Memorywhale
wuisabel-gif/MemWhale
Query and write durable debugging memory recorded by MemoryWhale.
NVIDIA App MCP: drivers, games, laptops, overlay. An agent skill from NVIDIA/skills.
$ npx skills add NVIDIA/skills --skill nvidia-app -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/skills nvidia-app --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nvidia-app .claude/skills/nvidia-app && rm -rf skills-srcUse ~/.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/
Install the "nvidia-app" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nvidia-app into .claude/skills/nvidia-app/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nvidia-app", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NVIDIA/skills/tree/main/skills/nvidia-appType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NVIDIA/skills --skill nvidia-app -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/skills nvidia-app --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nvidia-app .agents/skills/nvidia-app && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nvidia-app" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nvidia-app into .agents/skills/nvidia-app/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nvidia-app", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill nvidia-app -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/skills nvidia-app --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nvidia-app .cursor/skills/nvidia-app && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nvidia-app" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nvidia-app into .cursor/skills/nvidia-app/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nvidia-app", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NVIDIA/skills.git --path skills/nvidia-app--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NVIDIA/skills --skill nvidia-app -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/skills nvidia-app --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nvidia-app .gemini/skills/nvidia-app && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nvidia-app" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nvidia-app into .gemini/skills/nvidia-app/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nvidia-app", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NVIDIA/skills nvidia-appInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NVIDIA/skills --skill nvidia-app -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nvidia-app .github/skills/nvidia-app && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nvidia-app" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nvidia-app into .github/skills/nvidia-app/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nvidia-app", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill nvidia-app -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVIDIA/skills nvidia-app --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nvidia-app .opencode/skills/nvidia-app && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nvidia-app" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nvidia-app into .opencode/skills/nvidia-app/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nvidia-app", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
nvidia-appNVIDIA App MCP: drivers, games, laptops, overlay. An agent skill from NVIDIA/skills.
Nvidia App is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. NVIDIA App MCP: drivers, games, laptops, overlay. Check drivers, manage and optimize games, configure laptop features.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `BENCHMARK.md`, `evals/evals.json` and `references/connection.md`).
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 Apache-2.0.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 0e0d506. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Nvidia App loads about 4.3k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 2,103 words of instructions outside code blocks.
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.
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.
The full file from NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 2,103 words, ~4,255 tokens.
.claude/skills/nvidia-app/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.Use this skill for one product integration: operating NVIDIA App through its local MCP server. It has two routed modes:
The Overlay workflow supports:
Connection setup supports both modes but does not authorize additional actions.
Use this skill when the user asks for one of the supported application, driver, game-optimization, laptop-feature, Overlay, or connection workflows.
Do not select this skill for Desktop Capture, other Overlay filter mutations, NVIDIA Broadcast, OBS, Xbox Game Bar, or other capture software.
Resolve information in this order: explicit user instructions, fresh live MCP schema or state, current client connection configuration, then the applicable self-contained skill reference for static contract details. Never treat a previous tool result as current state.
%ProgramFiles%\NVIDIA Corporation\NVIDIA App\CEF\NVIDIA App.exe.nvapp_overlay_ call.MCP server readiness and Overlay readiness are separate. A successful MCP connection does not establish that Overlay tools are ready.
nvapp_overlay_ requests through the Overlay workflow. Read-only Overlay status can include fields for excluded features, but that does not authorize changing them.nvidia-app in the current MCP client, or fall back explicitly. The client is registered only when this session's live tool catalog advertises nvapp_ tools; an open loopback port or a working stdio bridge is not registration. If those tools are absent, attempt registration per references/connection.md before the first nvapp_ call. Registration is the default path because it persists across turns and sessions. A reachable HTTP endpoint is not a reason to skip the attempt.nvapp_ tools still do not appear in this session, connect directly to the loopback HTTP endpoint (or the stdio bridge) and continue with the same documented tool contracts. Say which path you used and that registering nvidia-app would make access persistent. Do not silently prefer the direct path.tools/list on whichever connection you established, then read references/general-tools.md before selecting or calling one of its seven documented public tools. Select only a returned tool whose description, schema, and annotations most narrowly match the user's in-scope intent, and follow any narrower live schema and annotations.The default HTTP endpoint is:
http://127.0.0.1:13508/mcpThe installed stdio bridge is:
%ProgramFiles%\NVIDIA Corporation\NVIDIA App\McpServer\NvAppMcpServer.exeThe stdio executable relays to the persistent server; it does not start or enable that server.
