░▒▓███████▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░
░▒▓█▓▒░ ░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓█▓▒░ ░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓██████▓▒░░▒▓███████▓▒░░▒▓████████▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░
░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓███████▓▒░░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░░▒▓██████▓▒░░▒▓███████▓▒░
Discover AI Agent Skills
Find, share, and deploy reusable skills for your AI agents
npm i -g skhub
Imagine your project has failed spectacularly—then work backward to identify why. Apply Gary Klein's "prospective hindsight" technique to catch failures before they happen. Use when: **Before launching** a product, campaign, or major initiative; **Before making** an important decision (hiring, investment, partnership); **Starting a project** to identify risks the team hasn't considered; **When overconfident** and everyone agrees the plan is great; **Before committing resources** to a signific...
00
Determine whether front/side/back/top reference templates can be satisfied by one rigid 3D Blender model, choose a canonical source policy, and emit constraints before rebuilding. Use when multiview bboxes, silhouettes, part counts, or depth ratios contradict each other.
00
Expert in product discovery - the continuous process of understanding what customers need and what solutions will work. Covers customer research, problem validation, solution testing, opportunity assessment, and reducing risk before committing resources. Knows the difference between discovery and delivery, and how to maintain continuous discovery habits. Use when "product discovery, customer research, problem validation, what to build, opportunity, user research, customer interview, " mentioned.
00
在构建 MCP 服务器或 MCP 工具时使用 —— 系统化的生产级 MCP 构建方法论，覆盖工具设计、错误处理、传输层选择与测试，让 AI 助手连接外部能力
00
Expert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior. Covers code smells, composing methods, moving features, organizing data, simplifying conditionals, method calls, and generalization. Triggers on: refactor, 重构, clean up, improve code, code smell, extract method, rename, simplify.
00
Show all Linear issues assigned to you
00
Token security: Indexing tokens have write access -- never expose in frontend.
Trigger: "glean security basics", "security-basics".
00
Build and deploy applications on inference.sh. Use when getting started, understanding the platform, creating apps, configuring resources, or needing an overview of inference.sh app development. Supports both Python and Node.js. Triggers: inference.sh app, belt app, inf.yml, inference.py, inference.js, deploy app, app development, build app, create app, GPU app, VRAM, app resources, app secrets, app credentials, multi-function app
00
Meeting preparation and template setup in Granola — templates, recipes, and pre-meeting workflows.
Use when configuring note templates for 1:1s, standups, discovery calls, or sprint planning,
creating custom recipes, or preparing agenda notes before important meetings.
Trigger: "granola template", "granola meeting prep", "granola recipe", "granola agenda".
00
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
00
AI agent with tools (search, calculator) using LangGraph and AI SDK.
00
Draft explanatory author notes for the user's own PR or local diff. Use for self-review or reviewer context; posting requires approval.
00
把 plan、spec 或当前对话拆成一组 tracer-bullet tickets，每个 ticket 声明 blocking edges，并发布到已配置的 tracker；本地用每 ticket 一个文件中的文本 edge，真实 tracker 用 native blocking links。
00
Control Home Assistant smart home devices through AI assistants using the Model Context Protocol
00
Make an evidence-backed go-live decision for installation, configuration, governance, security, continuity, and operations. Use when this operator task needs a current, evidence-backed CodeRabbit workflow. Trigger with "review CodeRabbit go-live".
00
Use when designing animations for medical apps, patient portals, telehealth, or health tracking interfaces
00
Use when the user asks to perform security audits, penetration testing, vulnerability scanning, OWASP Top 10 checks, or offensive security assessments. Covers static analysis, dependency scanning, secret detection, API security testing, and pen test report generation.
00
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.
00