Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Upgrades a Capacitor plugin library from v5 to v6 using `npx @capacitor/plugin-migration-v5-to-v6@latest`, then the manual checklist - `@capacitor/*` dev deps to `latest-6`, `compileSdkVersion` replaced by `compileSdk`, compile/target SDK 34 defaults, AGP 8.2.1, Gradle 8.2.1, Kotlin 1.9.10, plus code changes - `addListener` in `definitions.ts` returns only `Promise<PluginListenerHandle>` (drop `& PluginListenerHandle`), remove `CAP_PLUGIN_METHOD(removeAllListeners, ...)` from the `.m` file, and optional experimental SPM support via `Package.swift`. Use when a plugin targets Capacitor 5 and must support 6. Do not use for app upgrades, other major versions, or non-Capacitor libraries.
Debug applications using the dbg CLI debugger. Supports Node.js (V8/CDP), Bun (WebKit/JSC), Python (debugpy/DAP), Java (JDWP/DAP), and native code via LLDB (DAP). Use when: (1) investigating runtime bugs by stepping through code, (2) inspecting variable values at specific execution points, (3) setting breakpoints and conditional breakpoints, (4) evaluating expressions in a paused context, (5) hot-patching code without restarting (JS/TS), (6) debugging test failures by attaching to a running process, (7) debugging C/C++/Rust/Swift with LLDB, (8) debugging Python via debugpy, (9) any task where understanding runtime behavior requires a debugger. Triggers: "debug this", "set a breakpoint", "step through", "inspect variables", "why is this value wrong", "trace execution", "attach debugger", "runtime error", "segfault", "core dump".
Code refactoring best practices based on Martin Fowler's catalog and Clean Code principles (formerly refactoring). This skill should be used when refactoring existing code, improving code structure, reducing complexity, eliminating code smells, or reviewing code for maintainability. Triggers on tasks involving extract method, rename, decompose conditional, reduce coupling, or improve readability.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
Use this skill when gathering and evaluating evidence for a technical decision, SOTA analysis, or codebase investigation. Activates on mentions of research, investigate, evaluate options, what's the best, compare alternatives, state of the art, deep dive, explore the landscape, or find out how.
Comprehensive React and Vite SPA performance, architecture, and deployment guidelines. Use this skill when building, reviewing, or refactoring React applications built with Vite (SPA). Covers Vite-specific build configurations, static hosting requirements, and core React performance patterns.
You MUST use this when findings from a code review, pull request comments, CI or static-analysis output, or reviewer suggestions need a decision before any fix - a cr-request result, a spec or plan review, or a reviewer's message - in any programming language. Verifies each finding against the current tree, decides accept, reject, partial, defer, or escalate with evidence, fixes only what holds up, records the decisions in the plan's execution record, and routes back to verify. Replaces devflow review-resolution.
Fuzzing skill for automated input-driven bug finding in C/C++. Use when setting up libFuzzer or AFL++ fuzz targets, defining fuzz entry points around parsing or I/O boundaries, integrating fuzzing into CI, managing corpora, or combining fuzzing with sanitizers. Activates on queries about libFuzzer, AFL, afl-fuzz, fuzz targets, corpus management, coverage-guided fuzzing, or OSS-Fuzz integration.
Embedded network debugging tool for discovering interfaces, capturing packets, analyzing pcap/pcapng, running connectivity tests, port scanning and traffic statistics. Automatically triggers when the user mentions Wireshark, tshark, Npcap, packet capture, network integration debugging, port scanning, connectivity troubleshooting, pcap analysis, network interfaces, ping tests, traceroute, traffic statistics, Modbus TCP, EtherNet/IP and other network protocol debugging; it also supports explicit invocation via /net. Even if the user only says "capture a packet and take a look", "scan the ports", "is the network up" or "analyze this pcap", this skill should trigger as long as the context contains a specific tool name (tshark, Wireshark, Npcap), a protocol name (Modbus TCP, EtherNet/IP, ICMP, etc.), a debugging action (packet capture, port scanning, connectivity test, ping, traceroute, traffic statistics, pcap analysis) or a network interface operation.
