Full index · agent skills
All agent skills — page 102 of 112
Every one of the 11,101 agent skills in the directory, ranked by adoption. Jump to a tool, or browse the agent skills hub.
- Modular SkillsLearn hub-and-spoke modular SKILL.md layout so large agent skills stay maintainable and token-efficient.1 installs
- Moe TrainingCompare Mixture-of-Experts architectures (Mixtral, DeepSeek-V3, Switch, GLaM) when choosing or explaining sparse LLM designs.1 installs
- Morphing IconsImplement animated icon components that morph between any two glyphs using a shared three-line SVG model.1 installs
- Motion DesignerTurn a vague video idea into a Remotion-ready scene-by-scene spec with timing, audio, and motion before anyone writes React composition code.1 installs
- Mt5 TradingOperate Babata V6.6 Predator MT5 automation on Windows VPS with trailing risk, blacklist filters, and journal-backed self-review.1 installs
- Multi Harness PortabilityAuthor and maintain agent skills that run on Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and similar harnesses without rewriting for each platform.1 installs
- Multi Model RoutingRoute each agent subtask to the cheapest model that still meets quality, latency, and failover needs instead of paying premium tokens on every call.1 installs
- Multi Person TaskStructure and track work when more than one person (or agent role) shares a git-backed project without losing ownership or context.1 installs
- Multi Platform LaunchPlan and execute a sequenced launch across Product Hunt, Hacker News, directories, and other channels with goals, timeline, and budget fit for a small team.1 installs
- Multi Timeframe AnalysisAlign NSE/BSE trades with weekly bias, daily setup, and 4H/1H entry timing using the 3-screen method and confluence scoring.1 installs
- MusicGenerate original AI songs or cover versions from reference audio using the ListenHub CLI from your agent.1 installs
- Music Test PlanDraft a structured test plan for a music-related product or feature when Prism metadata is sparse and you need a QA scaffold from the skill slug alone.1 installs
- Mviz RecorderRecord or capture visualization telemetry from MCP-hub workflows so a solo builder can replay or audit agent sessions in production.1 installs
- N8n Hebrew WorkflowsDesign and harden Hebrew-oriented n8n automations with version-aware security notes and AI node patterns (LangChain, RAG vector stores).1 installs
- NanogptBuild and train minimal GPT-2 models to understand transformer architecture and language model internals.1 installs
- Nemo Automodel Distributed TrainingConfigure and run multi-GPU or multi-node NeMo AutoModel distributed training jobs from an agent-assisted workflow.1 installs
- Nemo Automodel Launcher ConfigGenerate or tune NVIDIA NeMo AutoModel launcher configuration so an agent can start local or workflow-based model training without hand-editing YAML by guesswork.1 installs
- Nemo Automodel Model OnboardingOnboard a new Hugging Face causal or MoE architecture into NeMo AutoModel with registry, adapters, YAML, and tests.1 installs
- Nemo Automodel Recipe DevelopmentStand up and iterate NVIDIA NeMo AutoModel training recipes so your coding agent follows a consistent ML workflow instead of improvising configs.1 installs
- Nemo CuratorDeduplicate large text corpora before fine-tuning or RAG so solo builders do not train or index redundant documents.1 installs
- Nemo Data Designer PluginUse NVIDIA’s NeMo Data Designer plugin workflow so your agent can design, evaluate, and prepare training or synthetic datasets for LLM fine-tuning pipelines.1 installs
- Nemo Evaluator PluginRun NVSkills-Eval style 3-tier benchmarks on an agent skill before publishing so security, discoverability, and effectiveness are evidenced.1 installs
- Nemo Evaluator SdkWire custom request/response interceptors into NeMo Evaluator so benchmark runs hit your model endpoints with the right shaping and HTTP plumbing.1 installs
- Nemo GuardrailsWrap production LLM apps with NVIDIA NeMo Guardrails so jailbreaks, toxic output, PII leaks, and hallucinations are blocked at runtime using Colang flows.1 installs
- Nemo Mbridge Mlm Bridge TrainingRun NVIDIA NeMo mBridge MLM bridge training workflows with an agent-guided procedure validated for correctness and safety before you publish or reuse the skill.1 installs
