Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
ARM architecture reverse engineering (non-Android): Cortex-M/A vector tables, Thumb/ARM switching, AAPCS calling convention, position-dependent code relocation, and MMIO peripheral register cross-referencing. Trigger terms: ARM, arm32, Cortex-M, Cortex-A, Thumb, AAPCS, embedded reverse engineering, bare-metal firmware, stm32, vector table.
Reverse engineering modern consoles and retro platforms: Switch NSO/NPDM containers and encrypted partitions, PS4/PS5 ORBIS structures, SDK library fingerprints; retro ROM headers, cartridge formats, saves, and Cheat codes. Trigger terms: console reverse engineering, Switch, NSO, NPDM, PS4, PS5, ORBIS, Xbox, retro, ROM, NES, GBA, emulator, Cheat.
eBPF program reverse engineering and adversarial analysis: BPF-64 instruction set, progs/maps relationships, bpftool disassembly, and three use cases: tracing and forensics, malware samples, and EDR evasion. Trigger terms: eBPF, BPF, bpftool, bcc, libbpf, xlated, BPF instructions, bpf hook, EDR evasion, tracepoint, kprobe.
MIPS architecture reverse engineering and router firmware analysis methodology: delay slots, $gp calling convention, endianness determination, and httpd identification. Triggers: MIPS, mipsel, router firmware, embedded, delay slots, big-endian, big-endian, little-endian, httpd, busybox
RTOS structure analysis: runtime model identification for FreeRTOS/ThreadX/Zephyr/RT-Thread/VxWorks/QNX/RTEMS/NuttX/eCos/µC-OS/SYS-BIOS/SAFERTOS/CMSIS-RTX5/T-Kernel/TOPPERS/OSE/INTEGRITY/ARINC 653/PikeOS/Deos, task table and TCB identification, kernel object recovery, and task-by-task decompilation. Triggers: RTOS, FreeRTOS, ThreadX, Zephyr, VxWorks, QNX, RTEMS, NuttX, eCos, µC/OS, Micrium, SYS/BIOS, SAFERTOS, CMSIS-RTX5, T-Kernel, TOPPERS, ITRON, OSE, OSEck, Nucleus, INTEGRITY, ARINC 653, PikeOS, VxWorks 653, Deos, task table, TCB, firmware scheduling, MCU firmware, confdefs, devicetree, DKM, resource manager, FromISR, DSR, OSIntEnter, Swi, Hwi, module preamble, upper half, partition scheduling, major frame, Safety Class
React Native and Expo patterns for navigation, data fetching lifecycle, infinite scroll lists, form handling, state persistence, authentication routing, gesture-driven animations, bottom sheets, push notifications, and OTA updates. Use when building Expo/React Native apps that need data prefetching without route loaders, auth guard routing, infinite scroll with FlashList, gesture-driven animations, or native platform integration (push notifications, OTA updates, MMKV persistence). Do not use for React web apps.
Web-specific React patterns for type-safe file-based routing, route-level data loading, server-side rendering, search param validation, code splitting, and list virtualization. Use when building React web apps with route loaders, SSR streaming, validated search params, lazy route splitting, or virtualizing large DOM lists. Do not use for React Native apps — use react-native-advanced instead.
Generate a portfolio-grade README.md for GitHub projects. Use for requests such as "write a README for me", "generate a README", "improve the README", "README best practices", "project homepage", "open source description", "README infographic", "README cover", or "generate README images with Codex Image Gen / gpt-image-2". Output includes a restrained README narrative, up to two high-quality visual assets, compressed images, an MIT license, GitHub Description and Topics recommendations, a recommended star count, and optional gh CLI update suggestions. The focus is helping the project tell its own story and judging visual intensity based on project type, avoiding boilerplate templates, information dumping and overdesign.
[Hyper] Create or refactor a project README.md by carefully reading the codebase. Detects project shape (CLI, library, web app, monorepo, plugin, framework, docs site, service), entry points, scripts, configuration, license, and existing docs, then produces a structured Korean README by default, unless the user requests another language or an existing README must preserve its current language. Use when the user wants a new README, a refactor of a stale README, or a section update grounded in the actual code.
Generate user-facing release notes from technical change information (commits, PRs, diffs, branch comparisons, or raw text). Goes deep — follows commit references to PRs, issues, and bug reports to understand the full story behind each change, then produces narrative prose that communicates what changed and why it matters. Works with GitHub, GitLab, and Jira. Use this skill whenever the user asks for release notes, changelogs, "what's new" summaries, or wants to communicate changes to users, stakeholders, or customers — even if they just say "write up what changed" or "summarize the release."
Model a requirement/system: extract goals, scope, roles, rules, exceptions, dependencies from PRD, docs, bugs, code; outputs a structured model with clarifications. Not for: writing cases, strategy decisions, the pipeline. 建模需求/系统:从 PRD、文档、Bug、代码提炼目标/范围/角色/规则/异常/依赖。不用于:直接写用例、策略、流水线。
Use this skill when turning a product brief, stakeholder notes, feature idea, client request, or vibe-coded concept into frontend requirements before design or implementation. Produces FR-XX functional requirements, NFR-XX quality constraints, explicit out-of-scope items, dependencies, assumptions, open questions, and a recommended next step.
