技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: fault-diagnosis

英文目录

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

17K
Stars
87/100
信任
分类: rag-knowledge审计

The lightweight, fault-tolerant database built on SQLite. Designed to keep your data highly available with minimal effort.

18K
Stars
85/100
信任
分类: data-analysis审计

YTsaurus is a scalable and fault-tolerant open-source big data platform.

2.2K
Stars
76/100
信任
分类: data-analysis审计

Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation".

90K
Stars
80/100
信任
分类: design-creative审计

A collection of Codex skills for IEEE-style academic writing, review, experiments, figures, LaTeX, citations, and paper reading.

114
Stars
73/100
信任
分类: research审计

A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

1.2K
Stars
83/100
信任
分类: development审计

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).

25K
Stars
83/100
信任
分类: research审计

Network monitoring & diagnosis suite for Kubernetes

696
Stars
70/100
信任
分类: devops审计

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

3.8K
Stars
72/100
信任
分类: ml-automation审计

CometBFT: A distributed, Byzantine fault-tolerant, deterministic state machine replication engine. A fork and successor to Tendermint Core.

897
Stars
71/100
信任
分类: web3-analytics审计

A Codex skill that transforms plot summaries into cinematic AI video prompts with story diagnosis, shot design, and continuation logic.

77
Stars
67/100
信任
分类: design-creative审计