AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
Choose the right MoE token dispatcher (alltoall, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
OfficialApache-2.0Auto-check passed
Install Nemo Mbridge Perf Moe Dispatcher Selection
$ npx skills add NVIDIA/skills --skill nemo-mbridge-perf-moe-dispatcher-selection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/skills nemo-mbridge-perf-moe-dispatcher-selection --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/nemo-mbridge-perf-moe-dispatcher-selection .claude/skills/nemo-mbridge-perf-moe-dispatcher-selection && 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 "nemo-mbridge-perf-moe-dispatcher-selection" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nemo-mbridge-perf-moe-dispatcher-selection into .claude/skills/nemo-mbridge-perf-moe-dispatcher-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemo-mbridge-perf-moe-dispatcher-selection", 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/nemo-mbridge-perf-moe-dispatcher-selectionType 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 nemo-mbridge-perf-moe-dispatcher-selection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/skills nemo-mbridge-perf-moe-dispatcher-selection --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/nemo-mbridge-perf-moe-dispatcher-selection .agents/skills/nemo-mbridge-perf-moe-dispatcher-selection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nemo-mbridge-perf-moe-dispatcher-selection" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nemo-mbridge-perf-moe-dispatcher-selection into .agents/skills/nemo-mbridge-perf-moe-dispatcher-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemo-mbridge-perf-moe-dispatcher-selection", 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 nemo-mbridge-perf-moe-dispatcher-selection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/skills nemo-mbridge-perf-moe-dispatcher-selection --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/nemo-mbridge-perf-moe-dispatcher-selection .cursor/skills/nemo-mbridge-perf-moe-dispatcher-selection && 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 "nemo-mbridge-perf-moe-dispatcher-selection" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nemo-mbridge-perf-moe-dispatcher-selection into .cursor/skills/nemo-mbridge-perf-moe-dispatcher-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemo-mbridge-perf-moe-dispatcher-selection", 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/nemo-mbridge-perf-moe-dispatcher-selection--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 nemo-mbridge-perf-moe-dispatcher-selection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/skills nemo-mbridge-perf-moe-dispatcher-selection --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/nemo-mbridge-perf-moe-dispatcher-selection .gemini/skills/nemo-mbridge-perf-moe-dispatcher-selection && 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 "nemo-mbridge-perf-moe-dispatcher-selection" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nemo-mbridge-perf-moe-dispatcher-selection into .gemini/skills/nemo-mbridge-perf-moe-dispatcher-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemo-mbridge-perf-moe-dispatcher-selection", 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 nemo-mbridge-perf-moe-dispatcher-selectionInstalls 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 nemo-mbridge-perf-moe-dispatcher-selection -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/nemo-mbridge-perf-moe-dispatcher-selection .github/skills/nemo-mbridge-perf-moe-dispatcher-selection && 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 "nemo-mbridge-perf-moe-dispatcher-selection" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nemo-mbridge-perf-moe-dispatcher-selection into .github/skills/nemo-mbridge-perf-moe-dispatcher-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemo-mbridge-perf-moe-dispatcher-selection", 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 nemo-mbridge-perf-moe-dispatcher-selection -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 nemo-mbridge-perf-moe-dispatcher-selection --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/nemo-mbridge-perf-moe-dispatcher-selection .opencode/skills/nemo-mbridge-perf-moe-dispatcher-selection && 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 "nemo-mbridge-perf-moe-dispatcher-selection" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/nemo-mbridge-perf-moe-dispatcher-selection into .opencode/skills/nemo-mbridge-perf-moe-dispatcher-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemo-mbridge-perf-moe-dispatcher-selection", 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.
Facts
- Skill name
nemo-mbridge-perf-moe-dispatcher-selection- GitHub stars
- 3.6k
- Token cost
- ~2k tokens
- SKILL.md length
- 1,002 words
- Files
- 6
- Skills in repo
- 390
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Choose the right MoE token dispatcher (alltoall, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
- Works in 3 steps: alltoall for initial bring-up → DeepEP if you want a familiar tuned path → HybridEP for the strongest steady-state…
- SKILL.md covers Quick Decision, Model-Family Patterns, Rounded Evidence Summary and Tuning Parameters, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Nemo Mbridge Perf Moe Dispatcher Selection is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Choose the right MoE token dispatcher (alltoall, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `BENCHMARK.md`, `card.yaml` and `evals/evals.json`).
