Каталог навыков агентов

Agent skill for app-store - invoke with $agent-app-store

Agent skill for arch-system-design - invoke with $agent-arch-system-design

Design agent loops: planning, tool use, subagents, memory, RAG, evals, budgets. Use when building LLM features or multi-...

Agent skill for architecture - invoke with $agent-architecture

Prompt-native architecture patterns, agent orchestration, iteration loops, and state management for autonomous work.

マービン・ミンスキーの『心の社会』に基づくエージェントアーキテクチャパターンと設計原則を適用し、単一責任、創発的複雑性、階層的組織化により、効果的なマルチエージェントシステムを設計します。Anchors:• Clean Architectu...

Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Clau...

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebas...

Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents...

Specialist subagent: Expert audio engineer for recording, mixing, mastering, and sound design

Expert en AudioCraft avancé (MusicGen text-to-music, AudioGen text-to-sound, fine-tuning)

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft....

Validates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when review...

Seal an agent's audit log (JSON lines from a hook, MCP gateway or agent runtime) as a SHA-256 or HMAC hash chain, verify...

Agent skill for authentication - invoke with $agent-authentication

Guide for creating DAAF agent definition files. Covers 12-section template, hook registration, skills-in-frontmatter, in...

Guide for authoring, designing, and building specialized AI agents. Use when creating, updating, reviewing, or improving...

机器学习与人工智能科研子 skill。用于地理学+体育学项目中的 classical ML、深度学习、时间序列、模型评估、数据泄露检查、基线设计、超参数搜索、SHAP/可解释 AI、公平性诊断、实验复现和论文方法写作。触发于 machine...

科研自动化与长期记忆子 skill。用于把 AutoSci/OmegaWiki 的论文摄入、知识库、idea 生成、novelty 检查、实验设计、失败经验、论文计划、review/rebuttal、可视化和进化记录流程转化为本地 Code...

数据分析与科学可视化子 skill。用于 EDA、数据质量审计、统计检验选择、效应量、稳健性分析、表格设计、出版级图件、文献计量图表、政策矩阵、交互式 HTML 仪表盘和论文图注写作。触发于 exploratory data analysi...

地理空间科学与遥感子 skill。用于 GIS、GeoPandas、栅格/矢量处理、CRS 审计、空间连接、缓冲区、网络可达性、OSM、遥感指数、LCZ、热暴露、绿地暴露、空间公平、空间机器学习、地图合规和论文地图设计。触发于 geospa...

研究方法论与批判性思维子 skill。用于研究问题 SMART 化、假设生成、机制框架、实验/准实验/观察研究设计、系统综述方法、证据质量评价、偏倚识别、因果边界、理论贡献、空间正义框架和审稿前风险扫描。触发于 hypothesis gen...

科学交流与学术写作子 skill。用于论文结构、IMRAD、综述写作、图表叙事、英文润色、投稿信、审稿意见拆解、rebuttal、学术海报、PPT、研究汇报、图形摘要和文献引用管理。触发于 scientific writing、paper...

Current state of CI/CD automation infrastructure, pre-built Docker images, and performance optimization strategies. Use...

Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent

停止等待提示词，持续自主工作

Backend Node.js Specialist IA — Expert en développement backend Node.js (Express, Fastify, NestJS, Prisma, real-time, We...

Backend architecture patterns and best practices for scalable server-side applications.

Backend Rust Specialist IA — Expert en développement backend Rust (Actix, Axum, Tokio, zero-cost abstractions, WASM)

生产级 agent 时代后端工程手册(hub)——建 / 评审 agent·LLM 后端、**任何碰 DB 的持久层后端**、或为任何后端建立 / 评审 repo 工程门禁时加载。覆盖架构、prompt、工具(ACI)、记忆、检索/RAG、...

Agent skill for base-template-generator - invoke with $agent-base-template-generator

Full async multi-agent development workflow: Planning → Design → Dev → Security/Tech Review loop with file-based handoff...

Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production....

Agent skill for benchmark-suite - invoke with $agent-benchmark-suite

Command-line task management tool for AI coding agents and humans. Provides local SQLite-based task boards for tracking...

WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration,...

Use when an agent in one harness must create, observe, or steer one or more agents in another harness through a tmux ses...

Write the brief before handing a non-trivial task to an agent or subagent, covering stakes, your own hypothesis, goal an...

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs...

Browser automation for testing and verification. Use when you need to interact with web UIs, verify visual changes, fill...

