搜索结果
agent
找到 5102 个相关结果
通用助手 / 编排推荐
bdi-mental-states
bdi-mental-states
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform…
通用助手 / 编排推荐
bmad-agent-analyst
bmad-agent-analyst
Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.
设计与产品 / 审核评估
memory-systems
memory-systems
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence…
通用助手 / 编排推荐
langchain-framework
langchain-framework
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
通用助手 / 编排推荐
deep-research-agent
deep-research-agent
Build agents specialized in conducting thorough research, gathering information from multiple sources, and synthesizing findings. Covers research planning,…
软件工程 / 诊断修复
deep-debug
deep-debug
Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API interactions, complex bugs resisting normal debugging, or when symptoms don't match expectations. Launches parallel agents with different perspectives and uses Chrome tools for evidence gathering.
软件工程 / 部署发布
java-maven-gradle
java-maven-gradle
Master Maven and Gradle - build configuration, dependencies, plugins, CI/CD
通用助手 / 编排推荐
specstory-guard
specstory-guard
Install a pre-commit hook that scans .specstory/history for secrets before commits. Run when user says "set up secret scanning", "install specstory guard",…
通用助手 / 编排推荐
project-development
project-development
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or…
通用助手 / 编排推荐
context-degradation
context-degradation
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context…
软件工程 / 诊断修复
编写计划
writing-plans
当你有针对多步骤任务的规范或需求时,在编写代码之前使用。
通用助手 / 编排推荐
agentic-os
agentic-os
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled…
软件工程 / 诊断修复
software-backend
software-backend
Production-grade backend APIs for Node.js, Python, Go, Rust, and C# with PostgreSQL. Use when building REST/GraphQL/tRPC services or auth.
研究学习 / 检索整理
kg-extract
kg-extract
Extract entities and relations from source files to build a knowledge graph
研究学习 / 检索整理
bmad-agent-tech-writer
bmad-agent-tech-writer
Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.
通用助手 / 编排推荐
blueprint
blueprint
Define reusable Airflow task group templates with Pydantic validation and compose DAGs from YAML. Use when creating blueprint templates, composing DAGs from…
软件工程 / 诊断修复
pine-debugger
pine-debugger
Adds debugging capabilities and troubleshoots Pine Script issues in TradingView's opaque environment. Use when scripts have errors, unexpected behavior, need…
通用助手 / 编排推荐
appwrite-dotnet
appwrite-dotnet
Appwrite .NET SDK skill. Use when building server-side C# or .NET applications with Appwrite, including ASP.NET and Blazor integrations. Covers user…
研究学习 / 检索整理
observe-metrics
observe-metrics
Aggregate and display system metrics with anomaly detection for a time period
软件工程 / 诊断修复
evaluation
evaluation
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or…