“pattern”的搜索结果

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

中文简介正在准备中。当前显示原文说明。

Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI.

中文简介正在准备中。当前显示原文说明。

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b

中文简介正在准备中。当前显示原文说明。

Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.

中文简介正在准备中。当前显示原文说明。

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

中文简介正在准备中。当前显示原文说明。

Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities

中文简介正在准备中。当前显示原文说明。

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.

中文简介正在准备中。当前显示原文说明。

Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality.

中文简介正在准备中。当前显示原文说明。

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

中文简介正在准备中。当前显示原文说明。

Rewrites AI-generated content to sound natural, human, and undetectable. Removes robotic patterns, adds voice variety, and preserves meaning.

中文简介正在准备中。当前显示原文说明。

Complete Claude Code productivity system — project setup, prompting patterns, sub-agent orchestration, context management, debugging, refactoring, TDD, and shipping 10X faster. Zero scripts needed.

中文简介正在准备中。当前显示原文说明。

Scan AI agent skills for security vulnerabilities — detects code injection, prompt injection, credential exfiltration, supply chain attacks, and 69+ threat patterns. Use when installing new skills, auditing existing ones, reviewing untrusted code, or validating packages before publishing.

中文简介正在准备中。当前显示原文说明。

End-to-end MegaETH development playbook (Feb 2026). Covers wallet operations, token swaps (Kyber Network), eth_sendRawTransactionSync (EIP-7966) for instant receipts, JSON-RPC batching, real-time mini-block subscriptions, storage-aware contract patterns (Solady RedBlackTreeLib), MegaEVM gas model, WebSocket keepalive, bridging from Ethereum, and debugging with mega-evme. Use when building on MegaETH, managing wallets, sending transactions, or deploying contracts.

中文简介正在准备中。当前显示原文说明。

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

中文简介正在准备中。当前显示原文说明。

Analyze Claude Code features and capabilities to uncover advanced usage patterns, best practices, and real-world application scenarios. Use this skill whenever the user mentions a Claude Code feature (like Streaming Tool Execution, Hooks, MCP, Skills, Subagents, Context Management, Permission Modes, etc.) and wants to know how to leverage it effectively — including advanced tips, workflow optimizations, creative use cases, and pitfalls to avoid. Also trigger when the user pastes a feature description or asks 'how to use X better in Claude Code', even without explicitly saying 'analyze'.

中文简介正在准备中。当前显示原文说明。

Analyze any codebase's source code in depth and produce structured analysis documents saved as markdown files. Use this skill whenever the user asks to understand how a codebase works — architecture, module design, call flows, data models, design patterns, performance characteristics, or any implementation detail. Trigger on phrases like "analyze the source", "explain this code", "how does X work", "where is Y implemented", "trace the flow of", "what happens when", "read through the code", "code walkthrough", "源码分析", "代码解读", "实现原理", "架构分析", "调用链路", "模块分析", or any code-exploration request. Works with any programming language: TypeScript/JavaScript, Java, Python, Go, Rust, C/C++, and more. Even if the user's question seems simple (e.g., "这个文件是干什么的"), use this skill — a thorough, source-backed analysis document is always more valuable than a surface-level guess.

中文简介正在准备中。当前显示原文说明。

Analyze closed deals and lost opportunities for patterns

中文简介正在准备中。当前显示原文说明。

Mine winning ad angles, hooks, and creative patterns from top-performing ads

中文简介正在准备中。当前显示原文说明。

Polish CLI user experience with @clack/prompts for interactive flows, update-notifier for version awareness, and enhanced Commander.js help text with examples and colors. Generic patterns for any Node.js CLI.

中文简介正在准备中。当前显示原文说明。

Add --json flag to CLI commands for machine-readable output on stdout. Generic pattern for any CLI tool, enabling piping to jq and CI/CD integration while keeping human-readable output on stderr.

中文简介正在准备中。当前显示原文说明。

Implement a structured error class hierarchy with actionable messages, proper exit codes, debug mode via env var, and bug report hints on unexpected errors. Generic pattern for any CLI tool or Node.js application.

中文简介正在准备中。当前显示原文说明。

Add zod schema validation for CLI options and YAML/JSON config files. Generic pattern for runtime validation with type-safe parsing and clear error messages in any Commander.js CLI.

中文简介正在准备中。当前显示原文说明。

Add automatic CI/CD environment detection using ci-info package. Generic pattern for any CLI tool that needs to adapt behavior (prompts, output, integrations) based on whether it's running in CI.

中文简介正在准备中。当前显示原文说明。

Add shell completion support via a 'completion' subcommand for bash, zsh, and fish. Generic pattern for any Commander.js CLI, with static and dynamic completion examples.

中文简介正在准备中。当前显示原文说明。