets with MeshJS SDK. Covers browser wallet connection (CIP-30) for Eternl, Nami, Lace, Flint, and Yoroi, headless server-side wallets from mnemonic or private keys, transaction signing, CIP-8 data signing for authentication, multi-signature workflows, and React wallet integration patterns.
Use when working on the underlying infrastructure of BK-CI microservices, such as conditional configuration, event-driven design, inter-service communication, internationalization, and logging conventions. Prefer this when the user needs to set up multi-environment configuration, asynchronous events, Feign calls, or unified i18n/logging.
Migrates existing Xcode projects to Tuist generated workspaces with build and run validation, external dependency mapping, and migration checklists. Use when adopting Tuist for an existing app or converting a hand-edited Xcode project to generated projects.
Use when designing and auditing multiple modules, system-wide quality trade-offs, data authority, target/transition, and migration/recovery from product value. Not for local class improvements, selecting trendy technologies, or extracting a single contract.
Use when converting natural-language requirements into preconditions, postconditions, invariants, and failure guarantees, plus per-condition guarantee responsibility and contract tests. Not for UI input validation only, adding general tests, or whole business implementations.
Use when auditing a fixed use case for missing terms, concepts, value constraints, states, transitions, failures, time, writer/reader, and authority. Not for modeling the whole world, diagrams only, general DDD explanations, or mere data item lists.
Use when separating the purpose, operations, and contracts known to consumers from internal technology and procedures, and designing/auditing technology leakage, caller branching, responsibility boundaries, and change locality. Not for reducing ifs, mass-producing interfaces, or whole architecture selection.
Use when untangling solution-first thinking, vague requirements, and mismatched terms, premises, purposes, and success conditions, and creating a Problem Frame and Context Packet. Not for specialized contracts, model design, whole implementations, or approved mechanical changes.
Router used when integrating two or more specialized deliverables, or an end-to-end trace from requirements to implementation, review, and verification. Not for a single design deliverable or small mechanical changes that do not touch public semantics.
Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.
Huawei Ascend NPU model compression tool (msModelSlim). Use for LLM quantization (W4A8, W8A8, W8A8S, W8A16), MoE model compression, multimodal model compression (Qwen-VL, InternVL, HunyuanVideo, FLUX, SD3), calibration data preparation, precision auto-tuning, sensitive layer analysis, custom model integration, and deployment in MindIE/vLLM-Ascend. Supports Qwen, LLaMA, DeepSeek, GLM, Kimi, InternLM and more.
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error branches/outputs, retries, retryOnFail, Respond to Webhook status codes, 4xx/5xx, Error Trigger, or "my workflow fails silently". Covers per-node error outputs and wiring, retry/self-healing, error-trigger workflows, and 4xx/5xx response shapes.
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.