Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer tokens.
中文简介正在准备中。当前显示原文说明。
Design system lookup, CSS best practices, and AI-driven UI component generation via MCP tools
中文简介正在准备中。当前显示原文说明。
Database expert including Prisma, Supabase, SQL, and NoSQL patterns
中文简介正在准备中。当前显示原文说明。
Validate planned changes against local framework rules and policy guardrails before implementation or creation.
中文简介正在准备中。当前显示原文说明。
Sets standards for Data Transfer Objects (DTOs), typically records, including parameter validation in compact canonical constructors.
中文简介正在准备中。当前显示原文说明。
Data processing expert including parsing, transformation, and validation
中文简介正在准备中。当前显示原文说明。
Context-Driven Development methodology - treating project context as managed artifacts alongside code for consistent AI interactions and team alignment.
中文简介正在准备中。当前显示原文说明。
Manage Claude Code --channels sessions (start/stop/status/health) via channel-manager.cjs and terminal-tracker.cjs.
中文简介正在准备中。当前显示原文说明。
Smart contract and secure API contract security analysis — invariant checking, access control, reentrancy, and integer overflow patterns. Implements Checks-Effects-Interactions pattern, formal invariant verification, and OpenSCV vulnerability taxonomy for Solidity/EVM and Rust/Solana contracts.
中文简介正在准备中。当前显示原文说明。
Build tools expert including Vite, Webpack, and bundler configuration
中文简介正在准备中。当前显示原文说明。
Programmatic web automation using Playwright Python — data extraction, form filling, multi-step workflows, auth session management, screenshot/PDF capture, and anti-detection patterns. Use for scripted automation tasks, not interactive MCP-based browser control.
中文简介正在准备中。当前显示原文说明。
Audit content and assets for brand compliance — style guide validation, tone of voice checking, visual identity consistency, brand asset management, and cross-channel coherence.
中文简介正在准备中。当前显示原文说明。
Specifies best practices, including following RESTful API design principles, implementing responsive design, using Zod for data validation, and regularly updating dependencies. This skill promotes modern coding standards and helps developers write consistent, maintainable code.
中文简介正在准备中。当前显示原文说明。
Detect when agents are stuck in repetitive action loops using a rolling 20-action window with escalating nudges — replan after 3 similar actions, explore after 5, force-done after 8.
中文简介正在准备中。当前显示原文说明。
Azure DevOps integration covering pipelines, boards, repos, artifacts, and work item management via Azure CLI and REST API
中文简介正在准备中。当前显示原文说明。
AWS cloud operations for CloudWatch, S3, Lambda, EC2, and IAM
中文简介正在准备中。当前显示原文说明。
Use when you need semantic retrieval from perpetual memory at query time. Parses query intent, searches vector store, ranks by relevance and recency, and injects context. Complements memory-search.cjs with the perpetual_memory LanceDB table.
中文简介正在准备中。当前显示原文说明。
OAuth 2.1 compliant authentication flows (MANDATORY Q2 2026). PKCE required for ALL clients, Implicit Flow removed, modern token security.
中文简介正在准备中。当前显示原文说明。
OAuth 2.1, JWT (RFC 8725), encryption, and authentication security expert. Enforces 2026 security standards.
中文简介正在准备中。当前显示原文说明。
Ultra-granular code analysis for deep architectural context building. Line-by-line and block-by-block analysis using First Principles, 5 Whys, 5 Hows methodology at micro scale. Builds mental models, tracks invariants and assumptions, and maps cross-function call flows for security audit preparation.
中文简介正在准备中。当前显示原文说明。
Atlassian ecosystem integration covering Jira project management, Confluence documentation, Bitbucket source control, and cross-product automation workflows
中文简介正在准备中。当前显示原文说明。
Specifies the preferred syntax for asynchronous operations using async/await and onMount for component initialization. This results in cleaner and more readable asynchronous code.
中文简介正在准备中。当前显示原文说明。
Benchmark external agent frameworks, auto-detect source type, scan for prompt injection, and convert findings into a concrete TDD upgrade backlog for agent-studio evolution.
中文简介正在准备中。当前显示原文说明。
Search and retrieve academic papers from arXiv.org using WebFetch and Exa. No MCP server required - uses existing tools to access arXiv API directly.
中文简介正在准备中。当前显示原文说明。