Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Comprehensive assistant for the full Xilinx toolchain, covering complete zero-to-one FPGA/MPSoC project builds, including: - Vivado: hardware design, Block Design, IP configuration, XDC constraints, synthesis and implementation, bitstream generation - Vitis HLS: C/C++ high-level synthesis, generating custom IP cores - Vitis Unified IDE (2022.x+): embedded software development, Platform/Domain/Application creation, XSCT scripts - PetaLinux: embedded Linux system builds, BSP configuration, kernel/rootfs customization, boot image generation - Device support: Zynq UltraScale+ MPSoC (full EG/EV range and ZCU10x evaluation boards), Versal, pure FPGA (UltraScale+/UltraScale/7 series) Whenever the user mentions any of the following, use this skill immediately: vivado, vitis, hls, high-level synthesis, vitis_hls, petalinux, zynq, ultrascale, fpga, mpsoc, xsa, bitstream, block design, synthesis, implementation, xdc, constraints, IP core, AXI, embedded software, bare-metal programs, linux image, bsp, device tree, jesd204, jesd204b, jesd204c, 204b upgrade to 204c, 204b migration, high-speed serial, DAC, ADC, AD9144, AD9250, AD9680, grpc, protobuf, rpc, remote calls, host-computer communication, petalinux grpc, embedded rpc, zmq migration to grpc, udmabuf, axi dma host computer. Please proactively use this skill whenever the user describes any Xilinx/AMD FPGA hardware or software design task.
A knowledge base of web/JS reverse-engineering case studies distilled from all 42 articles on 1997.pro. Applies to case leads such as Akamai/Kasada/PX/reese84/同盾/a_bogus/腾讯滑块/阿里滑块/JSVMP/227/226/wasm/protobuf/rid/fuid/fs/bx-pp/run_js/storage.estimate/animationend, as well as scenario assessment, method routing, and case comparison for risk-control fingerprints, environment patching, JSVMP/flat flow/WASM, CAPTCHAs, and protocol parameter chains; used by default together with web-js-reverse-master-flow and the three MCPs jshook + js-reverse + chrome-devtools-mcp.
Inspect an existing project to discover implicit architectural decisions and propose candidate ADRs. Use when the user wants to audit a repository for undocumented decisions, asks to "descubrir ADRs", "qué decisiones arquitectónicas tiene este proyecto", "busca ADRs en el repo", "analiza la arquitectura del proyecto", or any variant that involves exploring the code/structure to infer relevant decisions that deserve an ADR. Also trigger when the user arrives at a new project and wants to understand what decisions have already been made, even if they don't explicitly mention "ADR".
Build realtime voice / live audio agents with AG2's `ag2.live` module. Wrap a prompt + provider config in `LiveAgent` and open a bidirectional voice session with `agent.run()`, pumping mic audio in and playing synthesized speech out. Covers the two realtime providers — Gemini Live (`GeminiRealTimeConfig`) and OpenAI Realtime (`OpenAIRealTimeConfig`) with audio/text output modalities, voices, and user-speech transcription; audio I/O over the local sound card (`SoundDeviceRecorder` / `SoundDevicePlayer`, both sounddevice-backed); one-shot speech-to-text (`OpenAITranscriber`, `OpenAITranslationTranscriber`) and its `.pipe(agent)` voice pipeline; text-to-speech (`OpenAITTSConfig`); and `TTSObserver`, which speaks a regular text `Agent`'s streamed tokens aloud. Use when the user wants a talking agent, a phone/voice assistant, live transcription, or to add TTS playback to a text agent.
Inter-agent communication patterns including message passing, shared memory, blackboard systems, and event-driven architectures for LLM agentsUse when "agent communication, message passing, inter-agent, blackboard, agent events, multi-agent, communication, message-passing, events, coordination" mentioned.
Use when the request is already narrowed to wiring a model endpoint, env vars, settings-file-based model config, `${ENV.xxx}` placeholders, `auto_load_env=True`, or connectivity check for a model-powered feature, including local Ollama, dotenv-loaded DeepSeek or other OpenAI-compatible settings, plugin namespace placement, auth, request options, and minimal verification.
Use when the user is shaping how one model request or request family should be instructed or templated, including prompt slots, input/instruct/info layering, mappings, recursive placeholder injection, prompt config, YAML or config-file-driven prompt behavior, and reusable prompt structure.
Build React frontends for LiveKit voice AI agents. Use this skill when creating web interfaces for voice assistants using LiveKit's shadcn-based Agents UI components. Covers AgentSessionProvider, audio visualizers, media controls, chat transcripts, and customization with Tailwind CSS.
