精选 Skills 索引（第 168 页）
按质量分排序的前 8,000 个 Skills，每个都有可收录的独立页面。需要全库 15.8 万条检索时，请使用 Skills 目录。
- mcp-mock-client
Create mock MCP client for server testing with request/response simulation.
- mcp-resource-uri-designer
Design and implement MCP resource URI schemes and templates with proper naming, hierarchy, and documentation.
- mcp-tool-resource-pattern
Implements the core MCP Apps architectural pattern where a Tool declares _meta.ui.resourceUri referencing a registered Resource. Covers registerAppTool, registerAppResource, text fallback, structuredContent, and app-only helper tools.
- medical-agent
Build medical AI agents for clinical decision support, medical record summarization, diagnostic assistance, and healthcare workflow automation.
- mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
- memory-summarization
Conversation summarization for memory compression and context management
- merge-queue
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
- micro-optimizer
Apply language-specific micro-optimizations
- milvus-integration
Milvus distributed vector database configuration for large-scale RAG applications
- model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
- multi-app-orchestration
Orchestrate workflows across multiple applications and APIs — inter-app coordination, data handoff, and multi-system task completion.
- multi-service-orchestration
PM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.
- multi-turn-tool-use
Design agents for multi-turn tool use — sequential tool calls, result accumulation, error recovery, and complex task decomposition over multiple turns.
- number-theory-toolkit
Provide number theory algorithm implementations and guidance
- opentelemetry-llm
OpenTelemetry instrumentation for LLM applications with distributed tracing
- orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
- patrol-monitoring
Continuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.
- phoenix-arize-setup
Arize Phoenix observability platform setup for LLM debugging and evaluation
- pii-redaction
PII detection and redaction utilities for privacy-compliant conversational AI
- pinecone-integration
Pinecone vector database setup, configuration, and operations for RAG applications
- plan-implementation
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
- plan-review-gate
Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.
- plan-writing
Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.
- planning-design
Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.
- planning-patterns
Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.
- pr-shepherding
Monitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.
- prime-sieve-generator
Generate optimized prime sieves and factorization routines
- process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
- prompt-compression
Token-efficient prompt compression techniques for cost optimization
- prompt-injection-detector
Prompt injection detection and prevention for secure LLM applications
- prompt-template-design
Structured prompt template creation with variables, formatting, and version control
- proof-assistant
Assist in constructing algorithm correctness proofs
- qdrant-integration
Qdrant vector database with filtering, payloads, and quantization support
- quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
- rag-chunking-strategy
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking
- rag-embedding-generation
Batch embedding generation with caching, rate limiting, and multiple provider support
- rag-hybrid-search
Hybrid search combining semantic and keyword retrieval for RAG pipelines. Implement BM25 + dense vector search with fusion strategies.
- rag-query-transformation
Query expansion, HyDE, and multi-query generation for improved retrieval
- rag-reranking
Cross-encoder reranking and MMR diversity filtering for improved retrieval quality
- rasa-nlu-integration
Rasa NLU pipeline configuration and training for intent and entity extraction