nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Agents & models
25,125 results
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2×…
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need…
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want…
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux…
simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model…
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation…
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use…
training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters,…
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms…
slack-realtime-events
Real-time event handling with Socket Mode and Events API. Use when building interactive Slack bots, handling message events, app mentions, reactions, button…
social
Social network for AI agents — social connections through personality matching, social discovery, and social conversations. Meet people, mingle, social…
english-prompt-review
Use when a user wants an English task prompt reviewed or quietly coached while the requested work continues, especially for software engineering, AI research,…
verify-agent-action
Review a proposed AI-agent action or human-approval packet before execution. Use when an agent wants to run a consequential tool, command, deployment, message,…
custom-agents
Define and validate GitHub custom agent files, prompts, and examples.
install-mcp-genmedia
Installs Google's GenMedia MCP servers (Lyria, NanoBanana, Veo, Chirp, AVTool) via curl from pre-compiled release binaries and registers them in…
agento11y
Inspects and manages Grafana Agent Observability resources via gcx: conversations, generations, experiments, evaluators, rules, scores, and templates. Use when…
agent-development
Design and build AI agents with persistent memory, tool use, and multi-turn conversation. Covers architecture selection, memory design, model selection, tool…
context-report
Analyze Claude Code context efficiency. Use when evaluating session token usage.
hook
Enable, disable, and manage Claude Code hooks. Use for hook debugging or configuration.
iblai-vibe-agent-chat-sidebar
Wrap the Chat surface with the SDK's AppSidebar — projects dropdown, pinned/recent messages, and host-supplied content/footer menu items
iblai-vibe-agent-prompt
Add the agent Prompts tab (system prompts and suggested prompts) to your Next.js app
iblai-vibe-agent-task
Add the agent Tasks tab (schedule automated periodic agent tasks with run logs) to your Next.js app
iblai-vibe-local-llm
Use when adding on-device LLM inference (Ollama backend) to a vibe Next.js + Tauri app. Documents the contract a vibe app must implement so the SDK can route…