It works with Qwen. 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.
Example prompts
- “/nemo-mbridge-perf-moe-dispatcher-selection”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- alltoall for initial bring-up
- DeepEP if you want a familiar tuned path
- HybridEP for the strongest steady-state result on GB200
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 bash).
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
Nemo Mbridge Perf Moe Dispatcher Selection loads about 2k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,002 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.
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 Apache-2.0 licence (© NVIDIA). 1,002 words, ~1,988 tokens.
Download SKILL.mdSave it as
.claude/skills/nemo-mbridge-perf-moe-dispatcher-selection/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- nemo-mbridge-perf-moe-dispatcher-selection
- description
- Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
- license
- Apache-2.0
- when_to_use
- Choosing a MoE token dispatcher, or tracing a MoE regression or crash to a dispatcher config change; 'which dispatcher', 'alltoall vs DeepEP', 'HybridEP'…
MoE Dispatcher Selection Guide
Stable docs: @docs/training/moe-optimization.md Card: @skills/nemo-mbridge-perf-moe-dispatcher-selection/card.yaml
Quick Decision
By hardware
| Hardware | First choice | Why |
|---|---|---|
| H100 | DeepEP, if the runtime package is installed | Strong default for cross-node EP on Hopper |
| B200 | DeepEP, if the runtime package is installed | Good first choice unless a platform-specific HybridEP path is available |
| GB200 / GB300 NVL72 | HybridEP, if the runtime package is installed | Best fit for NVLink-domain-aware dispatch and lower memory pressure |
| Unknown or first bring-up | alltoall | Easiest path for correctness and debugging |
By EP degree
| EP size | Guidance |
|---|---|
| Small EP | Dispatcher choice is usually second-order; start with alltoall or DeepEP |
| Medium EP | DeepEP often becomes worthwhile |
| Large EP | HybridEP is usually the best target on NVL72 systems |
Model-Family Patterns
| Workload | Common best path | Notes |
|---|---|---|
| DSV3 at large scale | HybridEP on GB200 or GB300, DeepEP on H100 | Dispatcher choice matters more as EP and PP both grow |
| Qwen3 235B | DeepEP on H100, HybridEP on GB200 | HybridEP usually wins on GB200 and often uses less memory |
| Qwen3 30B | DeepEP | Smaller models still benefit, but the absolute gap is smaller |
| Qwen3-Next | Close race in BF16, HybridEP stronger in FP8 or memory-tight runs | Good reminder to test, not assume |
| MoE VLMs | Start simple, then test HybridEP on GB200-class systems | Vision workloads are sensitive to both memory and host overhead |
Rounded Evidence Summary
Backend availability gate
Do not interpret a dispatcher timing until the container has proven that the
selected backend package is available. --moe_flex_dispatcher_backend None
selects the standard alltoall dispatcher, while deepep and hybridep
select moe_token_dispatcher_type="flex" and then require their corresponding
runtime packages at model construction time. If DeepEP or HybridEP is missing,
record the import failure as an environment limitation and treat alltoall as
the only measured correctness fallback for that run.
Qwen3 30B A3B on H100
A short 2026-05-17 H100 smoke run used Qwen3 30B A3B BF16, 16 GPUs, EP=16,
the recipe's Transformer Engine CUDA graph scopes (moe_router,
moe_preprocess), and model.moe_permute_fusion=false due to a Triton JIT
compatibility issue in the run container. The alltoall fallback completed five
steps with 45.65 s mean step time after warmup, 132.9 mean TFLOP/s/GPU after
warmup, final loss 11.44050, and 61.351 GB peak max allocated memory. DeepEP
and HybridEP selected the requested flex backend in the dumped configs but
failed before the first iteration because the packages were not installed. This
confirms the availability gate; it is not a throughput ranking for flex
dispatchers on H100.
DSV3 on GB200 or GB300
The broad trend is more important than any single row in the tracker:
- plain
alltoallis usually the conservative baseline - DeepEP improves that baseline once EP communication becomes visible
- HybridEP adds another step up on NVL72 systems, especially after CUDA graphs, routing improvements, and CPU-side cleanup are already in place
In practice, the stack often moves from roughly "low-teens MFU" territory with an untuned baseline into "high-teens to low-20s MFU" territory after the full dispatcher and kernel stack is tuned.