Writing or reviewing code that handles untrusted input, secrets, outbound requests, rendered content, or third-party dependencies — the OWASP Top 10:2025 lens in two modes, writing secure-by-default code and judging the risk a change introduces. Triggers on "is this safe", "secure by default", "harden", "security", "secret", "privacy", "PII", "XSS", "injection", "SSRF", "safe fetch", "access control", or a dependency review. Covers secrets and environment variables, input validation, output encoding, SSRF, access control and data exposure, and supply-chain risk.
Reviews any arc42 section or the full document for accuracy, completeness, cross-section consistency, and alignment with arc42 standards. Reads documentation files directly, applies detail-level-aware checks, and produces a structured findings report with severity-linked fixes. Offers to resolve Critical issues immediately using the relevant section skill.
Interactively guides the documentation of arc42 Section 9 (Architecture Decisions) using Nygard ADR format extended with toolkit cross-references. Asks about significant decisions, alternatives considered, and consequences before generating structured ADRs. Official arc42 only requires that significant decisions are documented; the Nygard ADR base format and the toolkit cross-reference additions are conventions, not arc42 requirements. Iterates until the user is satisfied.
Use when the user mentions ARCS/arcs-sdk, cross-compilation toolchain (riscv64-unknown-elf-gcc), cskburn, flashing, /dev/ttyACM*, serial logs, JLink, JFlash, GDB debugging, JTAG/cJTAG, debug, breakpoints, single-stepping, and similar tasks: handles cloning repositories, environment setup, compilation, flashing, running, log reading and JLink debug environment deployment; does not handle writing or understanding code, which is Claude Code's own responsibility
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
Automake owns a Git-backed ratchet for safely improving a repository through separate optimizer and evaluator roles: it establishes a baseline, proposes and checks candidates, obtains an independent comparison against the current committed state, keeps accepted changes, and restores rejected ones exactly. It triggers when the request is to prepare or execute this bounded improvement workflow, draft or approve its role instructions, set limits or stop conditions, protect local files, initialize the baseline, or invoke `/automake`. It does not trigger when “automake” refers to the GNU build system, when the task is merely a Makefile target or normal bug fix, when the user only wants code review or an explanation, or when the request is generic branch reset or deleted-file restoration.
Work autonomously on a project without waiting for direction. On command, survey the codebase, pick one high-value low-risk improvement, do it, verify it, commit it, then pick the next, looping like a self-directed intern. Use when the user hands off open-endedly ("work on your own", "keep improving this", "find something worth doing", "don't wait for me", "go autonomous", "run for a while", "be a passionate intern", "do whatever you think is valuable") or invokes /autopilot, and you have to choose the work yourself rather than wait for instructions or feedback.
One-time installer that keeps a project's Internet Computer CLI toolchain current. Sets up a SessionStart hook plus a script that compares the installed `icp` and `ic-wasm` against the latest release and either reports the upgrade or applies it, using whichever channel each tool was installed from (npm, Homebrew, or the shell installer). Use when a user wants to install, bootstrap, or enable automatic icp-cli / ic-wasm updates, asks to stop running an outdated `icp`, asks how to upgrade or check the version of the ICP CLI, or pastes the link to this skill. This is a one-time setup action, not ongoing IC knowledge. Do NOT use for writing icp.yaml, deploying canisters, or other icp-cli usage questions — load `icp-cli` for those.
Scandit Barcode Capture (`BarcodeCapture`) in native iOS (Swift) projects — the low-level, full-control single-barcode scanning mode (BarcodeCapture + DataCaptureView + overlay), without the pre-built SparkScan UI. Use for integration, scan settings, result handling, overlay customization, SDK version migration (v6→v7→v8), replacing a third-party barcode scanner, or troubleshooting.
Use this skill when working with BoxLang's interceptor/event system: creating interceptors, registering announcement points, announcing custom events with announce() or announceAsync(), building pre/post operation hooks, validation interceptors, security guards, or leveraging BoxRegisterInterceptor() BIF for standalone and module-based interception.
Use this skill when installing, configuring, or using BoxLang modules: box install, boxlang.json module settings, BoxLang+ premium modules (bx-pdf, bx-redis, bx-csv, bx-spreadsheet), CFML compatibility, ORM, mail, and module introspection.
Build bulletproof React components that survive SSR, hydration, concurrent rendering, portals, transitions, and future React changes. Nine essential patterns from Shu Ding's guide. Use when writing reusable React components, fixing hydration mismatches, handling SSR edge cases, or building component libraries.
Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
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.