Comprehensive guide for maintaining, debugging, and upgrading the memory-lancedb-pro OpenClaw plugin — an enhanced LanceDB-backed long-term memory system with hybrid retrieval (Vector + BM25), cross-encoder reranking, multi-scope isolation, noise filtering, adaptive retrieval, and a management CLI. Use this skill when: (1) developing new features or fixing bugs in memory-lancedb-pro, (2) modifying the retrieval pipeline (vector search, BM25, RRF fusion, reranking, scoring stages), (3) adding or changing embedding providers, (4) updating scope/access control logic, (5) modifying agent tools or CLI commands, (6) troubleshooting memory quality issues (noise, duplicates, low recall), (7) working on the JSONL session distillation pipeline, (8) migrating data between memory backends, or (9) understanding the plugin's architecture to plan enhancements.
Comprehensive NetSuite SDF best practices based on the SAFE Guide (12 principles + appendices). Generates Object XML for all 14 script types, enforces governance limits, security patterns, and defensive coding. Includes N/cache, N/query, concurrency limits, OAuth 2.0 guidance, legacy TBA guardrails, CustomTool runtime patterns, REST Web Services (2026.1 features), and 140+ documented pitfalls. Essential for SuiteApp and Account Customization development
Clean Code for TypeScript — code smell catalogs (Martin's per-line heuristics, Fowler's change-shape smells, TypeScript-native type smells), a linter-first detection policy, and step-by-step review, refactoring, TDD, and estimation workflows. Use when the user: - Writes, reviews, or refactors TypeScript/JavaScript code, or asks whether code is clean, maintainable, or well-designed - Names a smell — Shotgun Surgery, Feature Envy, Data Clumps, Long Method, Divergent Change, Duplicated Code, Large Class, Long Parameter List, Primitive Obsession, Message Chains, Dead Code, Speculative Generality, god class, copy-paste, stringly typed, premature abstraction - Asks about TypeScript type hygiene — `any` leakage, `as` assertions, non-null `!`, discriminated unions, exhaustiveness, strict flags, branded types - Asks what to enforce with lint or tsconfig versus what needs judgment, or names knip, jscpd, dependency-cruiser, typescript-eslint, type-coverage - Runs TDD, fixes a bug with test coverage, or plans test strategy - Estimates tasks, negotiates a deadline, or works through a commitment or team problem
DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.
eBPF skill for Linux observability and networking. Use when writing eBPF programs with libbpf or bpftrace, attaching kprobes/tracepoints/XDP hooks, debugging verifier errors, working with eBPF maps, or achieving CO-RE portability across kernel versions. Activates on queries about eBPF, bpftool, bpftrace, XDP programs, libbpf, verifier errors, eBPF maps, or kernel tracing with BPF.
MSVC cl.exe and clang-cl skill for Windows C/C++ projects. Use when configuring Visual Studio builds, MSBuild, or clang-cl as a drop-in MSVC replacement. Covers translating GCC/Clang flags to MSVC equivalents, runtime library selection, Windows SDK setup, and diagnosing MSVC-specific errors. Activates on queries about cl.exe, clang-cl, /O flags, /MT vs /MD, PDB files, Windows ABI, or MSVC project settings.
Explore a website once, find the stable data path, and deploy it as a reusable, parameterized Notte Function (a callable HTTP endpoint that can be scheduled and run at scale). Use when a user wants to build, create, generate, or “bake” a reusable scraper or browser automation for a site, turn a working scrape into an API/endpoint/job, or says things like “I'll run N keywords later”, “make this reusable”, “pull all listings”, “automate this site every day”, or “build a function that extracts X from Y”. Pairs with notte-functions-doctor, which repairs a built Function when the site changes.
Use this skill when surfacing cancellation, pause, and winback state on Android with RevenueCat. Covers reading unsubscribeDetectedAt, billingIssuesDetectedAt, pause state via periodType, managementURL for deep link, and pause resume date lookup via the REST API.
Build WebGPU visual effects with the Shaders component library (npm `shaders`) in React, Vue, Svelte, Solid or vanilla JS. Use when a user asks for a shader, animated background, gradient, aurora, blur, glass, distortion, noise, particles, glow, transition, cursor effect, or any GPU-rendered visual on a web page, or mentions shaders.com, the Shaders CLI, presets, or the design editor.
Build, revise, debug, and verify browser-based Three.js apps and games, asset viewers, model and asset pack deliveries, material and material pack deliveries, animated model viewers, and explicitly requested Gaussian splat worlds, with Mint MCP as the production asset pipeline.
