torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,710 results
training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters,…
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation…
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
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…
agent-beacon
Operate Asymptote-Labs/agent-beacon, the cross-harness coding-agent session history and self-improving memory layer. Use when users name Agent Beacon,…
harness2
Operate google-research/harness2 (Harness²), the Apache-2.0 framework for recursive agent harnessing: refine the prompts, guardrails, memory, tool guidance,…
hwp
Use kordoc for agent-native HWP/HWPX document parsing, JSON extraction, diffing, form-field extraction, and Markdown→HWPX reverse conversion (read/convert only…
jev-control-plane
Configure and operate Jev independently for each coding-agent environment, including enable/disable, status checks, and API or local backend selection. Use…
llmfit
Operate AlexsJones/llmfit to inspect detected hardware, rank model fit, estimate plans and storage, run the local REST API, and separate formula-based…
memmachine
Operate MemMachine/MemMachine, the agent long-term memory server, Python/TypeScript clients and MCP integration. Use when a task names this exact repository,…
memori
Operate MemoriLabs/Memori, its agent-memory SDKs, cloud/BYODB modes, runtime configuration and SQL storage integration. Use when the task names this exact…
memsearch
Operate zilliztech/memsearch, the Markdown-canonical agent memory tool with a Milvus search index: CLI, platform plugins, config, indexing, recall and reset.…
rowboat
Operate or explain rowboatlabs/rowboat, the open-source personal/team AI work app whose local knowledge graph is an Obsidian-style network of Markdown notes.…
utopia
Operate deeplethe/utopia, the Rust/Postgres bitemporal knowledge application with ontology-driven ingest, review, search/chat, derivation and per-base MCP. Use…
voicestudio
Use when operating debpalash/VoiceStudio as a local-first voice cloning, voice design, speech generation, transcription, and video-dubbing repository: inspect…
loop-engineering
Loop engineering runtime Grill + Monitor
excalidraw-it
Draw diagrams with the operator on a live Excalidraw+ scene, through the Excalidraw+ MCP. Draws each diagram type from a few lines of YAML with a generator of…
loop
Use when an agent needs to complete its Tariboy iteration or control its own iteration loop.
messages
Use when sending requests or replies, subscribing to channels, or recovering queued and dead-lettered Tariboy messages.
tasks
Use when claiming, decomposing, delegating, questioning, updating, or completing work in Tariboy Native Tasks.
whoami
Use when an agent needs to identify its Tariboy agent, working directory, current iteration, or client and daemon versions.
workdir
Use when an agent needs the configured Tariboy workdir path for a command or file outside its current directory.
check
Review current changes with parallel subagents