Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Performance optimization, API design & compatibility, security vulnerabilities, and standards spec compliance for workerd code review. Covers tcmalloc-aware perf analysis, compat flags, autogates, web standards adherence, and security patterns. Load this skill when reviewing API changes, performance-sensitive code, security-relevant code, or standards implementations.
Memory safety, thread safety, concurrency, and critical detection patterns for workerd code review. Covers V8/KJ boundary hazards, lifetime management, cross-thread safety, and coroutine pitfalls. Load this skill when reviewing any C++ code.
Build and contribute Grommet React components following official team conventions. Use when creating a new component from scratch, refactoring a component to align with Grommet conventions, preparing a PR for Grommet core contribution, or reviewing a component against acceptance criteria. Covers scaffolding, forwardRef, displayName, useThemeValue, FormContext, propTypes, TypeScript declarations, accessibility, i18n, and testing.
Write or edit documentation in this repository under docs/. The site is built with mkdocs-materialx (a fork of mkdocs-material) and navigation is controlled via docs/.nav.yml. Use this skill whenever the user asks you to add, write, edit, restructure, or review any file under docs/ — including new pages, how-to guides, use-cases, design docs, README-style entries inside docs/, and updates to docs/.nav.yml. Trigger even when the user does not explicitly say "mkdocs" or "materialx" — any work that produces or modifies a Markdown file under docs/ should use this skill so the output uses admonitions (not `>` blockquotes for notes), omits manual tables of contents, and takes advantage of mkdocs-material features (tabs, code annotations, mermaid, collapsible blocks, etc.).
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
End-to-end agent for training LTX-2 models. Probes filesystem and GPU, picks the right conditioning mode from the user's intent, prepares the dataset (scenes, captions, references), preprocesses, autotunes, launches, and monitors training. Use when the user wants to train, fine-tune, LoRA, or otherwise produce a custom LTX-2 model.
Use Desktop Commander for terminal and command-line work, especially anything that needs a shell whose state persists across turns: Python/Node REPLs, database shells, dev servers and other long-running processes, SSH into remote machines, and Windows PowerShell. Also handles everyday terminal tasks — navigating folders, choosing the right command for the user's shell (PowerShell, cmd, bash, zsh), running Docker/curl/cloud-CLI commands, inspecting processes and ports, and saving recurring workflows as scripts — even when the user doesn't say "Desktop Commander" or "terminal." Reach for it on pasted errors like "command not found", "permission denied", "EADDRINUSE", "address already in use", "npm ERR!", "ModuleNotFoundError", or "ENOENT", and on intents like "what's using port 3000", "kill that process", "ssh into my server", or "why won't my dev server start". Works on Windows, macOS, and Linux. Never run destructive commands without explicit confirmation.
Doc conventions (impersonal style, formatting, Vitest in examples, structure, linking). Use when writing, editing, or reviewing guides, tutorials, or READMEs.
搜索、发现和安装阿里云 Agent Skills。当用户提到阿里云、alicloud、aliyun、 ECS、RDS、OSS 等阿里云服务操作或需要查找阿里云相关 skill 时触发。 典型触发词："找阿里云 skill"、"搜索 alicloud skills"、"有没有管理 ECS 的 skill"、 "阿里云 skills 有哪些类目"、"安装阿里云 skill"。
Best practices for using the managed browser — handling login walls, CAPTCHAs, lazy-loaded content, paywalls, and tab cleanup. Target=camoufox 主力路径。