Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Upgrade Spectrum 1 (sp-* elements, @spectrum-web-components/*) to Spectrum 2 (swc-* elements, @adobe/spectrum-wc). Use when developers need to migrate from Spectrum 1 to Spectrum 2 web components, or when they mention @spectrum-web-components, sp-* elements, or Spectrum 1.
Orchestrate multi-agent Claude Code teams with Minoan-Semitic naming — auto-discover project context (CLAUDE.md, roadmaps, plans, issues) and generate named team configurations with structured task lists and file ownership. Triggers on parallel workstreams, agent teams, multi-agent, spawn agents, swarm, minoan-swarm.
Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps.
Design and audit AI model routers that balance task quality, latency, cost, reliability, safety, privacy, context size, tool use, fallback, caching, evals, budgets, and provider outages. Use when an agent or product must choose models dynamically instead of hard-coding one default model.
Guide for modernizing legacy Python 2 scientific computing code to Python 3 with modern libraries. This skill should be used when migrating scientific scripts involving data processing, numerical computation, or analysis from Python 2 to Python 3, or when updating deprecated scientific computing patterns to modern equivalents (pandas, numpy, pathlib).
Molten OS Core — creates a practical Google DESIGN.md–spec visual system at `molten-docs/design/design.md`, plus `molten-docs/design/example.html`. Use for design system, design.md, or translating the brand brief into visual direction. Start by choosing one design surface (landing page, web product, mobile product, or desktop product), then load the matching surface reference and ask whether the user wants a fast draft or detailed pass. Do not use for brand strategy or messaging; use molten-brand for those.
Real-time blockchain event monitoring with webhooks across EVM, Solana, and Bitcoin. Use when user asks about webhooks, wallet/program/contract activity, transfers, stream addresses, Bitcoin xpubs, replaying blocks, or creating and listing historical stream jobs. NOT for querying historical or current blockchain state - use moralis-data-api instead.
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
Orchestrate multi-agent workflows from a Kiro spec using codex (code) + Gemini (UI), including dispatch/review/state sync via AGENT_STATE.json + PROJECT_PULSE.md; triggers on user says "Start orchestration from spec at <path>", "Run orchestration for <feature>", or mentions multi-agent execution.
Researches music, artists, playlists, and podcasts via the Crawlora API — Spotify tracks/albums/artists/playlists/profiles, Spotify Podcasts, Apple Podcasts, Discogs, and SoundCloud tracks/profiles/playlists — returning clean JSON. Use when the user wants a track/album/artist's details, a playlist or profile, podcast show/episode info and charts, a record's Discogs release/pressing data, or a SoundCloud track/user's stats.
Use this skill for authoritative Eastmoney MX financial data lookups when the user asks for exact, time-sensitive market or company data such as real-time quotes, historical prices, capital flows, valuation metrics, financial statements, company basics, shareholders, executives, or entity relationships. Do not use for news/reports/announcements (use mx-search), condition-based stock screening (use mx-xuangu), watchlist actions (use mx-zixuan), or simulated trading operations (use mx-moni).
Audit component and pattern naming for consistency and clarity, with rename suggestions. Triggers: naming review, are our component names consistent, fix our naming. Token names: token-audit. Prop names: component-api-validator. Figma variable names: figma-variable-audit
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv). Use when the user needs coordinated multi-step literature workflows beyond a single MCP call
Implicit use requires an explicit or already-established Nature Portfolio context. Plan, draft, structurally rebuild, faithfully polish, proofread, or translate manuscript text, prepare initial-submission materials, and fix LaTeX layout. Within that scope, use for 论文写作、章节重构、论文润色、局部改写、翻译、排版、投稿信、标题页 or 作者贡献. Preserve claims and evidence when editing existing text. Do not use for proposals, drafting post-review responses, citation search, or specialist data/statistics text; language-only editing of supplied response prose remains in scope.
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
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
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.
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
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.
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant integration, or the .agents/skills/ directory. Trigger keywords: nemoclaw agent skills, ai coding assistant, cursor, claude code, copilot
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw. Trigger keywords - nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server, openai compatible endpoint, switch nemoclaw inference model, change inference runtime, nemoclaw additional model, nemoclaw sub-agent model, openclaw sub-agent, agents.list, sessions_spawn, vlm-demo, nemoclaw tool calling, ollama tool calls, vllm tool-call-parser, raw json in tui, nemoclaw inference options, nemoclaw onboarding providers, nemoclaw inference routing.
Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or assessing control trade-offs. Trigger keywords - nemoclaw security best practices, sandbox security controls risk framework, nemoclaw credential storage, openshell provider, api key security, openclaw security controls, nemoclaw security boundary, prompt injection, tool access control.
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw plugins, openclaw plugins, install openclaw plugin, nemoclaw onboard from dockerfile, nemoclaw brev web ui, nemoclaw getting started, brev quickstart, nvidia nemotron agent, nemoclaw sandbox hardening, container security, docker capabilities, process limits.
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.
Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.
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.