skill-design
Best practices for skill structure and types. Use when creating skills.
浏览 chkim-su 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
37收录技能的仓库 Stars 合计
20仓库 Forks
0平均每个技能的仓库 Stars
1同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Best practices for skill structure and types. Use when creating skills.
Design patterns for automatic skill activation at plugin or project level. Use when implementing keyword-based skill suggestions.
Virtual test environment for Claude Code hooks, plugins, and agents. Use when testing or validating plugin components without affecting production.
Comprehensive Claude Code hook patterns for automation, state management, and external integration. Use when implementing hooks for validation, workflow gates, MCP integration, or state machines.
Detect unnecessary files and provide cleanup recommendations
Language, style, and comment quality guidelines for plugin content
Claude Code Hook system reference for capabilities, possibilities, and limitations. Use when you want to know what hooks can do.
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.
Categorize and display available skills. Use when listing or selecting skills.
Patterns for configuring agent tools correctly
Philosophical/meta project analysis - critical analysis framework that asks "why?"
LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.
U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features.
Claude Code Hook system entry point. Guides you to the right skill based on your needs.
Single-skill vs multi-skill subagent architectures. Use when designing subagents.
Protocol-based workflow enforcement with validation dependencies and anti-bypass protection
Smart routing wizard for creating skills, agents, commands with complexity-based skill loading
Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.
MCP Gateway design patterns for Agent Gateway, Subprocess, and Daemon isolation. Use when designing MCP integrations.
Hook-based state machine patterns for multi-phase workflows. Use when designing sequential workflows with quality gates.
Aggregation phase for /assist:health-check command - produces final report
Common schema validation rules for all plugin components
Validation phase for /assist:verify command - validates each component
Analysis phase for /assist:health-check command - scores each component
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。