发现 devops 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。
Recursive Language Model context management for processing documents exceeding context window limits. Enables Claude to match Gemini's 2M token context capability through chunking, sub-LLM delegation, and synth...
Predict persona performance in specific task contexts.
Delegate tasks across multi-agent architectures with proper context preservation.
Activate the Recursive Thought Committee multi-persona framework.
Design computational models for cognitive simulation and analysis.
Conduct multi-agent task orchestration and workflow coordination.
Tier escalation and human override cascade protocol for AI-to-Human governance bridge.
Execute Joseph Cognitive Baseline v2.1 evaluation protocol.
Guide for writing Drasi continuous queries using Cypher. Use this when asked to create, modify, or troubleshoot Drasi queries.
Collaborative product ideation through dialogue. Behave as a critical, refined creative product designer. Use when users want to brainstorm product ideas, explore concepts, discuss features, or shape an MVP. Tr...
Use when designing AI agents or chatbots, when raw model outputs feel like a black box, or when building natural language interfaces that need structure and trust
Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve specific blockers
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
Use when designing futuristic agentic workflows, when wanting AI to proactively act on team communications, or when eliminating the bottleneck of formal specifications
This skill should be used when the user asks to "collaborate with Codex", "use Codex for planning", "get Codex review", "delegate to Codex", "Codexと協調", "Codexにレビューを依頼", "Codexに計画を作成させたい",...
Document learnings, capture repeatable workflows as skills, and prepare to compound an opence change.
Coordinate prompt and skill updates across related changes
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
This skill should be used when the user asks to "find past conversations", "recall what was done", "search history", "look up previous work", "how did we handle X", "what was that implementation", "find similar...
Web search with automatic Qdrant storage for building persistent knowledge
Build Retrieval-Augmented Generation systems with vector databases
Build specialized sub-agents for the workflow system
Patterns for ingesting knowledge into vector databases and RAG systems
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。