Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Diagnose PostHog Surveys configuration and responses across all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Surveys support ticket is pasted ("survey not showing", "fewer responses than expected", "responses disappeared", "responses are incomplete", "only the first question was answered", "the user says they didn't mean to submit", "survey shows on wrong platform"), or when diagnosing why a survey does or doesn't display. Covers the eligibility pipeline, how a response actually gets stored (partial responses, branching, optional questions, auto-submit), cross-SDK feature parity, the known-cause catalog, read-only diagnostic queries, staff access, and the customer-reply style guide.
Filter degenerate, uninformative inputs before statistical tests: single-sequence alignments, empty files, constant features, zero-variance inputs, all-NaN columns. See nan-safe-correlation for NaN-aware correlation; statistical-analysis for test guidance.
Design and implement Azure cloud architectures using best practices for compute, storage, databases, AI services, networking, and governance. Use when building applications on Microsoft Azure or migrating workloads to Azure cloud platform.
Designer and customer-experience worker for user-facing UI. Owns docs/design.md (the app UX source of truth), captures the app from code, and implements screens, components, and visible copy to a finished professional bar in one pass. Use when building frontend, initializing or updating design.md, translating UI copy, locale files, English or French strings, or the user talks about UX, clicks, keystrokes, or how a screen should feel.
Read and parse DLIS (Digital Log Interchange Standard) and LIS (Log Information Standard) well log files. Use when the agent needs to: (1) Read/parse DLIS or LIS files, (2) Extract well log curves as numpy arrays, (3) Access file metadata and origin information, (4) Handle multi-frame or multi-file DLIS, (5) Convert DLIS to LAS or DataFrame, (6) Work with RP66 format well logs, (7) Process array or image log data.
Docker containerization expert: Dockerfile optimization, multi-stage builds, security hardening, Docker Compose orchestration, and production deployment. Use for Dockerfile creation/review, image size issues, container security, networking, and orchestration.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
A complete guide to ASP.NET Core WebApi integration testing. Use when you need to integration test WebApi endpoints or validate ProblemDetails error formats. Covers WebApplicationFactory, IExceptionHandler, Testcontainers multi-container orchestration, Flurl URL building, and AwesomeAssertions HTTP validation. Keywords: webapi integration testing, WebApplicationFactory, asp.net core integration test, WebApi integration testing, IExceptionHandler, ProblemDetails, ValidationProblemDetails, AwesomeAssertions, Flurl, Respawn, Be201Created, Be400BadRequest, multi-container testing, Collection Fixture, global exception handling.
Drizzle ORM — type-safe, lightweight TypeScript ORM for SQL databases. Schema declaration, CRUD queries, joins, relations, migrations with Drizzle Kit, and database seeding. Use when defining database schemas, writing queries (select/insert/update/delete), setting up migrations, configuring drizzle.config.ts, establishing database connections, validating data with drizzle-zod/valibot, or working with PostgreSQL, MySQL, SQLite, Turso, Bun SQL, Neon, Supabase, PGlite, Expo SQLite, Cloudflare D1, PlanetScale, SingleStore, MSSQL, CockroachDB.
Parse local DrugBank XML for drug info, interactions, targets, and properties. Search by ID/name/CAS, extract DDIs with severity, map targets/enzymes/transporters, compute SMILES similarity. Primary via local XML; REST API rate-limited (3k/month dev). For live bioactivity use chembl-database-bioactivity; for compound properties use pubchem-compound-search.
An analytical in-process SQL database management system. Designed for fast analytical queries (OLAP). Highly interoperable with Python's data ecosystem (Pandas, NumPy, Arrow, Polars). Supports querying files (CSV, Parquet, JSON) directly without an ingestion step. Use for complex SQL queries on Pandas/Polars data, querying large Parquet/CSV files directly, joining data from different sources, analytical pipelines, local datasets too big for Excel, intermediate data storage and feature engineering for ML.
Critique and improve academic writing at the paragraph level, or produce new academic paragraphs from scratch. Use this skill whenever the user pastes academic text and wants feedback, revision suggestions, or a rewrite; when they ask to "improve this paragraph", "critique my writing", "make this more academic", "help me write a paragraph about X", or asks for academic prose with a specific argument. Also trigger when the user provides a topic, claim, or rough notes and wants them shaped into a polished academic paragraph. Always use for academic writing tasks — even if the request is phrased casually.