Read references/general-tools.md before selecting or calling a general NVIDIA App tool. It contains the seven supported tool names, exact arguments, enums, conditional schemas, and prerequisite checks.
Use only a documented tool advertised by live tools/list. The packaged instructions are self-contained and do not depend on repository-internal schema sources.
Use only the tools in this table and the authorized arguments shown here:
| User intent | Tool | Arguments |
|---|---|---|
| Read overall Overlay status | nvapp_overlay_get_status | {} |
| Start recording | nvapp_overlay_capture | { "action": "toggle_recording", "enable": true } |
| Stop and save recording | nvapp_overlay_capture | { "action": "toggle_recording", "enable": false } |
| Enable Instant Replay | nvapp_overlay_capture | { "action": "toggle_instant_replay", "enable": true } |
| Disable Instant Replay | nvapp_overlay_capture | { "action": "toggle_instant_replay", "enable": false } |
| Save Instant Replay | nvapp_overlay_capture | { "action": "save_instant_replay" } |
| Enable Highlights | nvapp_overlay_capture | { "action": "toggle_highlights", "enable": true } |
| Disable Highlights | nvapp_overlay_capture | { "action": "toggle_highlights", "enable": false } |
| Capture a screenshot | nvapp_overlay_capture | { "action": "capture_screenshot" } |
| Show Statistics Overlay | nvapp_overlay_configure_stats | { "enable": true } |
| Hide Statistics Overlay | nvapp_overlay_configure_stats | { "enable": false } |
| Enable RTX Dynamic Vibrance | nvapp_overlay_configure_filters | { "filter": "rtx_dvc", "enable": true } |
| Disable RTX Dynamic Vibrance | nvapp_overlay_configure_filters | { "filter": "rtx_dvc", "enable": false } |
| Get current game | nvapp_overlay_get_current_game_info | {} |
Never invoke toggle_desktop_capture. For nvapp_overlay_configure_filters, use only the rtx_dvc filter value.
toggle_recording, toggle_instant_replay, save_instant_replay, toggle_highlights, and capture_screenshot record screen content and write media files to the user's system. Recordings and screenshots persist in the NVIDIA App Overlay gallery until the user deletes them, and this skill cannot choose their format, resolution, or destination.
Treat every one of them as a privacy-affecting operation:
nvapp_ tools, attempt nvidia-app registration before connecting directly. Once registration is refused or has failed, a direct HTTP or stdio connection is allowed for the rest of the session without re-asking.nvapp_overlay_get_status once and invert only recordingActive, instantReplayEnabled, highlightsEnabled, statsOverlayEnabled, or rtxDvc, respectively.false.nvapp_overlay_capture accepts one action, not an action list.enable to save_instant_replay or capture_screenshot.enable from toggle_recording, toggle_instant_replay, toggle_highlights, or nvapp_overlay_configure_stats.filter: "rtx_dvc" and enable to nvapp_overlay_configure_filters; never invent another filter value.running: false means no current game was identified. Do not invent gameName or processId. Report fullscreen only when it is returned.false or null.<redacted-token>.tools/list is authoritative.For a request such as "Show my NVIDIA driver status," first check whether the current MCP client advertises nvapp_ tools. If it does not, offer to register nvidia-app; if the user declines or registration is not possible, connect directly to the loopback endpoint and say so. Then call tools/list on that connection and confirm nvapp_client_get_driver_status is advertised with an empty-object input schema. If it is unavailable, explain that the connected NVIDIA App version or access level does not expose this workflow; do not substitute a similarly named tool without validating its live schema.
Invoke:
{
"name": "nvapp_client_get_driver_status",
"arguments": {}
}Use the returned structured fields literally:
systemType, installedDriver.version, optional installedDriver.channel, and installedDriver.availableActions.preferredChannel.recommendedDrivers, report name, version, channel, releaseDate, isUpdateAvailable, and availableActions.previouslyInstalledDriver is null, state that NVIDIA App reports no rollback driver is available. Otherwise, report its name, version, releaseDate, and availableActions.This tool is read-only. Do not invoke a driver mutation; none is included in this seven-tool scope.