Use agent-browser for tasks requiring a real rendered browser or supported desktop-app interaction, including navigation...

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screen...

业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type,...

Automatización de navegador para AI agents — navegación, forms, screenshots, testing

CLI-based browser automation with persistent page state using ref-based element interaction. Use when users ask to navig...

Browser automation CLI for AI agents. Use when needs to interact with websites, including navigating pages, filling form...

Browser automation and testing using Vercel's agent-browser CLI with ref-based element targeting

ブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract we...

Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extr...

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs...

Browser automation CLI for AI agents. 5-6x more token-efficient than Playwright MCP. Use for browser testing and web aut...

Browser automation CLI for AI agents. Requires Node.js with agent-browser. Use when the user needs to interact with webs...

Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, na...

Browser automation via agent-browser CLI. Use for web navigation, form filling, screenshots, scraping, login flows, UI t...

Browser automation command reference and usage patterns for web testing, form filling, screenshots, and data extraction.

Headless browser automation for AI agents - auto-installs if needed

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test...

AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying w...

AI代理的浏览器自动化CLI。在用户需要与网站交互时使用，包括导航页面、填写表单、单击按钮、截屏、提取数据、测试Web应用或自动执行任何浏览器任务。触发器包括“打开网站”、“填写表单”、“单击按钮”、“截屏”、“从页面中抓取数据”、“测试此...

Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, c...

credit to Amolith - https://git.secluded.site/agent-skills/blob/main/skills/formatting-commits/SKILL.md

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, fil...

Workflow para testear cambios frontend con agent-browser CLI, validar rutas, contenido UI y regresiones visuales basicas...

浏览器自动化工具，用于网页导航、交互、截图、录制等。当需要自动化浏览器操作、测试网页、抓取网页内容、填写表单、截图、录制视频，或提到「浏览器自动化」「网页测试」「agent-browser」「浏览器操作」时使用。

Use agent-browser for direct CLI browser automation, inspection, web-app testing, screenshots, sessions, and approved pr...

Runs agent-browser to open pages, snapshot refs, click, fill, screenshot, and extract. Use when web tests, forms, or int...

Use when a task involves automating an explicitly scoped browser task with a configured agent-browser tool or equivalent...

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take scre...

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflo...

Operate an agent-browser CLI for auditable navigation, extraction, screenshots, and UI checks.

Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating...

agent-browser CLIを使ったブラウザ操作のガイド。Webページの操作、スクレイピング、スクリーンショット取得などブラウザ自動化が必要なときに参照する。「ブラウザで開いて」「Webページを操作して」「スクリーンショットを撮って」...

Connects to Oxylabs remote agent browsers over the Chrome DevTools Protocol (CDP) with Playwright or Puppeteer. Built-in...

Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and networ...

Automates real browser interactions: navigating websites, clicking buttons, filling forms, taking screenshots, extractin...

Use the host-side `agent-browser` CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation ag...

Native Rust headless browser CLI for AI agents. Automates web UIs, scrapes pages, runs QA tests, and performs structured...

Use Vercel agent-browser for browser automation through a persistent visible Chrome or Chromium CDP session. Trigger whe...

Second browser lane after the active app's built-in browser, through the managed agent-browser CLI; read-only for shared...

Browser automation CLI for AI agents. Use for opening pages, snapshots with @e refs, clicking, filling forms, testing we...

Automate web interactions with agent-browser using Lightpanda by default. Use for navigation, data extraction, form fill...

Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and...

The browser CLI a coding run drives a web page with — opening a URL, clicking through a screen, reading what actually re...

Browser automation via the agent-browser CLI for navigation, interaction, snapshots, extraction, screenshots, network co...

A skill for discovery and implementation with browser-based verification.

Browser automation CLI for AI agents. Use for web scraping, testing, screenshots, form filling, and headless browser int...

Automate headless browser interactions using agent-browser CLI. Use when scraping web pages, automating form submissions...

Fast browser automation via agent-browser (accessibility snapshot + ref-based interaction). Use when automating multi-st...

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selectio...

use when you need to verify code changes preserve UI appearance

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Use this skill to extract page state and automate web interactions with the agent-browser CLI (navigate, snapshot, click...

agent-browser CLI の仕様と使い方に関する知識を提供。ヘッドレスブラウザ自動化、スナップショット、セレクター、セッション管理、ネットワーク制御について回答。Use when user asks about agent-bro...