LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Reviews recent code changes and checks if documentation needs updates.
$ npx skills add NVlabs/alpasim --skill doc-reviewer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVlabs/alpasim doc-reviewer --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/NVlabs/alpasim.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/doc-reviewer .claude/skills/doc-reviewer && 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 "doc-reviewer" agent skill from https://github.com/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewer into .claude/skills/doc-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-reviewer", 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/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewerType 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 NVlabs/alpasim --skill doc-reviewer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVlabs/alpasim doc-reviewer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVlabs/alpasim.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/doc-reviewer .agents/skills/doc-reviewer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "doc-reviewer" agent skill from https://github.com/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewer into .agents/skills/doc-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-reviewer", 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 NVlabs/alpasim --skill doc-reviewer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVlabs/alpasim doc-reviewer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVlabs/alpasim.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/doc-reviewer .cursor/skills/doc-reviewer && 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 "doc-reviewer" agent skill from https://github.com/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewer into .cursor/skills/doc-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-reviewer", 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/NVlabs/alpasim.git --path .cursor/skills/doc-reviewer--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 NVlabs/alpasim --skill doc-reviewer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVlabs/alpasim doc-reviewer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVlabs/alpasim.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/doc-reviewer .gemini/skills/doc-reviewer && 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 "doc-reviewer" agent skill from https://github.com/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewer into .gemini/skills/doc-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-reviewer", 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 NVlabs/alpasim doc-reviewerInstalls 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 NVlabs/alpasim --skill doc-reviewer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVlabs/alpasim.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/doc-reviewer .github/skills/doc-reviewer && 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 "doc-reviewer" agent skill from https://github.com/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewer into .github/skills/doc-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-reviewer", 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 NVlabs/alpasim --skill doc-reviewer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVlabs/alpasim doc-reviewer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVlabs/alpasim.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/doc-reviewer .opencode/skills/doc-reviewer && 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 "doc-reviewer" agent skill from https://github.com/NVlabs/alpasim/tree/main/.cursor/skills/doc-reviewer into .opencode/skills/doc-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-reviewer", 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.
doc-reviewerReviews recent code changes and checks if documentation needs updates.
Doc Reviewer is an agent skill from NVlabs/alpasim. Reviews recent code changes and checks if documentation needs updates. Reads all MD files in root and docs/ to identify stale or missing documentation. Use when completing features, before pushing, or when asked to "check docs", "review documentation", or "doc-reviewer".
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. It works with NVIDIA AI Platform. The repository describes itself as: AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies. The licence is Apache-2.0.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit affc2ea. 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.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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.
Doc Reviewer loads about 1.2k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 328 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 NVlabs/alpasim at commit affc2ea, republished under its Apache-2.0 licence (© NVlabs). 328 words, ~1,249 tokens.
.claude/skills/doc-reviewer/SKILL.md (or your agent's skills folder).Reviews code changes since branching from main and checks all documentation for staleness.
# Find the merge base with main
MERGE_BASE=$(git merge-base HEAD main 2>/dev/null || git merge-base HEAD origin/main)
# Get changed files with stats
git diff --stat $MERGE_BASE HEAD
# Get detailed list
git diff --name-only $MERGE_BASE HEADFind all markdown files in root and docs/:
# Discover all doc files
ls *.md docs/*.md 2>/dev/nullRead all discovered MD files. The total is typically ~40-50k tokens, well within context limits.
For each code change, check all documentation for:
## Documentation Review Summary
### Changes Analyzed
- X files changed across Y modules
- Commits: [describe range] since branching from main
### Documentation Status
#### Needs Update (High Priority)
- **[doc-path]**: [specific issue]
- Code change: [what changed]
- Doc gap: [what's missing or outdated]
- Suggested fix: [specific text to add/change]
#### May Need Update (Review Recommended)
- **[doc-path]**: [potential issue]
#### Verified Current
- [List docs that were checked and are still accurate]
### Recommended Actions
1. [Ordered list of suggested documentation updates]High-priority (almost always needs doc update):
Medium-priority (often needs doc update):
Low-priority (usually no doc update needed):
User: Review the docs for my recent changes
Agent: Let me check what's changed since you branched from main.
