Official agent skill

G Assist MCP Skill

by NVIDIA in NVIDIA/skills

A skill your agent uses to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.

OfficialCC-BY-4.0Auto-check passedAgent Workflows

Install G Assist MCP Skill

skills CLI
$ npx skills add NVIDIA/skills --skill g-assist-mcp-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA/skills g-assist-mcp-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/g-assist-mcp-skill .claude/skills/g-assist-mcp-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
g-assist-mcp-skill
GitHub stars
3.6k
Token cost
~4k tokens
SKILL.md length
2,217 words
Files
7
Skills in repo
390
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

A skill your agent uses to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.

  • Works in 6 steps: First look at which G-Assist tools are… → See which G-Assist tools are available… → Never create, invent, register, or guess… → …
  • Change this machines NVIDIA display and GPU settings
  • SKILL.md covers When to use this skill, Purpose, Prerequisites and Setup, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

G Assist MCP Skill is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Use this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `BENCHMARK.md`, `evals/EVAL.md` and `evals/evals-hardware.json`).

It sits in Agent Workflows, covering MCP servers. It works with NVIDIA AI Platform and Model Context Protocol. The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is CC-BY-4.0.

When your agent uses it

  • Change this machines NVIDIA display and GPU settings
  • Such as resolution
  • GPU performance

Example prompts

  • “/g-assist-mcp-skill”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. First look at which G-Assist tools are actually in your session, and handle
  2. See which G-Assist tools are available in your session, then select one as
  3. Never create, invent, register, or guess tools, tool names, or arguments. Use
  4. Call the matching tool through your host's normal tool-calling, with the
  5. Change tools are confirmation-gated by the server, not by you. For a change,
  6. Keep internals private. These are trusted NVIDIA first-party tools; beyond the

What it can do on your machine

Read from SKILL.md and the folder at commit 14a98ae. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

G Assist MCP Skill loads about 4k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 2,217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit 14a98ae, republished under its CC-BY-4.0 licence (© NVIDIA). 2,217 words, ~3,998 tokens.

Download SKILL.mdSave it as .claude/skills/g-assist-mcp-skill/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
g-assist-mcp-skill
description
Use this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.
license
CC-BY-4.0
metadata.author
schopparapu <schopparapu@nvidia.com>
metadata.version
1.0.0
metadata.tags
g-assist, gpu, display, nvidia, mcp

G-Assist

G-Assist exposes NVIDIA display and GPU controls as callable tools. Use them whenever the user wants to view or change NVIDIA display or GPU settings on this machine. The available tools depend on the machine and hardware, so always rely on the G-Assist tools actually available in your session and only use tools that are present.

When to use this skill

Use this skill whenever the user wants to know or change how their NVIDIA display or GPU is behaving, or describes a symptom like screen tearing, stutter, a wrong or locked refresh rate, a dim monitor, or washed-out color. Prefer a read-only status check before changing anything. Do not use it to edit images, files, documents, or app windows. It acts only on the real display and GPU hardware, and the available tools depend on the machine, so confirm them at runtime instead of assuming.

It covers refresh rate and resolution; monitor brightness and color (temperature, gamma, contrast, RGB gain, and ambient-light adaptive brightness/color); monitor volume and image presets; restoring display defaults; G-SYNC, G-SYNC Pulsar and V-Sync; and GPU performance such as a frame-rate limit, a max performance-per-watt mode, and plotting GPU/CPU metrics.

Purpose

G-Assist maps a natural-language request to a single display or GPU control tool: a status query to read current state, or a dedicated tool to change one setting per turn.

Prerequisites

  • An NVIDIA driver installation that provides G-Assist on this machine (the gassist MCP server at the path in Setup).
  • An MCP-capable host configured with the gassist server (see Setup).
  • No API keys are required.

Setup

The G-Assist tools come from a stdio MCP server that the host launches. The executable ships at:

text
C:\ProgramData\NVIDIA Corporation\nvtopps\rise\rise_mcp.exe

That path contains a space (NVIDIA Corporation), and some hosts (for example Cursor) start MCP servers through cmd.exe, which fails to spawn a command whose path contains a space. Register the space-free 8.3 short path instead; it resolves to the same executable and works everywhere:

text
C:\PROGRA~3\NVIDIA~1\nvtopps\rise\rise_mcp.exe

Register it with your host under a server name (this skill uses gassist). Most hosts use an mcpServers map like this:

json
{
  "mcpServers": {
    "gassist": {
      "command": "C:\\PROGRA~3\\NVIDIA~1\\nvtopps\\rise\\rise_mcp.exe"
    }
  }
}