OpenClaw configuration optimization wizard. Follows a flow of "layer 0 test observation (optional) + first 3 rounds of optimization + round 4 onboarding and extension": baseline recommendation layer (including web search and permission mode), channel enhancement layer (Discord/Feishu/Telegram branch optimization), Skills recommendation layer (executable or skippable), new channel onboarding guidance (skippable). Used to help users quickly complete OpenClaw initialization or configuration optimization. Triggered when the user says "优化 openclaw", "配置向导", "openclaw 初始化", "体验太差想一键整理配置" and similar.
Finds non-obvious corner cases of a task through the intersection of states, data, order of actions, failures, and concurrent changes; turns them into expected behaviour and verifiable scenarios. Use before implementing or reviewing a non-trivial product, UX, or technical task; when stateful/async behaviour, persistence, synchronisation, permissions, integrations, and multi-step flows change; when the user asks to think through edge cases, corner cases, extreme cases, or to check the completeness of the requirements. Do not use for small mechanical edits or before choosing the task itself or the scope of the solution — run nodumb first.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Pattern for wrapping third-party SDK clients (Stripe, Resend, AWS, etc.) with Effect. Use when creating Effect services that wrap external libraries with Promise-based APIs. Provides type-safe error handling, automatic tracing, and clean dependency injection via the "use" pattern.
Senior embedded debugging expert. Defaults to Classic AUTOSAR on ARM Cortex-M/R targets and operates in two modes: (1) Problem-report triage — take a field PR / bug ticket and produce symptom classification, affected-element mapping, ranked hypotheses, data-collection plan, and step-by-step investigation; (2) Targeted fault debugging — accept a specific fault signature (watchdog reset, HardFault, wrong output value, Dem event, stack overflow, AUTOSAR OS error, linker hang) and give concrete debugging steps with GDB/TRACE32 commands, code patterns to inspect, ranked root-cause candidates, and a minimal reproduction strategy. Covers AUTOSAR OS (EB Tresos, Vector) and common BSW/RTE failure modes. Handles Adaptive AUTOSAR when the input names POSIX/Linux/QNX, ara::, C++, segfault, core dump, or Execution Management. Returns decision-ready ranked hypotheses with a built-in self-check and can emit a self-contained HTML report under analysis/.
Read, write, and process Excel workbooks (.xlsx/.xlsm/.xls). Use for creating, reading, searching, and editing spreadsheet data; generating reports; handling workbooks with multiple sheets; writing formulas, formatting, and charts; and converting between xls/xlsx/csv formats. Use this skill when the user mentions Excel, xlsx, xls, spreadsheets, report exports, or format conversion.
This skill MUST be used for experiential and guerrilla marketing strategy, creative activity design, and campaign evaluation. MUST trigger on 體驗行銷、游擊行銷、快閃活動、品牌體驗、沉浸式品牌體驗、體驗與游擊整合, or natural-language requests for brand activities that invite participation, photo sharing, or creative attention on a limited budget. Users need not name the skill or its frameworks. SHOULD be used when improving an existing brand activation's participation, experience, or results. MUST NOT trigger solely on generic 行銷 KPI or low-budget advertising without an experiential or guerrilla activity context.
Designs fast, reliable validation experiments with hypothesis, method, success metric, and decision rules (Ship/Iterate/Kill). Use when you need to validate an assumption or test a product hypothesis before committing resources.
Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how is my MCP doing?", "what should I look at?", "explore my tool calls", "who uses my MCP tools?", "what are agents doing with the MCP?", or pastes an MCP analytics URL without a specific question. Offers a menu of questions, each backed by a query tool, then hands off to the focused skill.
Provides comprehensive guidance for FastAPI framework including routing, request validation, dependency injection, async operations, OpenAPI documentation, and database integration. Use when the user asks about FastAPI, needs to create REST APIs, or build high-performance Python web services.
Provides comprehensive guidance for Fastify framework including routing, plugins, schemas, hooks, and performance optimization. Use when the user asks about Fastify, needs to create high-performance Node.js applications, implement Fastify plugins, or optimize API performance.
Retrieve clean markdown from URLs when web_fetch fails. Converts pages via Jina AI reader service with automatic retry. Use when web_fetch or curl returns 403, blocked, paywall, timeout, JavaScript-rendering errors, or empty content or user explicitly suggests using jina.
Capture a rendered local web page or app screen into the clipboard for pasting into Figma using the official html-to-design capture.js flow. Use when the user invokes /figma-capture, asks to copy the current browser page to Figma, asks for a dev-only Figma capture button, or asks whether figma_key/captureId is needed for Figma HTML capture.
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.