Qwen3 235B on GB200
For Qwen3 235B, the practical ordering is usually:
alltoallfor initial bring-up- DeepEP if you want a familiar tuned path
- HybridEP for the strongest steady-state result on GB200
HybridEP is usually modestly faster than alltoall on this workload and often
has noticeably better memory headroom.
Qwen3-Next on GB200
This family is a good reminder that dispatcher wins are workload-dependent:
- in BF16,
alltoalland HybridEP can be close - in FP8 or memory-constrained settings, HybridEP tends to look better
- pipeline layout and grouped-GEMM changes can matter almost as much as the dispatcher itself
Tuning Parameters
Show full SKILL.md (420 more words)Show less
DeepEP
DeepEP is selected by setting
moe_token_dispatcher_type="flex" and moe_flex_dispatcher_backend="deepep".
--moe-deepep-num-sms 20Tune the SM count allocated to DeepEP communication kernels (default 20). The optimal value depends on the workload and EP degree. First confirm the DeepEP package imports in the target container; a missing package fails during model construction, before any dispatcher timing is available.
HybridEP
HybridEP is selected by setting
moe_token_dispatcher_type="flex" and moe_flex_dispatcher_backend="hybridep".
--moe-hybridep-num-sms 16Tune the SM count allocated to HybridEP communication (default 16). The
performance harness uses 32 for HybridEP workloads. Sweep between 16 and 32
for the target hardware. Set
NUM_OF_HYBRID_EP_RANKS_PER_NVLINK_DOMAIN to match the NVLink domain size of
the deployment. If it does not match the actual topology, performance and
sometimes correctness will suffer.
First confirm the HybridEP package imports in the target container; a missing
package fails during model construction, before any dispatcher timing is
available.
Routing mode
--moe-router-force-load-balancingFor performance benchmarking, force-balance routing is the safer default. It usually outperforms dropless routing in large-scale benchmarks and makes results more comparable across dispatcher backends.
Key Interactions
| Feature | Interaction |
|---|---|
| CUDA graphs | Best paired with attn moe_router moe_preprocess on dropless MoE |
| EP overlap | Helps when dispatcher time is still visible after backend tuning |
| FP8 | Often increases the relative importance of communication and host overhead |
| CPU affinity | Can matter as much as dispatcher choice on GB200 or GB300 |
| Pipeline layout | Poor PP or VPP layout can erase dispatcher gains |
When To Use Each
alltoall
- first correctness bring-up
- small EP configurations
- debugging communication regressions
DeepEP
- Hopper or B200 deployments
- cross-node EP is clearly visible in profiles
- you want a mature intermediate step before testing HybridEP
HybridEP
- GB200 or GB300 NVL72 systems
- large EP degrees
- memory headroom matters in addition to throughput
Pitfalls
Do not compare dispatchers on different stacks: container, routing mode, PP layout, and CUDA-graph scope can move the result as much as the dispatcher.
HybridEP is topology-sensitive: it is not a universal win outside the hardware it was designed for.
Both dispatchers need SM tuning: default
moe_deepep_num_sms(20) andmoe_hybridep_num_sms(16) are reasonable starting points but rarely optimal.Force-balance and dropless are not interchangeable baselines: keep the routing mode fixed when comparing dispatcher backends.
Memory and throughput can trade off differently by model: Qwen3-style runs may show a smaller speed delta than DSV3, but still justify HybridEP for memory headroom.
Backend import failures are not performance data: if DeepEP or HybridEP is missing from the container, do not compare its failed job against a completed
alltoalljob. Fix the environment first, then rerun the same stack.
© 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
Files
SKILL.md and 5 other files in skills/nemo-mbridge-perf-moe-dispatcher-selection of NVIDIA/skills.
