multi-agent
Multi-agent collaboration. Use when working with other Claude Code sessions, coordinating work, or needing to communicate with teammates.
按技能名称、说明或 GitHub 作者匹配的结果。
Multi-agent collaboration. Use when working with other Claude Code sessions, coordinating work, or needing to communicate with teammates.
Create complete Claude Code plugins with proper structure including skills, commands, agents, and hooks. Generates plugin manifests and directory structures for distribution. Use when building plugins, creating...
Optimizes model and IDE selection across Claude Code CLI and Antigravity IDE to maximize credit efficiency. Routes tasks to the best environment based on complexity and thinking requirements.
Guide for creating effective skills that extend Claude's capabilities. Use when users want to create a new skill or update an existing skill.
Create custom slash commands for Claude Code with proper markdown structure and YAML frontmatter. Use when creating commands, generating slash commands, making workflow automations.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, rou...
Run iterative task execution using Claude in a loop to complete PRD tasks. Use when: (1) Executing multi-step PRDs autonomously, (2) Running Claude in a loop until tasks complete, (3) Automating incremental tas...
Universal MCP-based delegation to Gemini Flash 2.0 for cost optimization. Works with ANY AI model (Claude, Gemini, Grok) via MCP server to route file I/O and routine tasks to the most cost-effective execution l...
Automated configuration of API Endpoints and Authentication for Claude Code and Antigravity. Handles requests involving "proxy", "reverse proxy", "mirror", "gateway", or "custom base URL". distinguish between A...
Configure a repo's agent instruction files (AGENTS.md, CLAUDE.md, etc.) to auto-apply Devvit skill guidance. Trigger phrases: "configure skills", "setup skills", "add devvit docs rule".
This skill provides guidance on using OpenAI's Codex CLI for detail-oriented code analysis. Use when the user explicitly invokes "/codex", asks to "use codex", "run codex", "have codex review", or when Claude d...
This skill should be used when the user asks to "analyze this project", "what type of project is this", "detect project structure", "understand this codebase", or when Claude needs to determine project type for...
Start the Wasp dev server and set up full debugging visibility. This includes running the server (with access to logs), and connecting browser console access so Claude can see client-side errors. Essential for...
Fork terminal to new window with Claude Code, Codex CLI, Gemini CLI, or raw commands.
Implements MCP (Model Context Protocol) server for ZoneWise zoning queries. Exposes tools for district lookup, permitted uses, setbacks, density calculations, and site analysis. Built with FastMCP (Python) or M...
Guides structure decisions for Next.js App Router projects with TypeScript. Invoked by prompt-classifier on PLANNING/IMPLEMENT sequences via "plan-structure". Focuses on minimal, colocated organization per CLAU...
Execute implementation plans in batches with Claude CodePro
This skill should be used when the user asks about "memory", "remember this", "what do you know about me", "recall", "forget this", "search memories", "save preference", or when Claude needs guidance on using m...
Create comprehensive feature specifications for Claude Code projects using iterative refinement with ISO/IEC/IEEE 29148:2018 criteria. Use when user requests creating a technical specification (ТЗ) for a new fe...
Code review for all uncommitted changes (staging status is irrelevant). Checks CLAUDE.md compliance, identifies bugs, security issues, style problems, and simplification opportunities.
Review recent code changes, check against standards, and suggest CLAUDE.md updates. Use this after completing a feature or before committing.
Run multiple Claude Code sessions simultaneously using git worktrees. Use when discussing parallel work, worktrees, concurrent development, or multiple sessions.
Retrieval-augmented Lean4 proof generation. Queries 94k+ exemplars from DeepSeek-Prover V1+V2, uses hybrid search (BM25 + semantic + graph), generates via Claude, compiles in Docker, retries on failure.
Gemini CLIを呼び出して、Claude Codeの機能を補完する。以下の場合に使用: (1) マルチモーダル分析 - 画像/音声/動画/PDFファイルの処理 (2) 大規模コンテキスト分析 - プロジェクト全体のコード分析(100万トークン活用) (3...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。