Distributed inference for Llama, Qwen, DeepSeek across heterogeneous hardware. Self-hosted distributed inference — scatter requests across macOS, Linux, Wind...

Agent Observability Stack: Distributed Tracing, Metrics, and Alerting for Multi-Agent Systems. Build a complete observability stack for agent commerce: OpenT...

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

Indexed by skills.sh from orchestra-research/ai-research-skills

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from aj-geddes/useful-ai-prompts

Query scientific findings, experiments, and papers from the Axiom distributed volunteer computing network (113+ hosts, 129 GPUs, 42K+ results).

Indexed by skills.sh from aradotso/trending-skills

P2P distributed AI platform for every domain — health, education, science, art, music, agriculture, law. Share compute, query specialists, sync memory. Ed255...

Join the Hyperspace distributed autonomous intelligence network. Use when: user wants to participate in collective AI research, access larger models via P2P,...

Browse, create, and complete tasks on Clawsy AgentHub — a distributed task platform for AI agents. Create tasks from GitHub repos, PDF/DOCX/PPTX/audio URLs,...

Clean training loops with built-in distributed support.

Ollama load balancer for Llama, Qwen, DeepSeek, and Mistral inference across multiple machines. Load balancing with auto-discovery via mDNS, health checks, q...

Principal-level system architect guiding structured requirements capture, pattern selection, layered design, data architecture, and API standards for scalabl...

Run PyTorch training across GPUs with minimal changes.

Fully sharded data-parallel training for large models.

Vector search engine for production RAG systems.

Pretrain LLMs at scale with PyTorch 4D parallelism.

Alibaba Cloud PolarDB-X Distributed Database AI Assistant. Use for PolarDB-X cluster management, topology inspection, performance diagnostics, SQL optimizati...

A complete social/economic network for AI agents. Provides semantic computing, distributed memory, social networking, coherence verification, autonomous lear...

Ship and operate AI agent systems in production. Covers fleet management, production hardening, distributed observability, QA/chaos testing, and incident res...

Alibaba Cloud PAI-DLC (Deep Learning Containers) job management skill. Covers: distributed training job CRUD, monitoring (logs and events), and GPU sanity ch...

Understand blockchain technology, interact with smart contracts, and evaluate when distributed ledgers solve real problems.

Source-distributed deterministic execution service with pinned dependencies. Runs only with a signed approval artifact (ClawShield mode) and emits verifiable...

A distributed task collaboration platform designed specifically for AI agents. Supports task creation, assignment, status synchronization, progress tracking,...

Connect to BlackPix to receive, complete, and submit knowledge tasks, earning karma to unlock more access within the distributed AI knowledge network.

A distributed labor network for AI agents. Pick up projects, contribute work, earn bounties.

The strategy game for AI agents. Control territory to take top positions in the leaderboards and get your share of USDC distributed from the Fund.

Collective immunity network for AI agents. When one agent detects a prompt injection attack, all connected agents become immune. Real-time pattern detection, community voting, and distributed threat intelligence. Built on top of prompt-guard.

Use when work targets NVIDIA GPUs for deep learning training, inference, distributed execution, CUDA/Triton kernels, or AI infra tuning. Enforces GPU-aware c...

Production-ready decentralized search for AI agents. Privacy-first, uncensored web search via distributed node infrastructure.

TiDB X — object-storage-native distributed SQL for AI agent workloads. Use when building agent memory, context storage, multi-agent coordination, Web3 indexi...

A versatile engineer with strong expertise in system design, distributed systems, and AI infrastructure. Experienced in building scalable backend services, o...

Production-ready decentralized search for AI agents. Privacy-first, uncensored web search via distributed node infrastructure.

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-r…

Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation.

SCAN → SIGN → VERIFY. Certify your skill, detect tampering, revoke instantly. Full control over how your skill is distributed and run. Requires AGENTVERIF_AP...

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-r…

Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation.

TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM, local Docker, Kubernetes). Use when the user wants to run TAO jobs through the SDK, get job tracking, S3 I/O wrapping, multi-node distributed training, or platform-specific f…

Design and implement API rate limiting strategies — token bucket, sliding window, fixed window, leaky bucket with Redis-backed distributed rate limiting.

Rate limiting algorithms, implementation strategies, HTTP conventions, tiered limits, distributed patterns, and client-side handling. Use when protecting APIs from abuse, implementing usage tiers, or configuring gateway-level throttling.

Distributed Datalog engine for sovereign agents enabling persistent, immutable fact storage, querying, and reasoning with built-in synchronization and time-t...

Master-Worker Agent Cluster for parallel task execution. Use when building distributed agent systems with parallel processing needs, task orchestration, or M...

Deploy HTML pages, static directories, or custom edge functions to Alibaba Cloud ESA edge nodes. Manage Edge KV for distributed key-value storage. Use when d...

APM, (Application Performance Management) tool for large-scale distributed systems. apm-monitor, java, agent, apm, distributed-tracing, monitoring.

Encrypted distributed storage using Archon DID vaults. Manage vaults, backup and restore workspace/config/memory with multi-party access control. Use for cre...

Azure Cosmos DB SDK for Python (NoSQL API). Use for document CRUD, queries, containers, and globally distributed data.

Generates high-signal senior-level backend interview questions by topic. Covers API design, distributed systems, databases, caching, messaging, reliability,...

Design Cassandra tables, write efficient queries, and avoid distributed database pitfalls.

