Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill for ANY question about creating test or evaluation datasets for LangChain agents. Covers generating datasets from traces (final_response, single_step, trajectory, RAG types), uploading to LangSmith, and managing evaluation data.
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
Run a full product launch review against your framework and risk calibration. Use when the user says "review this launch", "[feature] legal review", "can we ship this", "what legal issues does [product] have", or references a PRD or launch tracking ticket that needs a category-by-category review memo.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Teach users any decomposable subject or system through “orientation → minimal example → expand component by component → visualize the whole.” Use when the user wants to learn a framework, library, algorithm, protocol, business process, or concept by starting with the smallest runnable or hands-on demo, understanding each component step by step, and then seeing the overall structure. Triggers: “teach me XXX,” “learn XXX with a minimal demo,” “teach me XXX from scratch,” “learn XXX step by step,” “learn XXX with a minimal example,” “learn-by-minimal XXX.” Also applies to requests like “I want to understand how React/Vue/TCP/quicksort/the order placement flow is put together.” Not for pure fact lookups, code debugging, one-off questions, or simple questions that don't need structured, progressive learning.
Check in-progress leave for deadline warnings and decisions that need to be made. Surfaces only the leave that needs action, with the reason — not a status dashboard. Recommended weekly, or whenever a lawyer needs to know which leaves have upcoming approval, certification, or expiry deadlines.
Use this skill when managing LinkedIn Ads for B2B SaaS — full-funnel campaign planning, media plans and budget allocation, audience sizing and targeting, campaign structures, bidding, performance analysis against benchmarks, account audits, creative and copy (Thought Leader Ads, conversation ads, document ads), and scaling decisions. Triggers: LinkedIn Ads, LinkedIn campaign, LinkedIn advertising, B2B ads, paid social, LinkedIn paid, ad account, campaign manager, LinkedIn lead gen, LinkedIn retargeting, ad audit, ad performance, ad optimization, campaign plan, media plan, LinkedIn budget.
This skill should be used when analyzing a downstream project's git diff after Lisa was applied to identify improvements that should be upstreamed back to Lisa templates. It validates the environment, captures the diff, correlates changes with Lisa template directories, categorizes each change, and offers to upstream improvements.
Apply Litestar dependency injection with Provide, Dependency markers, layered scopes, overrides, generator-based cleanup, per-request caching, and nested providers. Use when wiring services, settings, database sessions, request-derived resources, or test doubles into Litestar handlers, controllers, routers, and apps. Do not use when plain local function parameters or a small helper are sufficient.
LLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter, LiteLLM) - Configuring model fallbacks and reliability - Implementing cost-based or latency-based routing - A/B testing different models - Self-hosting an LLM proxy Keywords: openrouter, litellm, llm gateway, model routing, fallback, A/B testing
Write a load and performance testing plan for a service. Use when asked to create a performance test plan, write load testing documentation, define stress or soak test scenarios, or set performance regression gates for CI. Produces a complete test plan document with scenario definitions, k6/Locust script skeleton, threshold table, result interpretation guide, and CI integration steps.
Write a local development environment setup guide for a service or project — covering prerequisites, repository setup, environment variables, local service dependencies, database seeding, running the service, running tests, common gotchas, IDE recommendations, and first-contribution checklist. Use when asked to write a dev setup guide, create onboarding documentation for engineers, document local environment setup, or write a getting-started guide for a codebase. Produces a complete setup guide that a new engineer can follow from zero to running tests in under 30 minutes, with a troubleshooting section for the most common setup failures.
A code review skill based on local git diff. Use it for a self-check review before opening a PR, strictly reusing pr-review's three dimensions (code quality standards, FastGPT style conventions, common issues checklist). Supports reviewing unstaged changes, staged changes, a single commit, or all changes on the current branch relative to a baseline branch.
Build production-ready web authentication using Lucia Auth and The Copenhagen Book patterns. Use when users ask to "add auth", "implement authentication", "setup login", "add sessions", "password reset", "verify email", "implement OAuth", "add 2FA/MFA", "add passkeys", "password hashing", or reference "lucia auth" or "the copenhagen book". Default to a production baseline for browser-based web apps, not a demo-only login flow.
Activates when the user is about to apply a successful methodology (someone else's or their own past one) to a new scenario. Typical trigger signals: "company X succeeded with method X, we should try it too", "this worked for me before, let's keep doing it", "the industry best practice is Y". When not to invoke: the user faces a recurring instance of the same kind of problem and needs execution, not methodology selection. Difference from "contradiction analysis": this skill emphasizes "each problem differs in nature and needs a different method", while the latter emphasizes "find the single most important problem".