- Nemo Mbridge Multi Node SlurmConfigure multi-node SLURM jobs for NVIDIA NeMo mBridge workflows when training or serving bridged models on HPC clusters.1 installs
- Nemo Mbridge Perf Activation RecomputeTune NeMo MBridge training runs with activation recompute so a solo builder can trade GPU memory for throughput without guessing kernel settings.1 installs
- Nemo Mbridge Perf Cpu OffloadingOptimize NeMo mBridge training or inference workflows with CPU offloading guidance when GPU memory is tight.1 installs
- Nemo Mbridge Perf Cuda GraphsTune NeMo mBridge training or inference with CUDA graphs when GPU kernel launch overhead is limiting throughput.1 installs
- Nemo Mbridge Perf Expert Parallel OverlapTune NeMo MBridge training for expert-parallel overlap and related performance decisions when scaling large language model jobs on NVIDIA stacks.1 installs
- Nemo Mbridge Perf Hierarchical Context ParallelTune NeMo Megatron Bridge jobs that use hierarchical context parallelism when you are optimizing large-model training throughput and memory layout.1 installs
- Nemo Mbridge Perf Megatron FsdpTune NeMo Megatron FSDP training throughput and memory behavior when you are building or scaling large-model fine-tuning jobs on NVIDIA stacks.1 installs
- Nemo Mbridge Perf Memory TuningTune NeMo mBridge training memory and throughput so large-model jobs fit GPU budget without OOM failures.1 installs
- Nemo Mbridge Perf Moe Comm OverlapTune NeMo Megatron-Bridge MoE training so expert communication overlaps compute instead of stalling multi-GPU runs.1 installs
- Nemo Mbridge Perf Moe Dispatcher SelectionPick the right MoE token dispatcher (AlltoAll, DeepEP, HybridEP) for NeMo Bridge training on your GPU platform and expert-parallel degree.1 installs
- Nemo Mbridge Perf Moe Hardware ConfigsTune NVIDIA MoE model and mBridge performance settings on target GPU hardware before you scale training or inference workloads.1 installs
- Nemo Mbridge Perf Moe Long ContextTune NeMo Model Bridge (mbridge) performance for mixture-of-experts models at long context using NVIDIA’s evaluated workflow.1 installs
- Nemo Mbridge Perf Moe Optimization WorkflowGuide an agent through NVIDIA NeMo mbridge MoE performance tuning so mixture-of-experts training or inference improvements follow an evaluated workflow instead of ad-hoc GPU tweaks.1 installs
- Nemo Mbridge Perf Moe Vlm TrainingOptimize NeMo mBridge performance settings for mixture-of-experts vision-language model training so agent-assisted runs follow an evaluated workflow.1 installs
- Nemo Mbridge Perf Parallelism StrategiesChoose and combine Megatron Bridge parallelism (DP, TP, PP, SP, CP, EP) when training dense or MoE models from sub-1B to 500B+ parameters.1 installs
- Nemo Mbridge Perf Sequence PackingApply NVIDIA NeMo mBridge sequence-packing guidance so training or inference batches use GPU memory more efficiently on variable-length sequences.1 installs
- Nemo Mbridge Perf Tp Dp Comm OverlapTune NeMo mbridge training so tensor-parallel and data-parallel communication overlaps compute instead of leaving GPUs idle behind collectives.1 installs
- Nemo Mbridge Recipe RecommenderRecommend NeMo mBridge training or workflow recipes so your agent picks vetted GPU/LLM pipeline configs instead of guessing model-bridge settings.1 installs
- Nemo Mbridge ResiliencyConfigure and troubleshoot NVIDIA NeMo mBridge resiliency patterns when you run distributed or bridged training and inference workloads that must survive node or link failures.1 installs
- Nemo Rl Auto ResearchRun NVSkills-evaluated NeMo RL auto-research workflows safely with agents before publishing skills to broader pipelines.1 installs
- Nemo Rl Brev EtiquetteFollow NVIDIA NeMo RL conventions when launching and managing reinforcement-learning jobs on Brev so GPU sessions stay clean, discoverable, and safe for agents.1 installs
- Nemo Rl DocsGive coding agents accurate, workflow-aligned guidance when you work with NVIDIA NeMo RL docs instead of guessing APIs from stale search snippets.1 installs
- Nemo Rl Session MemoryApply NVIDIA NeMo RL session-memory patterns when training or evaluating agents that must retain state across RL rollout steps.1 installs
- Nemoclaw User Agent SkillsPublish or adopt NVIDIA Nemoclaw user-agent skills only after NVSkills-Eval shows they are safe, discoverable, and effective for agent workflows.1 installs
