GitHub
debugging
Systematic debugging workflow to find and fix bugs efficiently. Use this skill when troubleshooting errors, investigating issues, or when code doesn't work as expected.
☆ 32查看技能
research llm ai AI 技能
发现 research 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: research llm ai
research llm ai 清除筛选
全部技能
GitHub
prompt-engineering
LLM prompt optimization and design patterns. Use for crafting effective prompts, chain-of-thought, and AI integration.
☆ 32查看技能
GitHub
multi-agent-system
Design and orchestrate multi-agent AI systems with knowledge harvesting, agent collaboration, and learning loops. Use when working on PSI Engine or similar autonomous agent projects.
☆ 32查看技能
GitHub
data-analysis
Data processing, analysis, and visualization with Python/JavaScript. Use for data exploration, pandas operations, chart generation, and insights extraction.
☆ 32查看技能
GitHub
vector-database
Work with vector databases for RAG, embeddings, and semantic search using ChromaDB or similar. Use when building knowledge bases for PSI Engine or AI-powered search.
☆ 32查看技能
GitHub
sentry-setup-ai-monitoring
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically dete...
☆ 32查看技能
GitHub
ai-proofreading
系统化降低AI检测率至30%以下，通过三遍审校流程（内容、风格、细节）增加人味。当用户提到"AI味太重"、"像AI写的"、"降低AI检测率"、"更像人写的"、"自然一些"、"口语化"时使用此技能。
☆ 32查看技能
GitHub
prompt-classifier
自动识别prompt类型并保存到相应分类（技术/内容/教学/产品/通用），支持自动文件命名和索引管理。当用户提到"保存prompt"、"记录prompt"、"管理prompt"、"整理prompt"、"prompt库"时使用此技能。
☆ 32查看技能
GitHub
orchestration-patterns
Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step work, coordinating subagents, or orchestrating PR workflow...
☆ 32查看技能
GitHub
skills-creator
Create and manage Agent Skills following the agentskills.io specification. Use when users want to create, validate, or modify skills for AI agents.
☆ 32查看技能
GitHub
opencode-agents
Create and configure custom OpenCode agents (primary and subagents) with specialized prompts, tools, permissions, and models. Use when the user wants to create, modify, or configure OpenCode agents, or mentions...
☆ 32查看技能
GitHub
using-agent-relay
Use when coordinating multiple AI agents in real-time - provides inter-agent messaging via Rust PTY wrapper with file-based protocol and reliability features
☆ 31查看技能
GitHub
lettactl
Manage Letta AI agent fleets declaratively with kubectl-style CLI. Use when creating, updating, or managing multiple Letta agents with shared configurations, memory blocks, tools, and folders.
☆ 31查看技能
GitHub
octave-mythology
Functional mythological compression for OCTAVE documents. Semantic shorthand for LLM audiences, not prose decoration
☆ 31查看技能
GitHub
slim-skill-creator
Meta-skill for creating and integrating new best practices (skills, agents, MCP servers) into the SLIM marketplace with dependency tracking and automated registry updates. Use when users want to create custom s...
☆ 31查看技能
GitHub
slim-executive-summary
Generate comprehensive executive summaries from workspace communication files using AI analysis with automatic context discovery
☆ 31查看技能
GitHub
journal
Guide for using the AI's persistent journal database
☆ 31查看技能
GitHub
nanobanana
Guide for generating and editing images using generative AI with the nanobanana CLI
☆ 31查看技能
GitHub
decisions
Guide for recording significant architectural and design decisions in docs/decisions.md. Use this skill when clearly significant architectural decisions are made (database choices, frameworks, core design patte...
☆ 31查看技能
GitHub
breakdown-review-tasks
Review generated tasks for quality and completeness. Called by /breakdown skill after task generation.
☆ 31查看技能
GitHub
breakdown
Break down a PRD or CRD into self-contained implementation tasks for LLM execution. Use when you have a PRD/CRD file and want to generate executable task files for autonomous implementation.
☆ 31查看技能
GitHub
claude-code-hooks
Create event-driven hooks for Claude Code automation. Configure PreToolUse, PostToolUse, Stop, and other hook events with bash scripts, environment variables, matchers, and exit codes.
☆ 31查看技能
GitHub
claude-code-mcp
Configure and build Model Context Protocol (MCP) servers for Claude Code integration. Set up database, filesystem, git, and API connections. Build custom MCP servers with TypeScript/Python SDK, implement tools...
☆ 31查看技能
GitHub
ai-prompt-engineering
Operational prompt engineering patterns, templates, and validation flows for Claude Code.
☆ 31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。