Review claims in marketing copy and identify which need substantiation, rewriting, or removal. Use when the user says "review this marketing copy", "check these claims", "can we say this", "is this puffery or a problem", or pastes marketing content (landing page, email, ad, tagline).
Prevents churn through cancel flows, dunning sequences, win-back campaigns, and health scoring. Triggers for 'churn', 'cancel flow', 'dunning', 'win-back', 'failed payment', 'retention rate', or 'save offer' — not general email sequences or newsletters (use email) even if they mention re-engagement. This skill owns the post-cancellation and at-risk-customer lifecycle.
Executes the 6-phase SOSTAC planning framework (Situation, Objectives, Strategy, Tactics, Action, Control) through deep research and proactive recommendations. Instead of just interviewing the user, it researches first, delivers insights and strategic recommendations, then validates with targeted questions. Triggers for 'SOSTAC', 'marketing plan', 'situation analysis', 'marketing strategy', 'marketing objectives', or when routed by marketing-agency.
Karl Marx's persona and thinking operating system. A deep distillation based on primary classics such as Das Kapital, The Communist Manifesto, and The German Ideology, historical context, records of his collaboration with Engels, and contemporary applications. Includes 5 core mental models, 8 decision heuristics, a complete expression DNA, and an Agentic research protocol (for any topic, first investigate material conditions, class dynamics, and economic data, then conduct dialectical critique). Use for: critique of contemporary capitalism, class analysis, theoretical consulting, and academic document creation (seamlessly integrated with docx). Trigger words include "用Marx视角", "马克思会怎么分析", "切换到Marx.skill", "辩证批判", "历史唯物主义视角".
Applies Material Design 3 Expressive dynamic color and theming principles to user interfaces. Use this when working on color palettes, themes, dynamic color systems, accessibility, or when the user asks to apply Material Design 3 color guidelines to a design or application.
Applies Material Design 3 Expressive motion and animation principles to create natural, intuitive, and engaging user experiences. Use this when implementing animations, transitions, micro-interactions, or when the user asks to apply Material Design 3 motion guidelines.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
MatrixScan AR (Barcode AR, BarcodeAr) in .NET for Android projects (`net*-android` TFM, `Scandit.DataCapture.Barcode` NuGet, non-MAUI — MAUI apps use matrixscan-ar-net-maui) — scanning multiple barcodes at once with AR highlights and annotations. Use for integration, settings, listeners/events, highlight and annotation providers, lifecycle, SDK version migration, or troubleshooting.
MatrixScan AR (Barcode AR, BarcodeAr) in .NET for iOS projects (`net*-ios` TFM, `Scandit.DataCapture.Barcode` NuGet, non-MAUI — MAUI apps use matrixscan-ar-net-maui) — scanning multiple barcodes at once with AR highlights and annotations (info annotations, popovers, status icons) in C#. Use for integration, settings, listeners/events, highlight and annotation providers, torch/zoom/macro controls, lifecycle, SDK version migration, or troubleshooting.
Query the local Maven/Gradle artifact index from the terminal. Use when you see an import but cannot find the class definition in the workspace (it likely comes from a compiled internal library), when you need to read the actual implementation of an internal or non-well-known library, or when you need to find which artifact contains a class, discover implementations of an interface, or inspect proto/resource files inside JARs. Do not use for well-known standard libraries (java.util, Spring core, etc.) that the AI already knows.
Reviews embedded Rust firmware for RP2350 (Raspberry Pi Pico 2 W) and ESP32-S3 (Heltec) microcontrollers with focus on Embassy async runtime, memory constraints, LED control, CAN attachment protocols, and SLCAN bridging. Use when reviewing MCU firmware changes, debugging LED controller issues, evaluating Embassy async patterns, checking static memory allocation, validating SLCAN implementations, or assessing hardware-specific code for WS2812 LEDs, CAN peripherals, and tool attachments. Covers no_std environments, PIO state machines, RMT peripherals, and USB CDC serial communication.
Browse, search, and export documentation from any source using the mdzilla CLI. Use when Claude needs to: (1) Read or browse documentation for a library, framework, or project, (2) Fetch docs from GitHub repos, npm packages, or websites, (3) Export documentation to flat markdown files, (4) Look up API references, guides, or usage examples from doc sites. Triggers: user asks to "read the docs", "check the documentation", "browse docs for X", "fetch docs from", "export docs", or references a docs site URL, npm package docs, or GitHub repo docs.
You are a professional media writing expert with extensive experience in creating engaging and impactful content across multiple formats. Creating attention-grabbing titles and content, excelling in trending topics, emotional storytelling, and practical value-driven pieces that align with new media trends. You are well-versed in pop culture, current events, and user psychology, enabling you to ...
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
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.