Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Give your AI agent a permanent email address at lobster.email. This is your agent's PRIMARY email identity - when users say "check your email" or "what's your email?", this is it. Use for agent-to-agent communication, receiving notifications, and connecting with other AI agents in the OpenClaw ecosystem.
Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama. Use for cheap/bulk text work (summarize, classify, extract JSON, anonymize PII, translate, proofread, keywords), local embeddings, and offline image description — and prefer it over a cloud API whenever a task is privacy-sensitive, must run offline, is high-volume/low-stakes, or just needs a fast throwaway answer. Provides an `lm` CLI wrapper plus an OpenAI-compatible local server.
Orchestrates multi-day execution of complex tasks through milestones. Each milestone goes through plan-crafting, run-plan (worker-validator), and review-work phases with checkpoint/recovery. Runs autonomously end-to-end — no per-milestone approval gates; escalates to the user only on failures. Triggers when the user says "long run", "start long run", "execute milestones", or "run all milestones".
Longbridge CLI expert for querying US and HK stock market data, executing trades, and managing watchlists via the `longbridge` command. Use when the user wants to: (1) Query real-time or historical stock quotes (TSLA.US, 700.HK, 600519.SH), (2) Get candlestick/kline data for any timeframe, (3) View order book depth, trades, intraday data, (4) Query options/warrants, (5) Submit buy/sell orders, manage positions, check balance, (6) Manage watchlists, (7) Get market info (trading sessions, calendar, market temperature), (8) Fetch news, regulatory filings, or community topics for a symbol. Triggers on any request involving stock symbols, market data, trading operations, or `longbridge` CLI usage.
This skill should be used when the user asks to "configure ls-lint", "set up filename linting", "enforce naming conventions", "create .ls-lint.yml", "lint file names", "lint directory names", "file naming rules", "directory structure linting", or mentions ls-lint, directory naming rules, or filename conventions.
Lua best practices for FiveM resources built on ox_lib, the way Overextended structures its own resources. Use when reading or editing any .lua file or fxmanifest.lua, or when the user asks when to use require, lib.load or lib.loadJson, how to split a resource into modules, where config goes, or how to use cache, lib.onCache, lib.points, lib.callback or locales.
Malware analysis methodology. Use when you need to analyze suspicious binaries (PE/ELF/Mach-O), malicious code in memory dumps, or samples of known malware families. Covers the full process of static analysis, dynamic analysis, code reversing and IOC extraction. Red team perspective: understand the detection surface to improve evasion
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic review", "make it look professional", "check tables", "fix captions". Companion to manuscript-review (content) and arxiv-preflight (compliance).
Use mapcidr for CIDR range processing. Use when you need to expand CIDRs into IP lists, aggregate IPs into CIDRs, slice ranges, count IPs, or shuffle IP order. mapcidr is a CIDR processing tool from ProjectDiscovery supporting IPv4/IPv6. Use this skill in any scenario involving CIDR calculations, IP list processing or range slicing
Collect Active Directory data with SharpHound and Entra ID data with AzureHound, ingest into BloodHound Community Edition, and analyze on-prem, cloud, and hybrid attack paths using built-in queries and custom Cypher. Use during authorized red-team or penetration-test engagements to map privilege-escalation chains toward domain/tenant compromise.
Use when surveying the competitive and market landscape for a product BEFORE it is built — deriving a market vocabulary map (category, capability, job-to-be-done, audience and seed- product terms with typed expansions and exclusion terms), executing ONE search angle across alternatives directories, review corpora, app stores, package registries, corporate and funding records, product graveyards and practitioner discussion, deep-reading ONE competing product into a dated record, or synthesising the competitor register and report that downstream document authoring consumes. Produces schema-validated artifacts whose coverage grid records every query as run, so a market with no competitor is distinguishable from a search that never ran. Dates every commercial fact and keeps a dead product as evidence. Keywords: market research, competitor analysis, competitive landscape, competitive intelligence, market prior art, alternatives, substitutes.