Connect multiple OpenClaw instances across devices (VPS, MacBook, Mac Mini) for distributed agent collaboration. Enables clawdbot-to-clawdbot communication, cross-device @mentions, task assignment, and group chat. Use when you have OpenClaw running on multiple machines that ne…

Distributed control system manager

Distributed mesh infrastructure operations — the unified remix of 12 ClawHub skills (Docker, Git, GCP, Linux, SSH, systemd, cron, network, security, DevOps,...

Monitor F5-TTS distributed training on the 9-GPU mining rig (Local-LLM) without interfering with the process.

Golang everyday observability — the always-on signals in production. Covers structured logging with slog, Prometheus metrics, OpenTelemetry distributed traci...

Manage Hadoop clusters with HDFS operations, YARN job tuning, and distributed processing diagnostics.

Connect to JanusGraph distributed graph database to query, manage, and analyze graph data using Apache TinkerPop Gremlin traversal language

Connect to TigerGraph distributed graph database to query, load, and manage large-scale knowledge graph data using GSQL and REST++ APIs

Structured logging, distributed tracing, and metrics collection patterns for building observable systems. Use when implementing logging infrastructure, setting up distributed tracing with OpenTelemetry, designing metrics collection (RED/USE methods), configuring alerting and d…

The 24/7 one-person-company operator agent for MagicHaqi. FOR DEVELOPER / OWNER USE ONLY — not distributed to end users. Runs MagicHaqi's whole operation aut...

Set up and deploy production-ready microservices with API gateway, service templates, service mesh support, distributed tracing, and container orchestration.

Focused on multi-agent collaboration and communication scenarios, helping users build and manage complex distributed agent systems to achieve task decomposit...

Based on two core tools, sessions_spawn and sessions_send, to help users build, manage, and optimize distributed Agent systems, enabling task decomposition,...

Detect the optimal NCCL configuration for distributed GPU training on this machine. Checks GPU topology (NVLink/PCIe), whether RDMA (InfiniBand / RoCE) is av...

Complete observability & reliability engineering system. Use when designing monitoring, implementing structured logging, setting up distributed tracing, buil...

Pydantic Logfire observability — OTEL GenAI traces, tool call spans, token metrics, distributed tracing

Distributed SETI scanner - contribute compute power to analyze real radio telescope data from Breakthrough Listen. Earn tokens when your analysis discovers a...

Create and manage MPC blockchain wallets and sign transactions on EVM and Solana chains using Para's secure distributed key infrastructure via REST API.

Distributed voting and agreement protocols for multi-agent decision making. Use this skill when: 1. Multiple agents need to agree on a value or decision 2. Y...

Distributed map-reduce over agent swarms for parallel data processing. Use this skill when: 1. You need to process large datasets across multiple workers 2....

Distributed configuration management for agent swarms with versioned updates. Use this skill when: 1. Multiple agents need to share configuration settings 2....

Deploy a self-organizing compute swarm with 5 agents. Use this skill when: 1. User wants to set up a distributed task farm or compute swarm 2. User is config...

CLI tool for the QuantMap distributed computing protocol. Manages node setup, task execution, and result submission on devnet.

Deep rate limiting workflow—identifying actors and resources, choosing algorithms, distributed vs local limits, client UX (headers, retries), and abuse detec...

Design and apply replication, partitioning, consensus, failure recovery, and message ordering patterns for reliable, scalable distributed systems.

Distributed task queue for OpenClaw multi-agent systems that routes tasks by capability, tracks lifecycle, coordinates async handoffs, rebalances load, and m...

Plan cross-time-zone meeting windows for distributed teams, providing region-by-region local time mappings and tradeoff analysis for scheduling decisions.

Deep distributed tracing workflow—instrumentation boundaries, context propagation, sampling, tail-based analysis, service maps, and using traces for latency...

Use this skill whenever the user needs to manage VMware NSX security — distributed firewall (DFW) policies, security groups, microsegmentation, and IDS/IPS....

You are an inter-agent communication specialist implementing message-passing patterns from distributed systems (Actor Model, Message. Use when: communication...

Caching strategies, invalidation, eviction policies, HTTP caching, distributed caching, and anti-patterns. Use when designing cache layers, choosing eviction policies, debugging stale data, or optimizing read-heavy workloads.

Crawl any JavaScript-rendered webpage through distributed real Chrome browsers. No local browser needed — perfect for headless VPS.

DevOps and cloud engineer skilled in Kubernetes, Terraform, CI/CD automation, observability, distributed storage, Linux administration, and cloud-native infr...

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeri…

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard ro…

Use when erlang distributed systems including node connectivity, distributed processes, global name registration, distributed supervision, network partitions...

Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention,...

You are an event-driven multi-agent coordination specialist implementing async patterns from distributed systems (Kafka, RabbitMQ, AWS. Use when: event-drive...

PDEBench competition workflow orchestration with expflow — three pipeline modes (full/fast/skip), distributed HPO, pruner integration, and ClearML HyperParam...

1+5 Distributed Production Swarm with Session Inheritance.

Distributed systems architect designing scalable microservice ecosystems. Masters service boundaries, communication patterns, and operational excellence in c...

TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM, local Docker, Kubernetes). Use when the user wants to run TAO jobs through the SDK, get job tracking, S3 I/O wrapping, multi-node distributed training, or platform-specific f…

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeri…

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard ro…

Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Priv...

Songwriting craft and Suno AI music prompts.

The only agent framework that improves itself while you sleep. Self-improving AI infrastructure with 17 dharmic security gates, 4-tier resilience, and 250k+ tokens of 2026 research.

Generate AI-integrated lesson plans with tailored teaching steps, activities, assessments, and tool guidance for Hong Kong primary and secondary STEAM educat...