Call the mutation directly because the requested target state is already known:
{ "name": "nvapp_overlay_capture", "arguments": { "action": "toggle_recording", "enable": true } }Do not read status before the call or issue a verification read afterward. The explicit request is the authorization, so no extra confirmation prompt is needed, but this call starts screen capture and writes a file; report the returned message and see Capture and privacy.
First call nvapp_overlay_get_status with {}. If instantReplayEnabled is present, call nvapp_overlay_capture once with enable set to its opposite. If the field is absent, ask whether to enable or disable Instant Replay and make no mutation yet.
For “Take a PNG screenshot in D:\Shots,” explain that the tool cannot select the format or destination. Ask whether to capture to the Overlay gallery. After confirmation, call:
{ "name": "nvapp_overlay_capture", "arguments": { "action": "capture_screenshot" } }| Error or symptom | Likely cause | Response |
|---|---|---|
service_disabled | Persistent MCP server access is disabled | Ask the user to enable MCP server access in NVIDIA App Settings; do not repeatedly spawn bridges. |
overlay_not_available | MCP is connected but In-Game Overlay is not ready | Ask the user to enable or start In-Game Overlay, then retry only if requested. |
overlay_timeout | Overlay did not answer before the deadline | Preserve retriable; retry at most once when the result allows retrying and the retry remains within the request, then report the failure and ask before trying again. |
access_level_restricted | Current MCP access ceiling blocks the tool | Report the restriction; do not raise access implicitly. |
isError: true or another backend/validation failure | The requested operation did not succeed | Preserve the message and error code; do not infer data or report success. |
Overlay mutations return a human-readable message rather than structured success fields. Report that message literally and do not infer additional state. If saving Instant Replay reports that it is disabled, ask before enabling it. If capture requires Desktop Capture, report the limitation rather than enabling Desktop Capture.
© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 9 other files (references) in skills/nvidia-app of NVIDIA/skills.
Open the folder on GitHubat commit 0e0d506
Nvidia App 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Nvidia App this skillNVIDIA/skills | 3.5k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | |
| Memorywhalewuisabel-gif/MemWhale | 151 | — | ~765 | Automated safety check: Pass | MIT | |
| Memorywhale Evidencewuisabel-gif/MemWhale | 151 | — | ~459 | Automated safety check: Pass | MIT | |
| Memorywhale Debuggingwuisabel-gif/MemWhale | 151 | — | ~370 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT |
wuisabel-gif/MemWhale
Query and write durable debugging memory recorded by MemoryWhale.
wuisabel-gif/MemWhale
Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.
wuisabel-gif/MemWhale
MemoryWhale debugging; compiler failures; terminal diagnostics.
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
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.
anthropics/claude-plugins-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.
NVIDIA/skills
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.
NVIDIA/skills
Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.
NVIDIA/skills
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.
NVIDIA/skills
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.
NVIDIA/skills
Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.
NVIDIA/skills
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.
Works with
Categories
NVIDIA App MCP: drivers, games, laptops, overlay. An agent skill from NVIDIA/skills. Nvidia App is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. NVIDIA App MCP: drivers, games, laptops, overlay.
Nvidia App fits situations like: tasks that involve MCP servers.
Run `npx skills add NVIDIA/skills --skill nvidia-app -a claude-code`. Or copy the skill folder (skills/nvidia-app in NVIDIA/skills) into .claude/skills/nvidia-app in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NVIDIA/skills --skill nvidia-app -a codex`. Or copy the skill folder (skills/nvidia-app in NVIDIA/skills) into .agents/skills/nvidia-app in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill nvidia-app -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nvidia-app, .gemini/skills/nvidia-app, .github/skills/nvidia-app and .opencode/skills/nvidia-app in your project.
SKILL.md names no scripts, command-line tools or credentials: Nvidia App is instructions for the agent only.
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.
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.
Nvidia App is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Nvidia App: Memorywhale (wuisabel-gif/MemWhale, 151 stars), Memorywhale Evidence (wuisabel-gif/MemWhale, 151 stars), Memorywhale Debugging (wuisabel-gif/MemWhale, 151 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.
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,534 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 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.