Align Recipe pyproject.toml
google/adk-recipes
Brings a Python recipe's pyproject.toml in line with the repo's CI rules, either as a read-only dry run or by rewriting the file while keeping comments.
Runs the Megatron-LM autoformat script and its linting tools before a pull request, and keeps Python imports in order with isort.
Install Megatron-LM Linting and Formatting
$ npx skills add NVIDIA/Megatron-LM --skill mcore-linting-and-formatting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/Megatron-LM mcore-linting-and-formatting --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/Megatron-LM.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mcore-linting-and-formatting .claude/skills/mcore-linting-and-formatting && 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 "mcore-linting-and-formatting" agent skill from https://github.com/NVIDIA/Megatron-LM/tree/main/skills/mcore-linting-and-formatting into .claude/skills/mcore-linting-and-formatting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcore-linting-and-formatting", 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/Megatron-LM/tree/main/skills/mcore-linting-and-formattingType 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/Megatron-LM --skill mcore-linting-and-formatting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/Megatron-LM mcore-linting-and-formatting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/Megatron-LM.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mcore-linting-and-formatting .agents/skills/mcore-linting-and-formatting && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mcore-linting-and-formatting" agent skill from https://github.com/NVIDIA/Megatron-LM/tree/main/skills/mcore-linting-and-formatting into .agents/skills/mcore-linting-and-formatting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcore-linting-and-formatting", 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/Megatron-LM --skill mcore-linting-and-formatting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/Megatron-LM mcore-linting-and-formatting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/Megatron-LM.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mcore-linting-and-formatting .cursor/skills/mcore-linting-and-formatting && 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 "mcore-linting-and-formatting" agent skill from https://github.com/NVIDIA/Megatron-LM/tree/main/skills/mcore-linting-and-formatting into .cursor/skills/mcore-linting-and-formatting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcore-linting-and-formatting", 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/Megatron-LM.git --path skills/mcore-linting-and-formatting--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/Megatron-LM --skill mcore-linting-and-formatting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/Megatron-LM mcore-linting-and-formatting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/Megatron-LM.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mcore-linting-and-formatting .gemini/skills/mcore-linting-and-formatting && 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 "mcore-linting-and-formatting" agent skill from https://github.com/NVIDIA/Megatron-LM/tree/main/skills/mcore-linting-and-formatting into .gemini/skills/mcore-linting-and-formatting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcore-linting-and-formatting", 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/Megatron-LM mcore-linting-and-formattingInstalls 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/Megatron-LM --skill mcore-linting-and-formatting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/Megatron-LM.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mcore-linting-and-formatting .github/skills/mcore-linting-and-formatting && 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 "mcore-linting-and-formatting" agent skill from https://github.com/NVIDIA/Megatron-LM/tree/main/skills/mcore-linting-and-formatting into .github/skills/mcore-linting-and-formatting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcore-linting-and-formatting", 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/Megatron-LM --skill mcore-linting-and-formatting -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/Megatron-LM mcore-linting-and-formatting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/Megatron-LM.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mcore-linting-and-formatting .opencode/skills/mcore-linting-and-formatting && 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 "mcore-linting-and-formatting" agent skill from https://github.com/NVIDIA/Megatron-LM/tree/main/skills/mcore-linting-and-formatting into .opencode/skills/mcore-linting-and-formatting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcore-linting-and-formatting", 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
mcore-linting-and-formatting- GitHub stars
- 18k
- Token cost
- ~316 tokens
- SKILL.md length
- 66 words
- Files
- 5
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Runs the Megatron-LM autoformat script and its linting tools before a pull request, and keeps Python imports in order with isort.
- Preparing a Megatron-LM pull request
- SKILL.md covers Running the Formatter, Import Ordering, Setting Up the Linting Group and Code Style Rules
- Calls uv and bash
- Checking formatting without changing files before CI runs
What it does
Before opening a PR, the agent runs `tools/autoformat.sh` with environment variables such as `BASE_REF=main`, `CHECK_ONLY=true` and `SKIP_DOCS=false` for a check that applies no changes. The script invokes `black`, `isort`, `pylint`, `ruff` and `mypy`. After editing imports in any Python file, the agent runs `uv run isort` on those files before committing.
