GitHub
onboarding-docs
This skill should be used when generating developer onboarding documentation including architecture overviews, setup guides, code tours, and decision records.
☆ 0查看技能
testing security llm ai AI 技能
发现 testing security llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: testing security llm ai
testing security llm ai 清除筛选
全部技能
GitHub
idea-exploration
Launch background Claude sessions to explore and analyze business ideas. Say "Idea: [description]" to trigger.
☆ 0查看技能
GitHub
ai-documentation-standards
Write AI-readable documentation following concise-over-comprehensive principle, hierarchical CLAUDE.md/AGENTS.md inheritance (100-200 line rule), structured formats (tables over prose), parallel validation, and...
☆ 0查看技能
GitHub
mcp-integration
Set up and use MCP (Model Context Protocol) servers to extend Claude Code capabilities including PRISM semantic memory, filesystem access, and database integration. Use when setting up MCP servers, debugging MC...
☆ 0查看技能
GitHub
agent-prompting
Write effective prompts for Task tool sub-agents, slash commands, and system prompts. Covers Claude 4.x prompting patterns, context engineering, output format specification, and parallel delegation. Use when sp...
☆ 0查看技能
GitHub
synthesizing-requirements
Analyzes unstructured documents, conversations, and notes to generate structured markdown documentation containing user stories, system requirements, and feature specifications. Use this skill when you need to:...
☆ 0查看技能
GitHub
task-to-agent-matcher
Matches tasks to appropriate agents by analyzing task requirements and finding agents with matching capabilities. Use when you need to assign tasks to agents or determine which agent should handle a task. Consi...
☆ 0查看技能
GitHub
agent-creator
Creates new agent files with complete specifications, following the same format as existing agents. Use when a new agent is needed for tasks that existing agents cannot handle. Generates agent markdown files wi...
☆ 0查看技能
GitHub
agent-capability-assessor
Assesses agent capabilities by analyzing agent files and determining what tasks they can handle. Use when you need to evaluate if an existing agent can handle a task or if a new agent is needed. Reviews agent d...
☆ 0查看技能
GitHub
ai-council
Multi-AI collaboration protocol using shared file editing. Use when major decisions require diverse AI perspectives (Claude, Grok, Gemini, etc.) to debate and reach consensus. AIs write directly to debate files...
☆ 0查看技能
GitHub
antigravity-core
AI collaboration protocols for multi-agent problem solving. Use when bouncing ideas between different AI perspectives, reviewing documents for updates, or simulating expert consultations. Enables structured thi...
☆ 0查看技能
GitHub
trading-knowledge-vault
Automated lessons learned system for NinjaTrader trading. Use when implementing new features, fixing bugs, or reviewing code. Ensures past mistakes are never repeated by making historical lessons mandatory chec...
☆ 0查看技能
GitHub
implementation-context
実装開始時のコンテキストセットアップ。関連ナレッジを検索し、効率的な実装開始を支援。新規実装タスク開始時に自動トリガーまたは明示的に呼び出し可能。
☆ 0查看技能
GitHub
fastapi-backend-specialist
Expert FastAPI backend development for building high-performance REST APIs with Python. Use when building APIs, creating endpoints, implementing CRUD operations, integrating databases (SQL/NoSQL), adding valida...
☆ 0查看技能
GitHub
database-specialist
Expert database design, queries, and optimization for both SQL (Neon serverless PostgreSQL) and NoSQL (MongoDB) databases. Use when designing database schemas, writing queries, creating migrations, optimizing p...
☆ 0查看技能
GitHub
ms-agent-patterns
Use when building multi-agent systems with Microsoft Agent Framework. Triggers: "microsoft agents", "agent framework", "semantic kernel", "autogen", "agent graph". NOT for: Simple single-agent scenarios or non-...
☆ 0查看技能
GitHub
mise-expert
Mise configuration and runtime management expert. Use when: - Installing programming language runtimes (node, python, go, rust, etc.) - Configuring tool versions globally or per-project - Questions about mise.t...
☆ 0查看技能
GitHub
ms-agent-types
Use when implementing different agent types in Microsoft Agent Framework. Triggers: "ChatAgent", "BaseAgent", "WorkflowAgent", "A2A agent", "custom agent class". NOT for: Non-Microsoft agent frameworks or simpl...
☆ 0查看技能
GitHub
agent-coordination
Use when coordinating multiple AI agents for parallel work. Triggers: "multi-agent", "parallel agents", "agent coordination", "QuantumDAG", "conflict-free". NOT for: Single-agent operations or basic jj commands...
☆ 0查看技能
GitHub
ms-ag-ui
Use when building web interfaces for Microsoft Agent Framework agents. Triggers: "AG-UI", "agent UI", "agent web interface", "SSE streaming", "human-in-the-loop UI". NOT for: CLI-only agents or backend-only imp...
☆ 0查看技能
GitHub
agentsdb-patterns
Use when implementing self-learning agent workflows. Triggers: "agent learning", "trajectory", "pattern recognition", "AgentDB", "self-learning agent". NOT for: Basic agent operations without learning requireme...
☆ 0查看技能
GitHub
ms-workflows
Use when building multi-agent workflows with Microsoft Agent Framework. Triggers: "workflow builder", "sequential workflow", "concurrent agents", "handoff", "group chat", "magentic". NOT for: Single-agent scena...
☆ 0查看技能
GitHub
context-loader
Tiered context management for multi-agent workflows. Use when: - Starting a new session and need to load project context - Context window approaching capacity (>70% usage) - Switching between different parts of...
☆ 0查看技能
GitHub
run-synth-server
Instructions for starting the MCP Synth server (FastAPI) for synthetic data generation and tools.
☆ 0查看技能
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。