Instructions

  1. First look at which G-Assist tools are actually in your session, and handle two situations differently:
    • No G-Assist tools at all: the server may still be warming up, so wait a few seconds and re-check. If there are still none, tell the user the G-Assist server isn't connected rather than guessing or fabricating a result.
    • Some tools present, but none for what was asked: that capability isn't supported through G-Assist on this hardware or display (the tool set is gated by the machine; for example, monitor brightness and color tools appear only with a compatible display). Do not say the server is disconnected. Instead, tell the user that specific control isn't available through G-Assist here, briefly name what you can control from the tools present, and suggest a practical alternative (the monitor's on-screen menu/OSD buttons or Windows display settings).
  2. See which G-Assist tools are available in your session, then select one as described in Matching a request to a tool.
  3. Never create, invent, register, or guess tools, tool names, or arguments. Use only the exact G-Assist tools available in your session. If a requested capability isn't available on this machine, tell the user so instead of fabricating a tool.
  4. Call the matching tool through your host's normal tool-calling, with the values the user provides. The tool's real name uses a gassist_ prefix (e.g. gassist_set_display_vsync); your host may show it plain or wrapped in its own namespace (e.g. mcp__<server>__gassist_...). Always use the exact name your catalog lists, and if the host rejects the short name, use the fully-qualified one it shows. Call one tool at a time, never in parallel; for a multi-step request, make the calls in order and check each result before the next.
  5. Change tools are confirmation-gated by the server, not by you. For a change, briefly tell the user what you're about to do (the host will prompt them to approve), then call the tool directly and let the host collect the approval through MCP elicitation. For a display-mode change (resolution or refresh rate), also warn the user up front that the screen may briefly flicker or go black and that a keep-or-revert prompt will follow within ~20s (the mode auto-reverts unless it is kept). Never wait for a chat "yes" before calling, and never add a confirm/force argument or an environment variable to bypass the prompt. Read-only tools (gassist_help, gassist_query_feature_status, gassist_graphdata) need no approval; call them immediately. Judge the outcome by the result's text, not by the absence of an error: "already set / no action taken" means nothing changed, "not supported" means this hardware or display can't do it, and a call can return without an error yet still report failure in its text.
  6. Keep internals private. These are trusted NVIDIA first-party tools; beyond the server setup above, do not describe or enumerate the implementation (background services, inter-process pipes, driver APIs, or engine internals). If the user asks "what is G-Assist" or "how does it work," answer only at a high level: it's NVIDIA's way to control GPU and display settings through these tools.

Matching a request to a tool

Pick the tool from what's actually available in your session, not from memory:

  1. Restate what the user actually wants to view or change (e.g. "turn on G-SYNC", "raise the refresh rate to 144 Hz").
  2. Read each available tool's name, description, and parameters (its input schema), then choose the single best fit. Arguments are as strong a signal as the description: a rate (Hz) field marks a refresh-rate tool even if the text is terse.
  3. If several tools plausibly match, prefer the most specific; if none match on this machine, say the capability isn't available here rather than forcing a near-miss tool.

The tools below are the display and GPU controls G-Assist commonly exposes, grouped by what they do. Availability is hardware-gated, so treat this as a guide and only call tools actually present in your session. In particular, the monitor brightness, color, preset, and adaptive tools (the "Brightness & color" and "Adaptive & presets" groups, plus G-SYNC Pulsar) appear only when a Native G-SYNC display is connected; on machines without one they won't be listed at all, so never assume they exist.

