dag-executor
End-to-end DAG execution orchestrator that decomposes arbitrary tasks into agent graphs and executes them in parallel. The intelligence layer that makes DAG…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Agents & models
25,124 results
prompt-engine
Template-based AI prompt engine with YAML templates, brand kit injection, input sanitization for security, and token-efficient context blocks.
submit-to-agentlaunch
Submit an AI agent to agentlaunch (a Product Hunt-style directory for AI agents) and read the directory via a public, no-auth REST API. Use when listing,…
voice-agent
Build a real-time voice agent on Deepgram's Voice Agent API: one WebSocket at wss://agent.deepgram.com/v1/agent/converse that runs speech-to-text, a language…
ask-demon
Ask which skill or flow fits your situation. A router over the docs/Agent-Note maintenance flow, the documentation governance run, the prose-and-docs tool…
bugfix
One-command automatic bug-fix orchestrator for this Project Memory MCP workspace using Revisionist → Executor → Reviewer loops plus testing.
skill-evolution
Skill experience evolution manager. At the end of a conversation, analyze user feedback, extract best practices and solutions, persist them to evolution.json, and stitch them into SKILL.md. Supports a three-tier architecture (upstream tier, global tier, project tier) to enable cross-project experience management. Use this tool when the user says "retrospective", "record experience", "save this tip", or "evolve".
instagram-posting
Automates the process of posting to an already logged-in Instagram account using a browser-capable agent. Use this skill when the user requests to post,…
scry-rerank
LLM-powered multi-attribute reranking of candidate sets via pairwise comparison. Supports canonical attributes (clarity, technical_depth, insight), custom…
desktop-control
Background knowledge for droid-control workflows -- not invoked directly. Desktop-control driver mechanics for native GUI app automation via trycua cua-driver.
engineering-redis-game-patterns
Use when implementing Redis patterns for games — caching, leaderboards, pub/sub messaging, session storage, rate limiting, or ephemeral game state. Triggers:…
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or…
axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from…
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or…
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device…
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model…
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
mamba-architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware…
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing…
model-pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50%…
nanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy.…