GitHub
extraction-design
Systematic AI extraction prompt design expert with Socratic methodology
☆ 0查看技能
devops llm ai AI 技能
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。
分类目录: devops llm ai
devops llm ai 清除筛选
全部技能
GitHub
cva-patterns-context
Context management patterns for multi-source AI agents in Clojure+Vertex AI. Covers 4 context types (static/query/API/previous-result), lifecycle management (load/cache/invalidate), TTL strategies, and LGPD-com...
☆ 0查看技能
GitHub
cva-patterns-workflows
Multi-agent workflow orchestration patterns for Clojure+Vertex AI. Covers sequential/parallel/DAG topologies, state management (stateless/stateful/hybrid), error handling (retry/circuit breaker), and monitoring...
☆ 0查看技能
GitHub
phase2-5-autonomous
Phase 2-5 autonomous execution guidance - Activate when Claude needs to decide technical choices during implementation/testing/review/release phases
☆ 0查看技能
GitHub
demo-skill
A simple demonstration skill that greets users and provides helpful information
☆ 0查看技能
GitHub
cc-overview
Comprehensive overview of Claude Code features, architecture, and capabilities. Learn about hooks, skills, commands, permissions, and best practices for configuring Claude Code as your AI development assistant....
☆ 0查看技能
GitHub
ashby-workflows
This skill should be used when the user asks to "move candidate through pipeline", "schedule an interview", "manage applications", "track hiring progress", "source candidates", "advance to next stage", or menti...
☆ 0查看技能
GitHub
skill-creator
効果的なスキルを作成するためのガイド。ユーザーがClaudeの機能を専門知識、ワークフロー、ツール統合で拡張する新しいスキルを作成（または既存のスキルを更新）したい場合に使用すべきスキルです。
☆ 0查看技能
GitHub
chroma-client
ChromaDB vector database client for storing and retrieving text embeddings with hybrid search (dense + sparse). Use for RAG operations, contextual retrieval, and similarity search in clinical notes.
☆ 0查看技能
GitHub
agent-authoring
Use when creating AGENTS.md files, writing SKILL.md files, or improving agentic coding developer experience. Triggers include create AGENTS.md, write SKILL.md, agent configuration, agentic DX, AI assistant cont...
☆ 0查看技能
GitHub
agent-interoperability-a2a
standardized protocols for agent collaboration. Use this to implement the Agent2Agent (A2A) protocol and Agent Cards to transform isolated agents into a collaborative ecosystem.
☆ 0查看技能
GitHub
mcp-server-capabilities
extended MCP features beyond tools, including Resources (data access), Prompts (templates), and Sampling (server-initiated model calls). Use this to implement rich, two-way agent interactions.
☆ 0查看技能
GitHub
manage-agents
Create, modify, and manage Claude Code subagents with specialized expertise. Use when you need to "work with agents", "create an agent", "modify an agent", "set up a specialist", "I need an agent for [task]", o...
☆ 0查看技能
GitHub
agent-foundations
core cognitive architectures for Gemini agents. Use this to implement reasoning loops (ReAct, Chain-of-Thought) and understand the orchestration layer.
☆ 0查看技能
GitHub
industry-agent-recommendations
基于 500+ AI Agents Projects 仓库和 2026 年趋势，推荐各行业最有潜力的 AI Agent 项目。当用户需要了解特定行业的 AI Agent 应用、选择适合的 agent 项目或寻找行业最佳实践时使用此技能。涵盖金融、医疗、教育、零售、法律...
☆ 0查看技能
GitHub
langchain
LangChain skill for building LLM orchestration, agents, RAG pipelines, tools, memory, callbacks, and deployment.
☆ 0查看技能
GitHub
project-memory
Persistent memory for the skills project - auto-generates Claude Code skills from conversation transcripts
☆ 0查看技能
GitHub
plan-format
Reference for creating Claude-executable plans (PLAN.md)
☆ 0查看技能
GitHub
project-bootstrap
Bootstraps a repository with project skills from the trusted internal skillregistry. Detect stack, install baseline + language skills into .codex/skills and .claude/skills, generate project-specific overlay ski...
☆ 0查看技能
GitHub
reasoning-patterns-v2
Use this skill for rigorous theoretical derivation with supercollider mode (G1-G7 simultaneous), diffusion reasoning, and synthesis engine. Applies enhanced Dokkado Protocol with generator hooks, meta-pattern r...
☆ 0查看技能
GitHub
observability-analyze-session-logs
Analyze Claude Code session transcripts (JSONL files) for context window content, token usage, and decision analysis. NOT for application logs (use analyze-logs instead). Use when debugging Claude behavior, inv...
☆ 0查看技能
GitHub
anima-commands
LTM (Long Term Memory) command reference. Use when saving memories, searching memories, or managing the memory system. Provides syntax for remember, recall, forget, memories, and other LTM commands.
☆ 0查看技能
GitHub
semantic-search
Search code semantically using AG4ONE Serena integration
☆ 0查看技能
GitHub
flow-next-interview
Interview user in-depth about an epic, task, or spec file to extract complete implementation details. Use when user wants to flesh out a spec, refine requirements, or clarify a feature before building. Triggers...
☆ 0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。