Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Drives Genie changes through test-first development using genie MCP tools. Works entirely in the live image without files, covering new behavior and bug fixes.
Plan and execute authorized phishing and social engineering campaigns for red team engagements. Use this skill when conducting simulated social engineering attacks including email phishing, spear phishing, vishing, pretexting, and credential harvesting. Covers GoPhish setup, pretext development, payload delivery, and measuring human vulnerability. Requires explicit written authorization before any…
Generate sophisticated initial access payloads designed to bypass email gateways and endpoint antivirus systems while executing Command and Control (C2) agents. Use this skill to craft malicious LNKs, ISOs, Weaponized Office Documents, and HTML Smuggling techniques for Red Team campaigns.
Exploit PHP object serialization vulnerabilities (Insecure Deserialization). This skill details how to identify unserialize() injection points and construct malicious serialized objects using Property Oriented Programming (POP) chains to achieve Remote Code Execution (RCE).
维护 Claude physics 的 LLM Wiki 知识库。适用于整理物理笔记、论文、题目、推导、方法页、论文页和综合讲义页，并将资料沉淀为结构化 Obsidian Markdown 页面。
Verifies that the bead daemon is alive and responds to requests.
Модульная Pino-архитектура для Node.js / Fastify / Next.js: один root logger в infrastructure/logging, child loggers, redaction, requestId, event-поля, JSON в stdout. Use когда внедряешь, аудируешь или обновляешь structured logging, pino, request context, background jobs или Next.js server logs.
screenshot to existing source. Primary owner: UI-to-file trace. Do not use for: new UI generation. Use when this role is selected by the Agent-Vorcl-Flow router.
Шаг 3 конвейера pinpoint (read-only) — определить конкретный контрол (кнопку/поле/иконку) со скриншота и его обработчик в коде (pinpoint). Use when вопрос «что делает вот эта кнопка?»; весь экран → /pinpoint:locate, цепочка логики до API → /pinpoint:trace
Шаг 5 конвейера pinpoint (сам read-only) — собрать точную заявку на правку существующего кода (без новых элементов) и делегировать frontend/backend (pinpoint). Use when картирование сделано и нужна правка чужими руками; сначала найти/понять → /pinpoint:locate|trace
Шаг 1 конвейера pinpoint (read-only) — найти по скриншоту УЖЕ существующие компонент/файл(ы) в проекте, file:line, без генерации нового (pinpoint). Use when вопрос «где этот экран в коде?»; какой это маршрут → /pinpoint:route, конкретный контрол → /pinpoint:control, логика до API → /pinpoint:trace
Шаг 2 конвейера pinpoint (read-only) — определить маршрут/страницу, на которой открыт экран со скриншота (App Router / React Router) (pinpoint). Use when вопрос «какая это страница/URL?»; сам файл компонента → /pinpoint:locate, элемент на странице → /pinpoint:control
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name