Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.
Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure or blueprint design. Trigger keywords — nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
Use this skill when writing, reviewing, debugging, or architecting TypeScript code. Trigger for tsconfig/compiler options, strict mode, generics, conditional/mapped/template literal types, structural typing, ESM/CJS interop, decorators, library typing, or TypeScript runtime boundary issues.
Deploy and manage Netlify projects using Next.js with serverless functions, environment variables, and continuous deployment. Use this skill when working with Netlify deployments, configuring netlify.toml, managing Netlify Functions, debugging webhooks, setting environment variables, or troubleshooting deployment issues for Next.js applications on Netlify. Essential for Twilio-Aldea and similar serverless SMS/telephony projects. v2.0 includes official Netlify documentation, production patterns from Twilio-Aldea (webhook timeout solutions, background functions), and TypeScript code examples.
NocoBase 2 only; never use in a NocoBase 3 project. Use when users need to inspect or maintain NocoBase core AI prerequisites through nb api, including LLM providers, saved services, CLI-versus-UI configuration routing, chat models, embedding discovery, secure credentials, and dependency-safe changes.
nuqs (type-safe URL query state) for Vite React apps WITHOUT TanStack Router. Use when writing or reviewing useQueryState, useQueryStates, parseAsInteger/parseAsString/parseAsJson and other parseAs* parsers, NuqsAdapter setup, or NuqsTestingAdapter tests. Not for TanStack Router or Start apps — use route validateSearch there.
Execute a spec-first one-task-at-a-time loop using OpenSpec OPSX. Use when asked to implement tasks from a list with single-task scope, spec artifacts, and sequential verification before archiving. Don't use for ad-hoc multi-task implementation, non-OpenSpec task trackers, or writing the specs themselves from scratch.
Instruments Java, Python, Node.js, .NET, and Go applications with OpenTelemetry SDKs to send traces, metrics, and logs to Coralogix. Use for SDK-side OTel setup, OTLP exporter env vars, Coralogix resource attributes, APM transaction samplers, Kubernetes Operator injection, or debugging missing traces, metrics, logs, or no telemetry from an application. Not for OTel Collector config (use opentelemetry-collector), OTTL authoring (use opentelemetry-ottl), eBPF instrumentation, or Lambda layers.
Update existing OpenWiki documentation (openwiki/ directory) after source changes — surgical, git-diff-driven edits to only the affected pages, with a no-op check when nothing changed. Use when the user wants to refresh, sync, or maintain the repository wiki.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Run one dev-loop session as the driver - preflight, select, one spec end to end. Harness-generic - grooming drafts and takes run in fresh native subagents of whatever harness drives, takes in their own worktrees (an explicit invocation request may route takes through a runner file instead); the gate stays yours.
Open source license compliance check — for dependency lists, a single library, or code being released. Use to review copyleft obligations and license compatibility for a manifest/SBOM/repository, when asked whether a library can be shipped, or when preparing to open source code.
Reproduce a paper's method in minimal, direct PyTorch when no official code is available, to check whether the method works as claimed. Use whenever the user says "reproduce this paper", "implement this paper's method", "there's no code for this paper", "I want to check if this paper actually works", "turn this algorithm/equation into code", or shares a paper/arXiv link and wants a working implementation of its core mechanism. The output is a small, single-file, readable implementation plus staged verification gates (shape checks → overfit tiny batch → baseline comparison at toy scale) and an explicit assumptions ledger for everything the paper left underspecified. Do NOT use for designing training recipes for your own experiments (pytorch-training-recipe / jax-training-recipe), auditing an existing released artifact (reproducibility-audit), or structuring a research repo (research-codebase).
Performance optimization specialist for profiling, caching, and latency optimization. Use when "performance, latency, slow query, profiling, caching, optimization, N+1, connection pool, p99, performance, profiling, caching, latency, optimization, async, database, load-testing, ml-memory" mentioned.
Use when user requests diagrams, flowcharts, sequence diagrams, class diagrams, component diagrams, ER diagrams, architecture charts, or visualizations — including generating a diagram from existing source code, or rendering/extracting PlantUML embedded in a Markdown file to images (e.g. preparing docs for Confluence/Notion). Also use proactively when explaining systems with 3+ components, APIs, data flows, or class hierarchies. Generates .puml files and exports to PNG/SVG via Kroki API (no local install required).
Assemble a full, market-driven Product Requirements Document (PRD) the Pragmatic way — problem-before-solution, evidence-based, persona-first. Use when the PM asks for a PRD, product spec, feature doc, "write the requirements doc", or "put it all together for the team". Pulls in existing personas, positioning, market problems, requirements and use scenarios if present, and gathers anything missing inline. Produces a Product Requirements Document as a Markdown or Word .docx artifact.
Write Pragmatic Institute use scenarios — short stories that put a market problem in context from the persona's point of view (a component of requirements). Use when the PM asks for “use scenarios”, “a day in the life”, “user story context”, “problem statements”, or needs to reframe a feature request as a real problem so development understands the WHAT (not the HOW). Produces a Use Scenarios document as a Markdown or Word .docx artifact.
Use when writing or modifying Python code that calls polars `DataFrame.join` or `LazyFrame.join` and any downstream step depends on the result's row order — attaching a looked-up column back onto order-sensitive data, positional alignment with a numpy array or `pl.Series`, `hstack`, or reproducible output. Skip for joins whose output you immediately re-sort or treat as an unordered set.
Onboard an AI agent into any project — detect stack (web, mobile, backend), research up-to-date docs, run a universal 8-category audit (pages, state, UI, API, data, auth, jobs, integrations) with auto-detection and auto-skip, interview the developer, and generate structured context files with task-based routing so the agent never wastes time exploring the project again. Re-running project-onboard on an already-onboarded repo refreshes changed context, re-runs the feature audit, preserves interview answers, and updates routing without requiring separate update or audit commands. Use this skill whenever the user says "onboard", "onboard again", "rerun onboard", "update onboard", "refresh context", "set up context", "scan this project", "generate AGENTS.md", "generate CLAUDE.md", "map this codebase", "audit features", "what does this project do", or any request to help an AI agent understand a new or existing codebase. Also trigger when the user starts working in an unfamiliar repo or an existing repo with stale `.context/` files and would benefit from structured context generation.
You are an expert Python software engineer with deep knowledge of modern Python 3.12+ best practices. Use when creating new Python projects, reviewing Python code, refactoring existing code, or when the user asks about Python project structure, dependencies, type hints, testing, or modern Python features. Ensures code follows current best practices with proper tooling (uv, ruff, ty/mypy, pytest), type hints, dataclasses, async patterns, and project structure. Includes version-specific features for 3.12, 3.13, and 3.14
Implement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like Agent Loop behavior to their own product or codebase.
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Autonomous AI coding loop that ships features while you sleep. Use when the user wants to run Ralph, start an autonomous coding session, work overnight, or let Claude implement multiple user stories autonomously. Triggers on "ralph", "autonomous mode", "overnight coding", "autonomous loop", or requests to implement multiple stories without supervision.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.