Reverse engineer undocumented binary network protocols from packet captures and the client that speaks them — recovering framing and field structure, identifying length prefixes, opcodes, checksums and encryption, and building a Wireshark/Kaitai/scapy parser to replay or fuzz. Use when analyzing a proprietary TCP/UDP protocol, a game or IoT or C2 protocol with no spec, or traffic that Wireshark shows only as raw bytes.
Publishes verified changes from rhdh-plugins or community-plugins: detect the repository and affected workspaces, run the repository build pipeline, create package changesets, stage generated files safely, create a signed-off commit and branch, push, open a GitHub pull request, upload optional bug-fix recordings, and link Jira or GitHub issues. Use for raise PR, create or open a plugin PR, push verified plugin changes, or publish a verified change another skill handed off.
Bumps Yarn Berry across the RHDH repos — rhdh-plugins, rhdh midstream, rhdh-plugin-export-overlays, rhdh-cli, and GitLab CEE rhidp/rhdh and rhdh-plugin-catalog — with `yarn set version` plus install, and rewrites the pins Yarn cannot see: `packageManager`, `yarnPath`, `ENV YARN=`, and Containerfile lines. Use for "bump yarn to 4.17.1", "upgrade Yarn Berry across the repos", "weekly yarn bump", "which Yarn version is each repo pinned to", or scanning yarn pins.
Generates CHANGES.md — an operational index of all OpenSpec changes for a project, with dependency tree, parallelism gates, critical path, multi-agent plan, and per-change scope, governance level, dependencies and "Leer antes" pointers to the knowledge base. Fire-and-forget, no questions asked. Trigger: When user asks to create, build, regenerate, or update CHANGES.md, roadmap, change map, implementation plan; or says "armar CHANGES", "armar roadmap", "crear mapa de changes", "generar plan de implementación", "qué changes necesito", "índice de changes".
MNDP (MikroTik Neighbor Discovery Protocol) wire format, behavior, and RouterOS /ip/neighbor integration. Use when: implementing MNDP discovery, parsing MNDP packets, working with /ip/neighbor, understanding WinBox device discovery, debugging why a router doesn't appear in neighbor lists, or when the user mentions MNDP, neighbor discovery, WinBox discovery, or /ip/neighbor.
Use when designing, building, reviewing, or fixing any right-to-left (RTL) user interface—Persian/Farsi (فارسی), Arabic, Hebrew, Urdu—on the web (React, Next.js, Vue, Tailwind, plain CSS) or Flutter, even if the user only says the app is Persian/Iranian without mentioning RTL. Covers layout direction and mirroring, which icons flip and which never do, bidirectional (bidi) text with LTR islands (URLs, emails, phone numbers, code), Persian vs Arabic-Indic vs Latin digits, Jalali (Shamsi) dates, Persian typography (font pairing, line height, the letter-spacing trap, ZWNJ نیمفاصله), font licensing, logical CSS properties, form input direction, and long-text overflow. Also use when Persian/Arabic text renders incorrectly or looks “off,” when localizing an LTR app to RTL, or to audit existing code for RTL violations with the bundled zero-dependency detector. Not for backend-only or non-UI tasks.
Advanced Rust patterns for ownership, traits, async, error handling, macros, type system tricks, unsafe, and performance. Use when tackling complex Rust problems — not basic syntax, but multi-concern tasks like designing cancellation-safe async services, choosing between trait objects and generics, building typestated APIs, structuring error hierarchies across crate boundaries, writing proc macros, or optimizing hot paths with zero-cost abstractions. Do not use for basic Rust syntax, simple CLI tools, or beginner ownership questions.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Create, describe, publish, or babysit GitHub PRs and GitLab MRs through a human merge decision. Make the change, evidence and recovery easy to inspect; handle CI, conflicts and feedback within the requested scope. Exclude independent review verdicts, approval and merging.
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
Comprehensive skill for Sentry error monitoring and performance tracking. Use when Claude needs to (1) Configure Sentry SDKs for error tracking and performance monitoring, (2) Manage releases, source maps, and debug symbols via CLI, (3) Query issues, events, and metrics via API, (4) Set up alerting and notification rules, (5) Configure sampling strategies and quota management, (6) Deploy self-hosted Sentry instances, (7) Integrate with OpenTelemetry for distributed tracing, or any other Sentry automation task.
Serverpod web server (Relic) — REST APIs, webhooks, middleware, static files, server-rendered HTML, SPAs, Flutter web. Use when adding raw HTTP routes, serving web pages or web apps, or intercepting requests. Not for RPC endpoints called from the generated client — use serverpod-endpoints for those.
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.
