GitHub
rnow-cli
Use the ReinforceNow CLI for RLHF training. Use when running rnow commands, initializing projects, submitting training runs, testing rollouts, or downloading models. Triggers on "rnow", "rnow init", "rnow run",...
☆ 98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
fine-tuning-customization
LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.
☆ 98查看技能
GitHub
ollama-local
Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.
☆ 98查看技能
GitHub
llm-testing
Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.
☆ 98查看技能
GitHub
memory-fabric
Graph-first memory orchestration - knowledge graph (PRIMARY, always available) with optional mem0 cloud enhancement for semantic search. Use when designing memory orchestration or combining graph and mem0.
☆ 98查看技能
GitHub
off-policy-distillation
Generate training data from teacher models for off-policy distillation. Use when converting prompts to SFT datasets using larger models, generating teacher completions with tools, or preparing data for knowledg...
☆ 98查看技能
GitHub
rnow-tools
Write tool functions for ReinforceNow agent training. Use when creating @tool decorated functions, writing tools.py, or sandbox tools. Triggers on "@tool", "tools.py", "tool function", "function calling", "agen...
☆ 98查看技能
GitHub
rnow-rewards
Write reward functions for ReinforceNow RL training. Use when creating @reward decorated functions, writing rewards.py, using precondition rewards, sandbox rewards, llm_judge, or math-verify. Triggers on "rewar...
☆ 98查看技能
GitHub
add-golden
Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden datasets, saving examples.
☆ 98查看技能
GitHub
context-engineering
Use when designing agent system prompts, optimizing RAG retrieval, or when context is too expensive or slow. Reduces tokens while maintaining quality through strategic positioning and attention-aware design.
☆ 98查看技能
GitHub
pgvector-search
Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or cho...
☆ 98查看技能
GitHub
llm-safety-patterns
Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection a...
☆ 98查看技能
GitHub
load-context
Auto-load relevant memories at session start from both mem0 and graph. Use when you need session context restored or preloaded.
☆ 98查看技能
GitHub
langgraph-functional
LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.
☆ 98查看技能
GitHub
function-calling
LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.
☆ 98查看技能
GitHub
llm-streaming
LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.
☆ 98查看技能
GitHub
agent-loops
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.
☆ 98查看技能
GitHub
langgraph-parallel
LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.
☆ 98查看技能
GitHub
contextual-retrieval
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
☆ 98查看技能
GitHub
agentic-rag-patterns
Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.
☆ 98查看技能
GitHub
prompt-engineering-suite
Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.
☆ 98查看技能
GitHub
context-compression
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
☆ 98查看技能
GitHub
mem0-memory
Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.
☆ 98查看技能
GitHub
langfuse-observability
LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.
☆ 98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。