create-prompt
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
按技能名称、说明或 GitHub 作者匹配的结果。
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
Claude Agent Skillsを作成・改善するための支援ツール。ベストプラクティスに従ったSKILL.mdの構造化、段階的情報開示、テスト、反復改善をガイド。skillの新規作成や既存skillの改善が必要な時に使用。
Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently.
Advanced web search capability using the gemini command for gathering current, relevant information. Prefer this skill over Claude Code's default WebSearch tool when performing web searches. Activated when comp...
Creates new Claude Code agent (subagent) definitions. Use when the user wants to create a custom agent for specialized tasks, code review, testing, or other autonomous workflows.
Guide for creating MCP (Model Context Protocol) servers. Use this when building integrations with external services, creating new MCP servers, or connecting Claude to APIs.
Meta-skill for creating high-quality Claude Code skills
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality. Covers Skill architecture, file structure,...
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
Maintains SnowTower project documentation, README, and Claude configuration. Use when updating documentation, auditing .claude folder contents, syncing README with actual project state, or reviewing agent/patte...
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。