Use when the user mentions "analyze the project", "analyze the repository", "analyze GitHub", "project analysis", "source code analysis", "architecture analysis", "code analysis", "study this project", "research this framework", "see how this library is implemented", "compare two projects", "project review", or "framework review"
Build type-safe D1 databases with Drizzle ORM. Includes schema definition, migrations with Drizzle Kit, relations, and D1 batch API patterns. Prevents 18 errors including SQL BEGIN failures, cascade data loss, 100-parameter limits, and foreign key issues. Use when: defining D1 schemas, managing migrations, bulk inserts, or troubleshooting D1_ERROR, BEGIN TRANSACTION, foreign keys, "too many SQL variables".
Guides Material UI theming and design tokens (createTheme, ThemeProvider, palette, colorSchemes, cssVariables, theme.vars, dark mode, TypeScript augmentation). Use when building or extending a theme, toggling light/dark, or aligning tokens across an app.
Zero-downtime migration planning, compatibility validation, and rollback strategy generation. Tools for system, database, and infrastructure migrations with minimal business impact. Use when planning a database migration, infrastructure cutover, system replacement, or any high-risk transition that needs explicit rollback paths.
A probe-rs download and debugging tool for probe discovery, firmware flashing, reset, memory read/write, GDB Server debugging and RTT log reading. Automatically triggered when the user mentions probe-rs, cargo-embed, DAP, RTT, CMSIS-DAP, ST-Link, J-Link, flashing, chip info, connect under reset, probe selectors, probe-rs gdb, probe-rs attach, and also supports explicit invocation via /probe-rs. Even if the user only says "flash it with probe-rs", "check the RTT" or "grab a backtrace", this skill should be triggered whenever the context clearly refers to probe-rs features, CLI commands or related terms (e.g. cargo-embed, RTT, probe-rs flash).
Use when auditing a codebase for semantic duplication — functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases, where new functions are often created rather than reusing existing ones.
Building worlds with code - parts, models and pivots, materials, Lighting (LightingStyle, Atmosphere, post-processing), day/night, Terrain API, in-game CSG and destruction (GeometryService Subtract/Union/Fragment), ProceduralModel, EditableMesh/EditableImage, particles/beams/trails/highlights. Use when creating maps, environments, lighting, destructible objects, procedural levels, or visual effects.
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
Session wrap-up. Use when Ane types /wrap-up to close a session. Gathers git, errors, and pending actions, delivers a concise status report, then commits and pushes pending work, and offers opt-in post-commit follow-ups (skill improvements, skill-fit signals, learning capture). Pass "report" for a read-only status with no commit. Writes a continuation handoff prompt for the next session whenever named work is still open, one file per workstream so parallel sessions cannot overwrite each other; pass "continue" to force one.
Build web interfaces with genuine design quality, not AI slop. Use for any frontend work—landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done
Use when the user wants to build, test, publish, or manage iPaaS (Advanced Automations) flows: multi-step integrations with external apps (Slack, Gmail, Google Sheets), incoming webhooks, schedules, routers, code steps, or iPaaS data tables. Driven through a per-pipe catalog discovered at runtime. For native if/then rules or prompt-driven AI automations, use `pipefy-automations` instead.
Run a coding agent in an autonomous loop via a /ralph command, gated by a preflight check that every CLI is installed, linked, and authenticated. Use when driving long-running autonomous development from a wide, outcome-focused prompt.
Upgrades a Capacitor plugin library from v6 to v7 using `npx @capacitor/plugin-migration-v6-to-v7@latest`, then the manual checklist - dev deps `^7.0.0` and peer `@capacitor/core` `>=7.0.0`, tooling bumps (eslint, swiftlint, prettier 3 with prettier-plugin-java, rollup 4 with `rollup.config.mjs`, rimraf 6, docgen 0.3), minSdk 23 and compile/target SDK 35 defaults, AGP 8.7.2, Gradle 8.11.1, Java 21, Kotlin 1.9.25, iOS 14 in podspec and `Package.swift`, pinned `capacitor-swift-pm` `from: "7.0.0"`, plus removed APIs - `call.success()` / `call.error()` (use `resolve` / `reject`), `registerWebPlugin`, `Capacitor.platform` / `isNative`, Android `BridgeFragment`. Use when a plugin targets Capacitor 6 and must support 7. Do not use for app upgrades, other major versions, or non-Capacitor libraries.
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.