LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.
$ npx skills add NVIDIA/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/NemoClaw nemoclaw-maintainer-analyze-pr-value-stream --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/NemoClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream .claude/skills/nemoclaw-maintainer-analyze-pr-value-stream && 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 "nemoclaw-maintainer-analyze-pr-value-stream" agent skill from https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream into .claude/skills/nemoclaw-maintainer-analyze-pr-value-stream/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemoclaw-maintainer-analyze-pr-value-stream", 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/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-streamType 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/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/NemoClaw nemoclaw-maintainer-analyze-pr-value-stream --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/NemoClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream .agents/skills/nemoclaw-maintainer-analyze-pr-value-stream && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nemoclaw-maintainer-analyze-pr-value-stream" agent skill from https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream into .agents/skills/nemoclaw-maintainer-analyze-pr-value-stream/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemoclaw-maintainer-analyze-pr-value-stream", 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/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/NemoClaw nemoclaw-maintainer-analyze-pr-value-stream --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/NemoClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream .cursor/skills/nemoclaw-maintainer-analyze-pr-value-stream && 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 "nemoclaw-maintainer-analyze-pr-value-stream" agent skill from https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream into .cursor/skills/nemoclaw-maintainer-analyze-pr-value-stream/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemoclaw-maintainer-analyze-pr-value-stream", 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/NemoClaw.git --path .agents/skills/nemoclaw-maintainer-analyze-pr-value-stream--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/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/NemoClaw nemoclaw-maintainer-analyze-pr-value-stream --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/NemoClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream .gemini/skills/nemoclaw-maintainer-analyze-pr-value-stream && 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 "nemoclaw-maintainer-analyze-pr-value-stream" agent skill from https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream into .gemini/skills/nemoclaw-maintainer-analyze-pr-value-stream/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemoclaw-maintainer-analyze-pr-value-stream", 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/NemoClaw nemoclaw-maintainer-analyze-pr-value-streamInstalls 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/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/NemoClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream .github/skills/nemoclaw-maintainer-analyze-pr-value-stream && 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 "nemoclaw-maintainer-analyze-pr-value-stream" agent skill from https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream into .github/skills/nemoclaw-maintainer-analyze-pr-value-stream/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemoclaw-maintainer-analyze-pr-value-stream", 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/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -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/NemoClaw nemoclaw-maintainer-analyze-pr-value-stream --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/NemoClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream .opencode/skills/nemoclaw-maintainer-analyze-pr-value-stream && 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 "nemoclaw-maintainer-analyze-pr-value-stream" agent skill from https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream into .opencode/skills/nemoclaw-maintainer-analyze-pr-value-stream/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nemoclaw-maintainer-analyze-pr-value-stream", 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.
nemoclaw-maintainer-analyze-pr-value-streamAnalyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.
Nemoclaw Maintainer Analyze PR Value Stream is an agent skill from NVIDIA/NemoClaw, published by the product's own GitHub organization. Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts.
It sits in Development. It works with NVIDIA AI Platform and Vitest. The repository describes itself as: Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference. The licence is Apache-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit fcbbab0. 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.
Ships 2 files in scripts/ (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
nodeFrom 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.
Nemoclaw Maintainer Analyze PR Value Stream loads about 1.1k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 522 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); the scripts in this folder are not scanned.
The full file from NVIDIA/NemoClaw at commit fcbbab0, republished under its Apache-2.0 licence (© NVIDIA). 522 words, ~1,118 tokens.
.claude/skills/nemoclaw-maintainer-analyze-pr-value-stream/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->
<!-- SPDX-License-Identifier: Apache-2.0 -->
Run the deterministic read-only analyzer once for one pull request. Every invocation collects the complete observable retained lifetime. It writes a Perfetto-compatible trace, summary, and manifest under .nemoclaw-maintainer/pr-value-stream/pr-<number>/ and emits the summary as bounded JSON on stdout.
Do not run a reduced or latest-revision-only analysis. The latest-revision waterfall remains one derived part of the complete lifetime result.
gh access.node_modules/vitest/vitest.mjs is available, and install zipinfo and unzip. Optional artifact failures appear in caveats and do not become test-timing evidence.node --no-warnings \
.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream/scripts/analyze-pr-value-stream.mts \
--workdir "$PWD" \
--number <pull-request-number>The default repository is NVIDIA/NemoClaw. Use --repository OWNER/REPO only when the user requests another repository. The ten-minute target defaults to 10; use --target-minutes only when the user requests another target.
The analyzer owns completeness and safety bounds. Do not use legacy pagination or truncation options to reduce the standard analysis. If required retained history exceeds a bound, the command fails rather than calling a partial trace complete.
A successful invocation writes:
summary.json: the complete bounded value-stream report printed on stdout.trace.json: Chrome Trace Event JSON for Perfetto or chrome://tracing.manifest.json: exact pull request identity, head commit, output sizes, and completeness declarations. This file is written last.The trace contains lifecycle events, all retained PR revisions, workflows, job queues, job executions, steps, external checks, reviews, comments, inline feedback, commit publication spans, and temporal feedback-to-next-change spans.
Open trace.json in Perfetto to zoom, filter categories, inspect event arguments, and measure arbitrary intervals.