- Nemoclaw User Configure InferenceConfigure Nemoclaw user inference settings through NVIDIA’s guided skill so your agent workflow points at the right models and endpoints.1 installs
- Nemoclaw User Configure SecurityReview NemoClaw and OpenClaw sandbox controls, credential storage, and risk trade-offs before hardening an agent deployment.1 installs
- Nemoclaw User Deploy RemoteMove NemoClaw off a laptop onto a remote GPU instance with clear deploy steps, Brev legacy caveats, and post-setup operations.1 installs
- Nemoclaw User Get StartedOnboard a solo builder to NVIDIA NemoClaw with the official get-started workflow agents are evaluated to follow.1 installs
- Nemoclaw User Manage PolicyApply Nemoclaw user-management policy rules when agents configure or change who can access claw-style agent deployments.1 installs
- Nemoclaw User Manage SandboxesLet an agent provision or adjust Nemoclaw user sandboxes when you run isolated NVIDIA agent workloads in shared cloud infra.1 installs
- Nemoclaw User Monitor SandboxRun NVSkills-Eval style sandbox checks before you publish or trust an agent skill for production workflows.1 installs
- Nemoclaw User OverviewGive your coding agent a concise Nemoclaw user overview so you can onboard to Nvidia’s claw tooling without hunting scattered docs.1 installs
- Nemoclaw User ReferenceLook up Nemoclaw usage, configuration, and expected agent behavior from NVIDIA’s packaged user-reference skill instead of guessing from repo scraps.1 installs
- Nemotron CustomizePlan repo-native NVIDIA Nemotron fine-tuning, alignment, conversion, and evaluation pipelines from curated JSONL through train and benchmark steps.1 installs
- Nemotron Policy GeneratorAuthor BYO Nemotron content-safety policies—Markdown rules, V2 JSON taxonomy, and inference prompts—for custom guardrails before production inference.1 installs
- Nemotron Retrieval RecipesApply NVIDIA Nemotron retrieval recipes so agents run validated RAG-style retrieval workflows with measurable eval pass rates.1 installs
- Nemotron SpeechImplement or evaluate NVIDIA Nemotron speech workflows in agent projects when you need speech understanding or synthesis with a skill vetted through NVSkills-Eval.1 installs
- Neo4j Agent Memory SkillAdd graph-native short-term, long-term, and reasoning memory to agents with Neo4j or NAMS and wire it into LangChain, CrewAI, or MCP.1 installs
- Neo4j Aura Agent SkillStand up and operate Neo4j Aura Agents with GraphRAG tools over an AuraDB knowledge graph via REST scripts.1 installs
- Neo4j Aura Graph Analytics SkillRun Neo4j Graph Data Science on Aura Graph Analytics with correct sessions, remote projection, and algorithm jobs from Python.1 installs
- Neo4j Aura Provisioning SkillProvision Neo4j AuraDB instances and configure console-based graph agents without hand-rolling aura-cli and API steps.1 installs
- Neo4j Document Import SkillTurn PDFs and text corpora into a queryable Neo4j knowledge graph with chunking, extraction, and loader choices your agent can execute end to end.1 installs
- Neo4j Driver Dotnet SkillImplement correct Neo4j .NET Driver v6 patterns in C# apps—sessions, transactions, mapping, and batching.1 installs
- Neo4j Driver Go SkillImplement Go services against Neo4j using driver v6 patterns for queries, transactions, errors, and batch writes.1 installs
- Neo4j Driver Java SkillImplement correct Neo4j Java Driver v6 patterns—transactions, async, reactive, and batch writes—in a Spring-free or plain Java/Kotlin service.1 installs
- Neo4j Driver Python SkillImplement correct Neo4j Python driver v6 patterns—sessions, transactions, async FastAPI lifespan, errors, and type mapping—in production graph apps.1 installs
- Neo4j Gds SkillRun Neo4j Graph Data Science projections and core algorithms from Python or Cypher with memory estimation and embedding write-back patterns.1 installs
- Neo4j Genai Plugin SkillCall embeddings, completions, structured JSON, and chat from Cypher using Neo4j’s GenAI Plugin for in-database GraphRAG and agent retrieval.1 installs
- Neo4j Getting Started SkillRun the official eight-stage Neo4j pipeline from prerequisites through provision, model, load, explore, query, and build a runnable app or notebook.1 installs