- SKILL.md
- BENCHMARK.md
- card.yaml
- evals/evals.json
- skill-card.md
- skill.oms.sig
Open the folder on GitHubat commit 14a98ae
Compare with similar skills
Nemo Mbridge Perf Moe Dispatcher Selection 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 |
|---|---|---|---|---|---|---|
| Nemo Mbridge Perf Moe Dispatcher Selection this skillNVIDIA/skills | 3.6k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Agent Feature ReproductionQwenLM/qwen-code | 28k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Qwen Code E2E TestingQwenLM/qwen-code | 28k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Game Asset Generatorhtdt/godogen | 7.1k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Fix Art IssuesOpenPipe/ART | 11k | — | ~840 | Automated safety check: Notes | Apache-2.0 |
Similar skills
Agent Feature Reproduction
QwenLM/qwen-code
Reproduces a feature from Codex or Claude Code in Qwen Code by running the reference agent under capture, reading the traces, then implementing matching behavior.
Qwen Code E2E Testing
QwenLM/qwen-code
Guides end-to-end testing of the Qwen Code CLI in headless mode with real model calls, MCP test servers and inspection of raw API traffic.
Game Asset Generator
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
Fix Art Issues
OpenPipe/ART
Fix a GitHub issue on OpenPipe/ART and open a PR. An agent skill from OpenPipe/ART.
Weavebench Cua Reproduce
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
More from NVIDIA/skills
All 390 skills in this repo- Official
Vss Deploy Detection Tracking 2D
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.
- Official
HSB IP Def File Tool
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.
- Official
Isaac Sim Mission Control Showcase
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.
- Official
Defect Image Generation with Cosmos AnomalyGen
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.
- Official
Physical AI Video Augmentation on OSMO
NVIDIA/skills
Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.
- Official
TAO Detection KPI Analysis
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.
Related
Works with
Questions about Nemo Mbridge Perf Moe Dispatcher Selection
What does Nemo Mbridge Perf Moe Dispatcher Selection do?
Choose the right MoE token dispatcher (alltoall, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Nemo Mbridge Perf Moe Dispatcher Selection is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Choose the right MoE token dispatcher (alltoall, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
How do I install Nemo Mbridge Perf Moe Dispatcher Selection in Claude Code?
Run `npx skills add NVIDIA/skills --skill nemo-mbridge-perf-moe-dispatcher-selection -a claude-code`. Or copy the skill folder (skills/nemo-mbridge-perf-moe-dispatcher-selection in NVIDIA/skills) into .claude/skills/nemo-mbridge-perf-moe-dispatcher-selection in your project. Claude Code loads it when a task matches its description.
How do I install Nemo Mbridge Perf Moe Dispatcher Selection in Codex?
Run `npx skills add NVIDIA/skills --skill nemo-mbridge-perf-moe-dispatcher-selection -a codex`. Or copy the skill folder (skills/nemo-mbridge-perf-moe-dispatcher-selection in NVIDIA/skills) into .agents/skills/nemo-mbridge-perf-moe-dispatcher-selection in your project. Codex loads it when a task matches its description.
Can I use Nemo Mbridge Perf Moe Dispatcher Selection 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 nemo-mbridge-perf-moe-dispatcher-selection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nemo-mbridge-perf-moe-dispatcher-selection, .gemini/skills/nemo-mbridge-perf-moe-dispatcher-selection, .github/skills/nemo-mbridge-perf-moe-dispatcher-selection and .opencode/skills/nemo-mbridge-perf-moe-dispatcher-selection in your project.
What does Nemo Mbridge Perf Moe Dispatcher Selection need to run?
SKILL.md names no scripts, command-line tools or credentials: Nemo Mbridge Perf Moe Dispatcher Selection is instructions for the agent only.
Does Nemo Mbridge Perf Moe Dispatcher Selection 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 Nemo Mbridge Perf Moe Dispatcher Selection 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 Nemo Mbridge Perf Moe Dispatcher Selection use?
Nemo Mbridge Perf Moe Dispatcher Selection is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Nemo Mbridge Perf Moe Dispatcher Selection use?
About 2k tokens (SKILL.md is roughly 8k 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 Nemo Mbridge Perf Moe Dispatcher Selection?
Skills that share tags, products or a category with Nemo Mbridge Perf Moe Dispatcher Selection: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Agent Feature Reproduction (QwenLM/qwen-code, 28k stars), Qwen Code E2E Testing (QwenLM/qwen-code, 28k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Nemo Mbridge Perf Moe Dispatcher Selection?
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.