To prepare the tools inside the container, `uv sync --locked --only-group linting` installs `ruff`, `black`, `isort` and `pylint`, the same ones used by the autoformat script and by the linting job in CI. Code style rules are not repeated in the skill, which refers to the project's `style-guide.md`. The folder also holds evaluation files and a skill card.
When your agent uses it
- Preparing a Megatron-LM pull request
- Checking formatting without changing files before CI runs
- Fixing import order after editing Python files
Example prompts
- “Run the Megatron-LM formatter in check-only mode against main before I open a PR.”
- “I changed imports in two files, so sort them the way the repo expects.”
- “Set up the linting dependencies inside the container.”
Requirements
- A Megatron-LM checkout with `tools/autoformat.sh`
- uv
- The project's linting dependency group
What it can do on your machine
Read from SKILL.md and the folder at commit eb50202. 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
Shell commands in SKILL.md call:
uvbash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Megatron-LM Linting and Formatting loads about 316 tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 66 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/Megatron-LM at commit eb50202, republished under its Apache-2.0 licence (© NVIDIA). 66 words, ~316 tokens.
Download SKILL.mdSave it as
.claude/skills/mcore-linting-and-formatting/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- mcore-linting-and-formatting
- description
- Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules. Use when running linting or autoformat; fixing style violations before a PR; 'pre-commit fails', 'ruff error', 'isort', 'mypy', 'style violation', 'how do I format', 'autoformat.sh'.
- license
- Apache-2.0
- metadata.author
- Oliver Koenig <okoenig@nvidia.com>
Linting and Formatting
Running the Formatter
Run before opening a PR:
# Check mode (no changes applied)
BASE_REF=main CHECK_ONLY=true SKIP_DOCS=false bash tools/autoformat.sh
# Fix mode
BASE_REF=main CHECK_ONLY=false bash tools/autoformat.shTools invoked: black, isort, pylint, ruff, mypy.
Import Ordering
After editing imports in any Python files, always run uv run isort on those
files before committing:
uv run isort <file1>.py <file2>.pySetting Up the Linting Group
Inside the container:
uv sync --locked --only-group lintingThis installs ruff, black, isort, pylint — the same tools used by
tools/autoformat.sh and CI's linting job.
Code Style Rules
Follow style-guide.md.
© 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 4 other files in skills/mcore-linting-and-formatting of NVIDIA/Megatron-LM.
- SKILL.md
- BENCHMARK.md
- evals/evals.json
- skill-card.md
- skill.oms.sig
Open the folder on GitHubat commit eb50202
Compare with similar skills
Megatron-LM Linting and Formatting 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 |
|---|---|---|---|---|---|---|
| Megatron-LM Linting and Formatting this skillNVIDIA/Megatron-LM | 18k | — | ~316 | Automated safety check: Pass | Apache-2.0 | |
| Align Recipe pyproject.tomlgoogle/adk-recipes | 10k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Cb Code QualityBlkLeg/CircuitBreaker | 201 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Code Qualitynotque/vexjoy-agent | 439 | — | ~1.5k | Automated safety check: Notes | MIT | |
| ONNX Runtime Lintmicrosoft/onnxruntime | 22k | — | ~392 | Automated safety check: Pass | MIT | |
| Vibe Python Style Guidemistralai/mistral-vibe | 5.1k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Cb Code Quality
BlkLeg/CircuitBreaker
Circuit Breaker code conventions and the quality gates that actually block a push — ruff, mypy, eslint, the pytest coverage ratchet, and the make verify tiers.
Code Quality
notque/vexjoy-agent
Code quality: cleanup, linting, formatting, quality gates. An agent skill from notque/vexjoy-agent.
- Official
ONNX Runtime Lint
microsoft/onnxruntime
Lints and formats C++ and Python code in the ONNX Runtime repository with lintrunner, clang-format and ruff, preferring a pass over only the changed files.
- Official
Vibe Python Style Guide
mistralai/mistral-vibe
Python conventions for the Mistral Vibe codebase covering style, strict typing, imports, Pydantic patterns, logging, error handling and file I/O.