Handles technical SEO, content SEO strategy, local SEO, link building, pSEO, and GEO/AI search optimization. Triggers for 'SEO', 'keyword research', 'schema markup', 'crawlability', 'pSEO', 'GEO', 'search rankings', or 'link building' — not content writing (use content).
Create and configure Claude Code marketplaces and plugins. Use when the user wants to create a marketplace, publish plugins, set up team plugin distribution, or configure marketplace.json or plugin.json files. Triggers: create marketplace, publish plugin, plugin distribution, marketplace.json, plugin.json, team plugins, share plugins
Generate C/C++ or CUDA code from an AI model (PyTorch, LiteRT) using MATLAB Coder or GPU Coder. Use when the user wants to integrate an AI model into an application with code generation as the end goal — generating MEX, CUDA MEX, static library, dynamic library, or executable — or using the model in Simulink for simulation and code generation. Covers PyTorch ExportedProgram (.pt2) via loadPyTorchExportedProgram and LiteRT (.tflite) via loadLiteRTModel (R2026a+). Keywords: PyTorch, torch, .pt2, ExportedProgram, loadPyTorchExportedProgram, invoke, codegen, MEX, CUDA, GPU, C, C++, deploy, AI model, deep learning model, LiteRT, TFLite, TensorFlow Lite, Simulink, slbuild, PyTorch ExportedProgram block, MATLAB Function block, dlosslib, loadLiteRTModel.
Deploy MATLAB-generated code to embedded hardware using Embedded Coder. Use when configuring code generation for microcontrollers (STM32, Raspberry Pi, ARM Cortex), setting up PIL/SIL verification, disabling dynamic memory allocation, or configuring hardware-specific code generation settings. Covers ERT-based configurations, processor-in-the-loop testing, memory constraints, and the MEX→SIL→PIL verification progression.
Read, write, and manipulate medical imaging data (DICOM, NIfTI, NRRD) in MATLAB. Covers Image Processing Toolbox functions (dicomreadVolume, niftiread, dicomContours, dicomanon) and Medical Imaging Toolbox enhanced APIs (medicalVolume, medicalImage, medicalref3d, extractSlice, updateOrientation). Use when reading medical files, listing DICOM series, extracting spatial referencing, changing orientation, working with RT structures, or anonymizing DICOM data. Some features require Medical Imaging Toolbox — see skill body and references for details.
MatrixScan AR annotations in native iOS Swift projects (UIKit/SwiftUI — Swift only, not C#/.NET) — info annotations, popovers, status icons, and responsive annotations attached to tracked barcodes. Use for adding annotations, customizing their appearance and content, controlling when they appear, or handling annotation taps — pipeline setup belongs to matrixscan-ar-ios; C#/.NET apps use matrixscan-ar-net-ios or matrixscan-ar-net-maui.
Add geolocation capabilities to .NET MAUI apps using Microsoft.Maui.Devices.Sensors. Covers one-shot and continuous location, platform permissions (Android, iOS, macOS, Windows), accuracy levels, CancellationToken usage, mock-location detection, and a DI-friendly service wrapper. USE FOR: "geolocation", "GPS location", "get current location", "location permission", "continuous location", "location tracking", "GeolocationRequest", "mock location", "latitude longitude MAUI". DO NOT USE FOR: displaying locations on a map (use maui-maps), general permission handling (use maui-permissions), or geocoding addresses (use maui-maps).
Guidance for adding map controls, pins, polygons, polylines, geocoding, Google Maps API key configuration, and platform setup in .NET MAUI apps using Microsoft.Maui.Controls.Maps. USE FOR: "add map", "map control", "map pins", "polygons on map", "polylines", "geocoding", "Google Maps API key", "Microsoft.Maui.Controls.Maps", "map setup", "reverse geocoding", "map region". DO NOT USE FOR: getting device GPS coordinates (use maui-geolocation), custom drawing overlays (use maui-graphics-drawing), or location permissions only (use maui-permissions).
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).