[Runs git diff --stat against merge-base]
Found 8 files changed:
- src/runtime/dispatcher.py (new --parallel-workers option)
- src/wizard/cli.py (added --dry-run flag)
- pyproject.toml (bumped numpy version)
Discovering documentation files...
[Lists *.md and docs/*.md, then reads all of them]
## Documentation Review Summary
### Changes Analyzed
- 8 files changed across runtime/, wizard/, and root config
- Branch: feature/parallel-workers
### Needs Update (High Priority)
1. **docs/TUTORIAL.md**: Missing --dry-run flag
- Code: wizard/cli.py line 45 adds --dry-run option
- Gap: CLI options section doesn't mention this flag
- Fix: Add to "Wizard CLI Options" table:
`| --dry-run | Validate config without executing |`
2. **AGENTS.md**: Outdated numpy reference
- Code: pyproject.toml now requires numpy>=2.0
- Gap: Build section mentions numpy 1.x compatibility
- Fix: Update dependency note or remove version mention
### Verified Current
- docs/OPERATIONS.md - Already covers topic
- docs/DESIGN.md - Architecture unchanged
- CONTRIBUTING.md - Dev workflow unchangedBefore creating a PR:
During code review:
Periodic maintenance:
© NVlabs, 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
Just SKILL.md in .cursor/skills/doc-reviewer of NVlabs/alpasim.
Open the folder on GitHubat commit affc2ea
Doc Reviewer 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 |
|---|---|---|---|---|---|---|
| Doc Reviewer this skillNVlabs/alpasim | 1.3k | — | ~1.2k | 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 | |
| Fla Triton To Gluonfla-org/flash-linear-attention | 5.8k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Megatron-LM Container and Dependency SetupNVIDIA/Megatron-LM | 18k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Nemoclaw Contributor Update DependenciesNVIDIA/NemoClaw | 23k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Refactor OpCVCUDA/CV-CUDA | 2.7k | — | ~1.5k | Automated safety check: Pass | Custom licence |
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
fla-org/flash-linear-attention
Port an FLA Triton kernel to Gluon when explicit layouts, asynchronous transfers, or scheduling can address a measured bottleneck.
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.
NVIDIA/NemoClaw
Audit and implement a NemoClaw dependency version upgrade, including Hermes and base images.
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/Megatron-LM
Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.
NVlabs/alpasim
Optimize AlpaSim Slurm topology throughput using persistent local Prometheus/Grafana telemetry and run artifacts.
Works with
Categories
Reviews recent code changes and checks if documentation needs updates. Doc Reviewer is an agent skill from NVlabs/alpasim. Reviews recent code changes and checks if documentation needs updates.
Doc Reviewer fits situations like: completing features; asked to check docs; review documentation.
Run `npx skills add NVlabs/alpasim --skill doc-reviewer -a claude-code`. Or copy the skill folder (.cursor/skills/doc-reviewer in NVlabs/alpasim) into .claude/skills/doc-reviewer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NVlabs/alpasim --skill doc-reviewer -a codex`. Or copy the skill folder (.cursor/skills/doc-reviewer in NVlabs/alpasim) into .agents/skills/doc-reviewer 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 NVlabs/alpasim --skill doc-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doc-reviewer, .gemini/skills/doc-reviewer, .github/skills/doc-reviewer and .opencode/skills/doc-reviewer in your project.
Going by SKILL.md and its folder, Doc Reviewer needs the command-line tools its instructions call (git).
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. 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.
Doc Reviewer 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 1.2k tokens (SKILL.md is roughly 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 Doc Reviewer: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Fla Triton To Gluon (fla-org/flash-linear-attention, 5.8k stars), Megatron-LM Container and Dependency Setup (NVIDIA/Megatron-LM, 18k stars) and Nemoclaw Contributor Update Dependencies (NVIDIA/NemoClaw, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
NVlabs (a GitHub organization) maintains it in NVlabs/alpasim, which has 1,259 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 18, 2026.
Source: NVlabs/alpasim on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.