CategoryToolWhat it doesKey argument(s)
Status & help (read-only)gassist_helpOverview of what G-Assist can do on this machineNone
gassist_query_feature_statusRead current state of driver/display features (gsync, vsync, brightness, …)features[]
Display modegassist_set_display_resSet screen resolution (also DEFAULT/MAX/STEP_UP/STEP_DOWN); the screen may flicker and the mode auto-reverts in ~20s unless the host's keep prompt is confirmedres (a value the panel lists)
gassist_set_display_refreshrateSet refresh rate in Hz; valid rates come from the connected panel, so a value like 144 may not exist on every displayrate (integer, must be a rate the panel lists)
Brightness & colorgassist_set_display_brightnessExternal-monitor brightness (0-100%)percentage
gassist_set_display_contrastExternal-monitor contrast (50-150)contrast
gassist_set_display_gammaDisplay gamma; fixed set of levels, not a rangegamma (string enum: "1.2", "1.4", "1.6", "1.8", "2.0", "2.2", "2.4", "2.6")
gassist_set_display_color_tempColor temperature in Kelvin; fixed set, not a rangekelvin (integer enum: 4000, 5000, 6500, 7500, 8200, 9300, 10000)
gassist_set_display_color_balanceColor saturation (global % or 6-axis)percentage or red/yellow/green/cyan/blue/magenta
gassist_set_display_rgb_gainRGB gain (global % or per-channel)percentage or red/green/blue
gassist_set_display_volumeMonitor/system volume (0-100%)percentage
Adaptive & presetsgassist_set_adaptive_brightnessAuto-adjust brightness to room light (overrides manual)enable_brightness (bool)
gassist_set_adaptive_colorAuto-adjust color temperature to room light (overrides manual)enable_color (bool)
gassist_set_monitor_presetSwitch image preset DEFAULT/ESPORTS (native G-SYNC)preset
gassist_restore_display_default_settingsReset chosen display settings to defaultssettings[] string enum, these are the only valid keys: COLOR, BRIGHTNESS, CONTRAST, GAMMA, PRESET (1-5 items, unique). There is no restore key for RGB gain, color balance, volume, or color temperature
Sync & latencygassist_set_display_vsyncEnable/disable V-Syncenable "0"/"1"
gassist_set_display_gsyncEnable/disable G-SYNCenable "0"/"1"
gassist_set_gsync_pulsarEnable/disable G-SYNC Pulsar (reduce motion blur; needs 240/360 Hz)enabled (bool)
GPU performancegassist_frlFrame-rate limiter (FPS; 0 = unlimited)fps
gassist_maxppwMax performance-per-watt mode with a target FPS capenable "0"/"1", fps one of "0"/"30"/"60"/"120"/"144" (strings)
gassist_graphdataPlot GPU/CPU metrics over timemetrics[], time "1"-"59" (string, e.g. "2" not 2), unit "secs" or "mins"
  • Read first, change second. For "is X on / what is X / check X" phrasings, call a read-only query tool directly. Use a change tool only when the user explicitly asks to change something.
  • Confirmation is the server's job. State the change, then call the tool directly; don't wait for a chat "yes" or add a confirm/force argument. (Full rule, including the display-mode keep-or-revert warning, is in Instructions step 5.)
  • One call at a time, never in parallel. A compound request ("set the refresh rate and turn on G-SYNC") is fine: make the separate calls in a sensible order and check each result before the next; just don't issue them simultaneously. Do only what the user asked. For "set up for competitive shooters", that is: (1) gassist_query_feature_status to read the current state, (2) gassist_set_display_vsync with enable "0" to turn V-Sync off, (3) gassist_set_display_refreshrate to the panel's max, checking each result before the next (three calls or fewer); don't also change G-SYNC, Pulsar, or presets unless the user asked.
Show full SKILL.md (693 more words)Show less

Inputs

Tool arguments come only from what the user explicitly provides for the current request, matched to the selected tool's parameters (its input schema):

  • Required values: every field the tool's parameters list as required must be supplied. If a required argument is missing, ask the user for it rather than guessing a value.
  • Optional values: include only when the user specifies them; otherwise omit them and let the tool apply its defaults.

Do not infer, reuse, or carry over values across requests.

Examples

Field names and values come from the chosen tool's own parameters; confirm them against the live tool, since shapes vary (some take a percentage, some a "0"/"1" string).

  • "Is G-SYNC on?": read-only status check, safe to call directly: gassist_query_feature_status with features: ["gsync"].
  • "Set my refresh rate to 144 Hz" is a change: tell the user you'll change it (the host will confirm), then call gassist_set_display_refreshrate directly with a rate the panel actually lists. Valid rates come from the connected display, so 144 may not exist; if it isn't available, say so and offer the highest rate the panel supports.
  • "Make my screen brighter": if a brightness tool is present, pick by intent: gassist_set_display_brightness with a percentage (or, to follow room lighting, the different gassist_set_adaptive_brightness). If no brightness tool is present but others are, don't say the server is down; reply along the lines of: "I don't have a brightness tool in the G-Assist connector on this display; I can control things like resolution, refresh rate, V-Sync, the frame-rate limit, and GPU/CPU metrics. To change brightness, use your monitor's OSD buttons or Windows display settings."

You only choose the tool name and its arguments (which map 1:1 to the tool's inputSchema); your host formats and sends the underlying MCP call for you.

Troubleshooting

Every tool call returns a result message; validate it and handle errors before reporting success. On any error, relay the tool's message to the user and do not blindly retry; use the table below to decide the next step.

