Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Cheminformatics pipeline for small-molecule property calculation, filtering, and similarity analysis using RDKit. Use when the user asks to compute molecular descriptors, filter compounds by Lipinski or Veber rules, detect PAINS, calculate fingerprint similarity, run matched molecular pair analysis, generate ADMET descriptors, or process SMILES. Triggers include "RDKit", "molecular descriptors", "Lipinski", "rule of five", "Veber", "PAINS", "pan-assay interference", "Morgan fingerprint", "Tanimoto", "fingerprint similarity", "matched molecular pair", "MMP", "mmpdb", "ADMET", "druglikeness", "SMILES", "cheminformatics", "compound filtering", "chemical similarity".
Use this skill to pick which behaviors to cover in an Android test suite using Google's five-category state vocabulary plus the explicit "what NOT to test" list from `/training/testing/fundamentals/what-to-test`. Covers state on screen, state held in memory (ViewModels), persisted state (DB / DataStore / files), other state (system bars / system services), and errors / edge cases. Includes Google's verbatim "Tests to Avoid" list (framework entry points such as activities / fragments / services should not have business logic) and an edge-case mining checklist. Use when the user asks "what should I write tests for", "should I unit-test this Activity", "do I need a test for this util class", "what edge cases am I missing", or "should I test the ViewModel or the Composable".
Back up and reset Claude Desktop's local state on macOS and Windows; check network egress, DNS/WebRTC, proxy, and relay configuration; automatically deliver an HTML QA report and a navigable Claude account-ban-prevention guide. First pause to confirm the task scope: clear local Claude usage traces or perform only a network check. The guides walk first-time and previously restricted users through manual preparation (time zone, egress, TUN, pre-login checks, account and payments, daily use, pre-departure checklist) and invoking the skill for QA. The environment can be checked independently; no guarantee is made to remove server associations or prevent account bans. Do not apply to Linux or unverified installation methods.
Use CLI for Microsoft 365 (`m365`) to manage Microsoft 365 tenants, SharePoint, Entra ID, Teams, Outlook, Planner, Power Platform, Viva, Purview, and more from the command line. Activate when the user asks to manage, query, configure, or automate anything in Microsoft 365 — including SharePoint sites/lists/pages, Entra users/groups/apps, Teams channels/messages, Outlook mail/calendars, Planner tasks, Power Automate flows, Power Apps, Viva Engage/Connections, Purview labels, OneDrive, To Do, or Microsoft Graph extensions.
Search products across 8 Chinese e-commerce platforms: Taobao, Tmall, JD, PDD, 1688, AliExpress, Douyin, XHS. Zero-config — no API keys needed. Powered by Shopme unified product database. Use when the user asks to find products, get product info by URL or ID, search Chinese suppliers, or compare prices.
Use whenever writing, editing, or reviewing code that carries comments or doc blocks, in any language. Covers the test a comment has to pass to earn its place, the comments to delete (restating the code, listing fields a doc block sits above, boilerplate copied across files, a comment that drifted away from the line it explains), how to cut a four-line comment down to one without losing the reason, and what belongs in a doc block versus what the signature already says. Also covers the comments that always stay: todos, license headers, security boundaries, workarounds, and references to an external spec. Apply on every code change, not only when asked to clean up comments.
Review a shipped diff for quality and whether it matches the request. Quality checks use /taste and /architecture (keep it simple, keep jobs apart, honest names, trust the server, types tell the truth, and related rules), a correctness hunt for reachable bugs, plus a pass for stale file and symbol names after renames, mixed-parent file dumps, and new env synonyms (`FRONTEND_URL` when `SITE_URL` already exists). Parallel Standards and Spec Tasks, evidence-backed findings, and a bounded fix path. Use for branch, PR, or parent-owned review. User must invoke (not auto).
Analyze text content using both traditional NLP and LLM-enhanced methods. Extract sentiment, topics, keywords, and insights from various content types including social media posts, articles, reviews, and video content. Use when working with text analysis, sentiment detection, topic modeling, or content optimization.
Use this skill to create or refresh a content strategy with pillars, topic clusters, buyer-stage keyword mapping, priorities, and an editorial calendar. Trigger it when planning what a company should publish and why, before drafting individual pieces.
Guide for Convex performance optimization including denormalization, index design, avoiding N+1 queries, OCC (Optimistic Concurrency Control), and handling hot spots. Use when optimizing query performance, designing data models, handling high-contention writes, or troubleshooting OCC errors. Activates for performance issues, index optimization, denormalization patterns, or concurrency control tasks.
Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management, custom tools, streaming, hooks, MCP servers, BYOK providers, session persistence, custom agents, skills, and deployment patterns. Requires GitHub Copilot CLI installed and a GitHub Copilot subscription (unless using BYOK).
