Templates
Project and code templates
conversation-memory
by davila7
"Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history."
agent-memory-mcp
by davila7
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
context7-auto-research
by davila7
Automatically fetch latest library/framework documentation for Claude Code via Context7 API
ray-data
by davila7
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
deepspeed
by davila7
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
graph-query
by davila7
Query the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find callers", "check dependencies", "what uses this", "show relationships", "find serializers", or when reading code and needing to understand what depends on a component before modifications.
long-context
by davila7
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
memory-search
by davila7
Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.
langchain
by davila7
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
model-pruning
by davila7
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
agent-tool-builder
by davila7
"Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa"
training-llms-megatron
by davila7
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
moe-training
by davila7
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
dispatching-parallel-agents
by davila7
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
llama-factory
by davila7
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
tensorrt-llm
by davila7
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
gepetto
by davila7
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
evaluating-llms-harness
by davila7
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
datadog-cli
by davila7
Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.
agent-manager-skill
by davila7
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
docs-search
by davila7
Search auto-generated codebase documentation for function signatures, API docs, class definitions, and code comments. Use when the user asks to "search docs", "find documentation", "look up a function", "check the API", or before implementing changes to verify correct signatures and patterns.
vibe-prd
by KhazP
Create a Product Requirements Document (PRD) for your MVP. Use when the user wants to define product requirements, create a PRD, or says "help me write requirements", "create PRD", or "define my product".
html-ppt
by lewislulu
HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation".
vibe-build
by KhazP
Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".