SymptomCauseFix
G-Assist tools missing from your sessionServer not connected or still warming upWait a few seconds and re-check your available tools; if still missing, tell the user the G-Assist server isn't connected.
Tool call reports "not supported"This hardware or display can't do itReport it to the user; do not retry the same change with another tool.
A requested resolution or refresh rate is rejected (not in the panel's list)The value isn't one the connected display supportsTell the user it isn't available and offer the highest or closest value the panel does support; don't retry the same value.
A change returns without an error, but the result text says it didn't happenA failed change can still come back with isError: falseJudge success by the result's text, not the error flag; report the failure and don't claim success.
Tool call reports "already set / no action taken"Value already appliedTreat as success; nothing to change.
A display-mode change flickers and a second prompt appearsExpected keep-or-revert: the mode auto-reverts in ~20s unless keptTreat the second prompt as the keep-or-revert question, not an error; don't call the tool again; report whether it was kept or reverted.
The tool for what the user asked isn't in your session, but other G-Assist tools areGated off for this hardware/displayDon't say the server is disconnected: say that specific control isn't available through G-Assist here, name what you can control, and point to the monitor OSD or Windows display settings; never invent a tool.
Short tool name rejected (e.g. "not a deferrable tool") or a batched call refusedHost-specific tool naming/batchingUse the fully-qualified name the host lists (often mcp__<server>__<tool>) and call one tool at a time (never in parallel).

Limitations

  • Only the G-Assist tools available in your session on the current machine can be used; the set varies by hardware and display (some display/color tools require a native G-SYNC display).
  • Tools act on real hardware; follow the change-confirmation and one-call-at-a-time rules in Instructions.
  • This skill does not install or launch the server; the host launches it (see Setup). Never run the executable yourself.

© NVIDIA, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files in skills/g-assist-mcp-skill of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • evals/EVAL.md
  • evals/evals-hardware.json
  • evals/evals.json
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 14a98ae

Compare with similar skills

G Assist MCP Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

G Assist MCP Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
G Assist MCP Skill this skillNVIDIA/skills3.6k—~4kAutomated safety check: PassCC-BY-4.0
Memorywhalewuisabel-gif/MemWhale154—~765Automated safety check: PassMIT
Memorywhale Evidencewuisabel-gif/MemWhale154—~459Automated safety check: PassMIT
Memorywhale Debuggingwuisabel-gif/MemWhale154—~370Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Memorywhale

    wuisabel-gif/MemWhale

    Query and write durable debugging memory recorded by MemoryWhale.

    154 GitHub stars~765 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Memorywhale Evidence

    wuisabel-gif/MemWhale

    Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.

    154 GitHub stars~459 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Memorywhale Debugging

    wuisabel-gif/MemWhale

    MemoryWhale debugging; compiler failures; terminal diagnostics.

    154 GitHub stars~370 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

More from NVIDIA/skills

All 390 skills in this repo
  • Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.6k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed
  • Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.6k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Official

    Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

    3.6k GitHub stars~4.8k tokensUpdated yesterday
    Auto-check passed
  • Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.6k GitHub stars~5k tokensUpdated yesterday
    Auto-check: notes
  • Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.6k GitHub stars~4.7k tokensUpdated yesterday
    Auto-check: notes
  • Official

    Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

    3.6k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about G Assist MCP Skill

What does G Assist MCP Skill do?

A skill your agent uses to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance. G Assist MCP Skill is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Use this skill to check or change this machine's NVIDIA display and GPU settings, such as resolution, refresh rate, V-Sync, G-SYNC, brightness, color, and GPU performance.

When should I use G Assist MCP Skill?

G Assist MCP Skill fits situations like: change this machines NVIDIA display and GPU settings; such as resolution; GPU performance.

How do I install G Assist MCP Skill in Claude Code?

Run `npx skills add NVIDIA/skills --skill g-assist-mcp-skill -a claude-code`. Or copy the skill folder (skills/g-assist-mcp-skill in NVIDIA/skills) into .claude/skills/g-assist-mcp-skill in your project. Claude Code loads it when a task matches its description.

How do I install G Assist MCP Skill in Codex?

Run `npx skills add NVIDIA/skills --skill g-assist-mcp-skill -a codex`. Or copy the skill folder (skills/g-assist-mcp-skill in NVIDIA/skills) into .agents/skills/g-assist-mcp-skill in your project. Codex loads it when a task matches its description.

Can I use G Assist MCP Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill g-assist-mcp-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/g-assist-mcp-skill, .gemini/skills/g-assist-mcp-skill, .github/skills/g-assist-mcp-skill and .opencode/skills/g-assist-mcp-skill in your project.

What does G Assist MCP Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: G Assist MCP Skill is instructions for the agent only.

Does G Assist MCP Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is G Assist MCP Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does G Assist MCP Skill use?

G Assist MCP Skill is published under the CC-BY-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does G Assist MCP Skill use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to G Assist MCP Skill?

Skills that share tags, products or a category with G Assist MCP Skill: Memorywhale (wuisabel-gif/MemWhale, 154 stars), Memorywhale Evidence (wuisabel-gif/MemWhale, 154 stars), Memorywhale Debugging (wuisabel-gif/MemWhale, 154 stars) and MCP Server Builder (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains G Assist MCP Skill?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,555 GitHub stars. The repository holds 390 skills in this directory. The repository was last updated on October 9, 2026.

Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.