When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution
Provides comprehensive guidance for Cypress end-to-end testing including commands, assertions, component testing, CI/CD integration, and best practices. Use when the user asks about Cypress, needs to write E2E tests, component tests, or configure Cypress for testing.
Review fetched papers and write evidence-based recommendations with reading priorities. English triggers: "review fetched papers", "generate paper recommendations". This is pipeline stage 2. 论文点评（3 步流水线的第 2 步）。读取富化后的论文数据，扫描笔记库，生成有态度的推荐点评，保存推荐文件到 Obsidian，更新 history；git 自动化默认关闭。触发词："论文点评"、"跑一下论文点评"
Data export to CSV, Excel (XLSX), and JSON. ExcelJS, SheetJS (xlsx), Papa Parse, Apache POI (Java), openpyxl (Python). Streaming exports for large datasets. USE WHEN: user mentions "export CSV", "export Excel", "XLSX generation", "download spreadsheet", "ExcelJS", "SheetJS", "Papa Parse", "data export" DO NOT USE FOR: PDF generation - use `pdf-generation`; file upload/download - use `file-upload`/`cloud-storage`
ASP.NET Core Data Protection API patterns for encryption, key management, and secure data handling in web applications. Use when protecting sensitive data at rest or in transit, managing encryption keys in ASP.NET Core applications, or implementing secure token generation and validation.
Databricks AI Runtime, the `databricks air` CLI commands for submitting and managing GPU training workloads on Databricks serverless compute. Use for: writing and submitting `databricks air` workload YAML, passing hyperparameters and secrets, checking run status, listing/cancelling runs, streaming a run's logs and watching its progress, custom Docker image setup, and environment configuration
Audit relational schema normalization — 1NF through 3NF violations, repeating groups and CSV-in-a-column, partial and transitive functional dependencies, and the inverse trap of premature or undisciplined denormalization. Module M1. Feeds the Design & Integrity score (Modelado category).
Use when drawing or auditing model boundaries — phrases like "bounded context", "where do we draw the line between X and Y", "this model is getting muddled", "should this be one service or two", "the same word means different things in different places". Defines what a bounded context is, what it isn't, and the signals that say a boundary should exist. Pairs with ddd-context-mapping for the relationships across boundaries.
Provides comprehensive guidance for DDD in microservices including bounded contexts, service boundaries, event-driven architecture, and microservice patterns. Use when the user asks about DDD microservices, needs to design microservices with DDD, or implement microservice architectures.
Use when the user wants to transform existing code toward DDD — phrases like "refactor this to use aggregates", "extract a value object from this primitive", "split this god aggregate", "make this domain model less anemic", "introduce a bounded context boundary here". Sequences refactor steps and points at the pattern skill that explains the target shape. Do NOT use for code review (route to ddd-review) or initial design (route to ddd-design).
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when: standard troubleshooting fails, systematic root cause analysis needed, complex bugs, mysterious errors.
Find deepening opportunities in a codebase, surfacing architectural friction and proposing refactors that turn shallow modules into deep ones. Use when the user wants to improve architecture, make a codebase more testable, consolidate tightly-coupled modules, or make it safer for AI agents to navigate and change.
Implement applications using Google Cloud Platform (GCP) services. Use when building on GCP infrastructure, selecting compute/storage/database services, designing data analytics pipelines, implementing ML workflows, or architecting cloud-native applications with BigQuery, Cloud Run, GKE, Vertex AI, and other GCP services.
cuTile Python DSL kernel implementation patterns, CtKernel runtime wrapper, suitability gate, and cuTile-specific pitfalls. Use when: (1) creating or modifying a cuTile Python DSL kernel version, (2) implementing an optimization that still fits within cuTile's exposed control surface, (3) deciding whether cuTile is still the right DSL, (4) reviewing cuTile-specific runtime patterns. Always also load /design-kernel for shared naming, versioning, and workflow.
Design an interaction flow with inclusive input and output options from the start. Chains: multi-modal-input, keyboard-navigation, touch-target-design, feedback-and-status. Use when designing a new feature, flow, or interface and you want to build inclusive interaction in from the beginning.
Shared kernel design workflow across all supported languages and DSLs. Provides language selection table, naming conventions, versioning rules, KernelPlan structure, composition patterns, clone workflow, implementation workflow, devlog template, and designer output contract. Use when: (1) choosing which language-specific kernel design skill to load, (2) the intended implementation language is not fixed yet, (3) you need naming or versioning guidance before selecting a DSL, (4) you are implementing any kernel regardless of DSL, (5) you are updating docs that refer to kernel design skills.
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.