Report these fields first:
target.status and target.theoreticalFastestSeconds.bottlenecks.elapsed.approvalDelaySeconds and elapsed.mergeLagAfterReadySeconds.lifetime artifact paths and counts.caveats.Do not describe a fallback branch timestamp as exact. Do not claim causal attribution from temporal feedback-to-change spans or counterfactual approval calculations. Treat null timing fields as queued or otherwise unobserved. Treat artifact failure caveats as status evidence, not test timing evidence.
The script performs no GitHub writes. It invokes executables with argument arrays, bounds GitHub output, pagination, revisions, workflow runs, jobs, trace events, artifact sizes, and file sizes, and rejects malformed or incomplete required history. Lifetime artifact publication uses a per-PR lock. An active publication waits for up to 30 seconds; a lock left untouched for more than five minutes is reclaimed when its recorded owner identity no longer matches or owner metadata is unreadable. When either process-start identity is unavailable, the lock is retained unless the recorded process is confirmed absent. A timeout reports the exact active lock path for diagnosis.
GitHub does not expose canonical branch-creation timestamps or pull request description edit history. The trace uses the first retained exact-commit workflow as an observable push signal and records that limitation. Draft transitions appear only when GitHub's timeline returns them.
When retained CLI shard artifacts are available, the script accepts only an exact run and commit match, one regular blob-*.json ZIP entry, and bounded compressed and expanded sizes. It uses a private temporary directory and removes it after the attempt.
© 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 2 other files (scripts) in .agents/skills/nemoclaw-maintainer-analyze-pr-value-stream of NVIDIA/NemoClaw.
Open the folder on GitHubat commit fcbbab0
Nemoclaw Maintainer Analyze PR Value Stream 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 |
|---|---|---|---|---|---|---|
| Nemoclaw Maintainer Analyze PR Value Stream this skillNVIDIA/NemoClaw | 23k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| Megatron-LM Container and Dependency SetupNVIDIA/Megatron-LM | 18k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Code Reviewyaklang/yakit | 7.8k | — | ~1.5k | Automated safety check: Notes | AGPL-3.0 | |
| Happy Monorepo Dev Guideslopus/happy | 24k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Doc ReviewerNVlabs/alpasim | 1.3k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 |
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
NVIDIA/Megatron-LM
Walks an agent through working inside the Megatron-LM CI container and changing dependencies with uv, so lock files resolve the same locally and in CI.
yaklang/yakit
对 Yakit 仓库的代码改动做规范化 code review:按代码逻辑、TS 定义、UI 引用与 Props、CSS 样式、依赖版本、配置项六个维度审查,检查测试用例缺失,强制执行 tsc 类型检查与 vitest 测试验证,输出「结果汇总 / 明细解释 / 合并结论」三块报告,经用户确认后写入文件。当用户要求 review、审查、评审代码改动,或在提交、合并、提 PR…
slopus/happy
Local development guide for the Happy pnpm monorepo: install, build, test and run the CLI, server, Expo app and Tauri desktop packages.
NVlabs/alpasim
Reviews recent code changes and checks if documentation needs updates.
CVCUDA/CV-CUDA
Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).
NVIDIA/NemoClaw
Find open issues that a NemoClaw PR may also fix or conflict with.
NVIDIA/NemoClaw
Run a NemoClaw daytime maintainer pass over release-targeted work.
NVIDIA/NemoClaw
Remove bracketed NemoClaw tags from GitHub issue and PR titles.
NVIDIA/NemoClaw
Audit and implement a NemoClaw dependency version upgrade, including Hermes and base images.
NVIDIA/NemoClaw
Continuously maintain automatic NemoClaw main E2E results through coordinated repairs.
NVIDIA/NemoClaw
Analyze retained NemoClaw CI timings for slow CLI tests, runner queues, or base-image publication.
Works with
Categories
Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target. Nemoclaw Maintainer Analyze PR Value Stream is an agent skill from NVIDIA/NemoClaw, published by the product's own GitHub organization. Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.
Nemoclaw Maintainer Analyze PR Value Stream fits situations like: development work in your project.
Run `npx skills add NVIDIA/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a claude-code`. Or copy the skill folder (.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream in NVIDIA/NemoClaw) into .claude/skills/nemoclaw-maintainer-analyze-pr-value-stream in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NVIDIA/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a codex`. Or copy the skill folder (.agents/skills/nemoclaw-maintainer-analyze-pr-value-stream in NVIDIA/NemoClaw) into .agents/skills/nemoclaw-maintainer-analyze-pr-value-stream 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/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nemoclaw-maintainer-analyze-pr-value-stream, .gemini/skills/nemoclaw-maintainer-analyze-pr-value-stream, .github/skills/nemoclaw-maintainer-analyze-pr-value-stream and .opencode/skills/nemoclaw-maintainer-analyze-pr-value-stream in your project.
Going by SKILL.md and its folder, Nemoclaw Maintainer Analyze PR Value Stream needs TypeScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Nemoclaw Maintainer Analyze PR Value Stream 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 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Nemoclaw Maintainer Analyze PR Value Stream: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Megatron-LM Container and Dependency Setup (NVIDIA/Megatron-LM, 18k stars), Code Review (yaklang/yakit, 7.8k stars) and Happy Monorepo Dev Guide (slopus/happy, 24k 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/NemoClaw, which has 22,692 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 10, 2026.
Source: NVIDIA/NemoClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.