Plankton Code Quality
affaan-m/ECC
使用Plankton进行编写时代码质量强制执行——通过钩子在每次文件编辑时自动格式化、代码检查和Claude驱动的修复。
More from NVIDIA/Megatron-LM
All 14 skills in this repo- Official
Megatron-LM Container and Dependency Setup
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.
- Official
Megatron-LM Base Image Bump
NVIDIA/Megatron-LM
Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.
- Official
Megatron-LM CI/CD Guide
NVIDIA/Megatron-LM
Explains Megatron-LM's CI pipeline, PR scope labels, triggering the internal GitLab CI with a dry run first, and investigating CI failures.
- Official
Megatron-LM CI Failure Triage
NVIDIA/Megatron-LM
Investigates a failing GitHub Actions run or job for Megatron-LM, finds the root cause plus the PR and test author involved, and files a structured bug issue.
- Official
Megatron GPT to Hybrid Migration
NVIDIA/Megatron-LM
Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.
- Official
Megatron GB200 One-Node Test Onboarding
NVIDIA/Megatron-LM
Creates one-node GitHub merge-request variants of existing two-node GB200 functional tests in Megatron-LM, adjusting parallelism settings to fit four GPUs.
Related
Works with
Categories
Questions about Megatron-LM Linting and Formatting
What does Megatron-LM Linting and Formatting do?
Runs the Megatron-LM autoformat script and its linting tools before a pull request, and keeps Python imports in order with isort. sh` with environment variables such as `BASE_REF=main`, `CHECK_ONLY=true` and `SKIP_DOCS=false` for a check that applies no changes. The script invokes `black`, `isort`, `pylint`, `ruff` and `mypy`.
When should I use Megatron-LM Linting and Formatting?
Megatron-LM Linting and Formatting fits situations like: preparing a Megatron-LM pull request; checking formatting without changing files before CI runs; fixing import order after editing Python files.
How do I install Megatron-LM Linting and Formatting in Claude Code?
Run `npx skills add NVIDIA/Megatron-LM --skill mcore-linting-and-formatting -a claude-code`. Or copy the skill folder (skills/mcore-linting-and-formatting in NVIDIA/Megatron-LM) into .claude/skills/mcore-linting-and-formatting in your project. Claude Code loads it when a task matches its description.
How do I install Megatron-LM Linting and Formatting in Codex?
Run `npx skills add NVIDIA/Megatron-LM --skill mcore-linting-and-formatting -a codex`. Or copy the skill folder (skills/mcore-linting-and-formatting in NVIDIA/Megatron-LM) into .agents/skills/mcore-linting-and-formatting in your project. Codex loads it when a task matches its description.
Can I use Megatron-LM Linting and Formatting 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/Megatron-LM --skill mcore-linting-and-formatting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcore-linting-and-formatting, .gemini/skills/mcore-linting-and-formatting, .github/skills/mcore-linting-and-formatting and .opencode/skills/mcore-linting-and-formatting in your project.
What does Megatron-LM Linting and Formatting need to run?
Going by SKILL.md and its folder, Megatron-LM Linting and Formatting needs the command-line tools its instructions call (uv and bash). Our summary lists: A Megatron-LM checkout with `tools/autoformat.sh`; uv; The project's linting dependency group.
Does Megatron-LM Linting and Formatting access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Megatron-LM Linting and Formatting 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 Megatron-LM Linting and Formatting use?
Megatron-LM Linting and Formatting 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 Megatron-LM Linting and Formatting use?
About 316 tokens (SKILL.md is roughly 1.3k 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 Megatron-LM Linting and Formatting?
Skills that share tags, products or a category with Megatron-LM Linting and Formatting: Align Recipe pyproject.toml (google/adk-recipes, 10k stars), Cb Code Quality (BlkLeg/CircuitBreaker, 201 stars), Code Quality (notque/vexjoy-agent, 439 stars) and ONNX Runtime Lint (microsoft/onnxruntime, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Megatron-LM Linting and Formatting?
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/Megatron-LM, which has 18,094 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 2026.
Source: NVIDIA/Megatron-LM on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.