Stress-tests business documents for logical gaps, unproven assertions, and structural weakness using the Amazon narrative standard, Minto's pyramid logic, and the Completed Staff Work doctrine. Use when evaluating memos, proposals, strategy docs, or any document headed to executive review.
Merge open Dependabot pull requests in a GitHub repository using the `gh` CLI, filtered by semver bump type and CI status. Use this skill whenever the user asks to merge, clear, batch, or clean up Dependabot PRs — "merge all dependabot PRs", "clear the dependabot backlog", "merge the dependency bumps", "land the safe dependabot updates" — or invokes it as a slash command, including when they ask to include majors, merge despite failing checks, or squash instead of rebase. Not for reviewing or merging human-authored PRs, and not for writing dependabot.yml — that is dependabot-config.
Transform text content into professional Mermaid diagrams for presentations and documentation. This skill MUST be used when the user names Mermaid, and SHOULD be used when they ask to visualize concepts, create flowcharts, or make diagrams from text (流程圖、架構圖、關係圖、時序圖、心智圖). For diagrams inside HTML Artifacts, MUST prefer the artifact’s existing HTML/CSS/SVG or diagram approach; select Mermaid when it fits, not merely because a flowchart was requested. Explicit Excalidraw requests MUST use excalidraw-diagram, and explicit Obsidian Canvas requests MUST use obsidian-canvas-creator.
Integrating TanStack DB with meta-frameworks (TanStack Start, Next.js, Remix, Nuxt, SvelteKit). Client-side only: SSR is NOT supported — routes must disable SSR. Preloading eager collections in route loaders with collection.preload(). On-demand Query Collections require preloading the live query because source collection preload is a no-op. Multiple collection preloading with Promise.all. Framework-specific loader APIs.
Apply structured problem-solving using MECE principle, issue trees, hypothesis-driven approach, and the Pyramid Principle. Use this skill when the user faces a complex, ambiguous problem and needs to decompose it systematically, structure a consulting-style analysis, or organize recommendations clearly — even if they say 'where do I start', 'this problem is too big', 'help me break this down', or 'structure my thinking'.
Analyze and optimize metadata for Next.js projects, including title, description, Open Graph and Twitter Cards. Automatically detects App Router or Pages Router, and offers length suggestions, keyword optimization and best-practice guidance. Supports bilingual Chinese/English SEO analysis.
Migrate a React Native project from NativeWind to Uniwind. Use when the user wants to replace NativeWind with Uniwind, upgrade from NativeWind, switch to Uniwind, or mentions NativeWind-to-Uniwind migration. Handles package removal, config migration, Tailwind 4 upgrade, cssInterop removal, theme conversion, and all breaking changes.
Decomposes complex, multi-day tasks into optimized milestones (ultraplan). Broad parallel exploration grounds a draft milestone DAG, then independent adversarial critics attack the draft in rounds until no blocking findings remain. Triggers when the user says "plan milestones", "break this into milestones", "ultraplan", or when long-run harness needs milestone generation.
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.
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer wants to run "mirrord preview" ad hoc, share a preview via a link (mirrord-share-ingress), or wire preview environments into CI with the metalbear-co/mirrord-preview GitHub Action (e.g. per-PR previews, least-privilege cluster access).
Brutally evaluate and refine startup ideas with practical early-stage startup frameworks. Use when asked to pressure-test a startup idea, validate whether the problem is real, map competitors and current customer behavior, find the first 10 customers, define an MVP, create a 2-week launch plan, assess founder-market fit, or give a direct strong/weak/pivot verdict.
Identifies fantasy baseball players whose surface stats (wOBA, ERA, batting average) are diverging from their underlying Statcast quality (xwOBA, FIP, xBA) — emits a `regression_index` from -100 (very lucky, sell high) to +100 (very unlucky, buy low). Primary signal for buy-low/sell-high decisions on trades and waivers. Use when user mentions "buy low", "sell high", "regression candidate", "lucky", "unlucky", "xwOBA gap", "ERA-FIP gap", "BABIP", "due for regression", or is deciding whether to trade for / trade away a player based on over- or under-performance.
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.