- Neo4j Graphql SkillStand up a secured GraphQL API on Neo4j with @neo4j/graphql typeDefs, relationships, Cypher directives, and OGM access.1 installs
- Neo4j Graphrag SkillWire Neo4j GraphRAG retrieval pipelines in Python—pick retrievers, LLM providers, and GraphRAG prompts for agent-backed Q&A over your graph.1 installs
- Neo4j Import SkillChoose and execute the right Neo4j import path—Data Importer GUI, LOAD CSV, transactional batches, or neo4j-admin bulk—for your CSV graph load.1 installs
- Neo4j Kafka SkillConfigure Neo4j Connector for Kafka sink/source strategies, CDC, Schema Registry, EOS, and DLQ for graph streaming pipelines.1 installs
- Neo4j Nvl SkillEmbed interactive Neo4j graph visualizations in a React or canvas/WebGL app using the official NVL packages.1 installs
- Neo4j Query Tuning SkillDiagnose slow Cypher queries on production Neo4j with EXPLAIN/PROFILE and apply index, planner, and runtime fixes.1 installs
- Neo4j Security SkillApply Neo4j RBAC, privileges, and Enterprise auth patterns with correct Cypher so your graph database users and roles match least privilege before and after go-live.1 installs
- Neo4j Snowflake Graph Analytics SkillRun Neo4j graph algorithms inside Snowflake SQL for fraud, recommendations, and entity resolution without leaving the warehouse.1 installs
- Neo4j Spark SkillWire Apache Spark or Databricks jobs to read and write Neo4j with correct connector options, partitioning, and Delta-to-graph ingestion patterns.1 installs
- Neo4j Vector Index SkillCreate Neo4j vector indexes, ingest embeddings, and run hybrid vector-plus-graph retrieval for RAG or similarity search.1 installs
- NetDebug embedded device networking with tshark capture, pcap analysis, ping, traceroute, port scan, and live traffic stats from the agent CLI.1 installs
- Next UpgradeUpgrade an existing Next.js app to a target major version using official docs, codemods, and coordinated React peer dependency bumps.1 installs
- Night ParkPark a late-night Claude Code session with a handoff file and exact resume command for tomorrow.1 installs
- Nitro FetchRoute existing Axios instances through react-native-nitro-fetch via a custom adapter so interceptors and instances stay intact while HTTP uses the native client.1 installs
- Nnsight Remote InterpretabilityRun nnsight LanguageModel traces and remote interpretability experiments on transformer hidden states without rewriting HuggingFace boilerplate.1 installs
- No Outlinks AuditFind blog and content pages that link to nothing else on your domain and get three concrete internal-link fixes per dead-end with a filterable HTML report.1 installs
- NodeApply Node.js `node:test` patterns for HTTP servers, health checks, and graceful shutdown so solo builders ship reliable APIs.1 installs
- Nse Trading ToolkitRun orchestrated NSE/BSE equity analysis—entries, sizing, stops, and setups—when you trade Indian stocks via Groww and want agent-grade trade plans.1 installs
- Nss Rpc Qps Scannss-rpc-qps-scan is used to measure and monitor RPC query-per-second (QPS) performance for backend services and APIs, enabling builders to identify bottlenecks and optimize throughput.1 installs
- Nss Server Qps ScanA solo builder uses nss-server-qps-scan to measure and monitor queries-per-second performance of their server infrastructure.1 installs
- Nv Generate Ct RflowGenerate NVIDIA CT-R flow workflows for medical imaging pipelines when your agent must scaffold radiology-oriented computation graphs instead of hand-authoring boilerplate.1 installs
- Nv Generate MrRun the NVIDIA nv-generate-mr workflow so your agent produces merge-request-ready changes with eval-backed correctness and security checks.1 installs
- Nv Generate Mr BrainRun NVIDIA’s nv-generate-mr-brain agent workflow when your stack expects that skill package instead of improvising the same steps in chat.1 installs
- Nv Generate Mr Brain FinetuneGuide an agent through NVIDIA-style workflows to generate and fine-tune medical brain MRI datasets for downstream model training.1 installs
- Nv Generate Vae FinetuneFine-tune a VAE on NVIDIA’s generate stack with an agent-guided workflow that was benchmarked for correctness and safety before publication.1 installs
- Nv Reason CxrRun NVIDIA’s chest X-ray (CXR) reasoning skill inside agent workflows so medical-imaging assistance follows the evaluated NVSkills workflow.1 installs