New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Update Megatron Golden Values

by NVIDIA in NVIDIA/Megatron-LM

Refreshes stored golden values from a GitHub Actions run, reports signed percentage changes per model, and writes a summary ready for a pull request description.

OfficialCustom licenceAuto-check passedTesting & QA

Install Update Megatron Golden Values

skills CLI
$ npx skills add NVIDIA/Megatron-LM --skill update-golden-values -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA/Megatron-LM update-golden-values --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA/Megatron-LM.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/update-golden-values .claude/skills/update-golden-values && rm -rf skills-src

Use ~/.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/

Facts

Skill name
update-golden-values
GitHub stars
18k
Token cost
~2.8k tokens
SKILL.md length
815 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Custom licence

At a glance

Refreshes stored golden values from a GitHub Actions run, reports signed percentage changes per model, and writes a summary ready for a pull request description.

  • Works in 5 steps: Environment → Reset prior edits (only if user re-runs) → Download → …
  • Refreshing golden values after a CI workflow run changed expected results
  • SKILL.md covers Inputs to gather from the user, Workflow, Reading the columns and Notes & gotchas
  • Calls git, python and gh; needs GITHUB_TOKEN and RO_API_TOKEN

What it does

The skill refreshes the stored golden values for functional tests from a GitHub Actions workflow run, reports how much each model's metrics changed, and writes a summary ready for a pull request description. It orchestrates two scripts already in the repo: one downloads artifacts from the run and overwrites the `golden_values_*.json` files, the other diffs the working-tree goldens against git HEAD and reports each metric's signed average relative difference.

Before starting, the agent collects the workflow run ID and the scope: only-failing downloads from failing or cancelled jobs, for fixing broken tests, while all downloads from every job that produced golden values. If you do not say which, it asks rather than defaulting. The environment step derives GITHUB_TOKEN from the authenticated `gh` CLI for a single command, never exporting it for the whole shell or committing it, and reuses a Python virtual environment. A reset step discards earlier golden edits when you re-run. The excerpt ends before the download and summary steps.

When your agent uses it

  • Refreshing golden values after a CI workflow run changed expected results
  • Fixing failing functional tests by downloading goldens from failed jobs only
  • Producing a per-model percentage-change summary for a PR description

Example prompts

  • “Update the goldens from workflow run 25341543542, failing jobs only.”
  • “Refresh all golden values from this run ID and summarize the changes per model for the PR.”
  • “Generate a golden-value diff summary against HEAD for my PR description.”

Requirements

  • The gh CLI, authenticated, to derive a GitHub token
  • A Python virtual environment with the scripts' dependencies, including click
  • A checkout of the Megatron-LM repository

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Environment
  2. Reset prior edits (only if user re-runs)
  3. Download
  4. Relative-diff comparison
  5. Summary blurb

What it can do on your machine

Read from SKILL.md and the folder at commit d5fbb65. 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:

    • git
    • python
    • gh
    • python3
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, gh and pip, 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 these keys or tokens, usually read from environment variables:

    • GITHUB_TOKEN
    • RO_API_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Update Megatron Golden Values loads about 2.8k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 815 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 815 words (~2,796 tokens).

“End-to-end workflow for refreshing golden values from a GitHub Actions workflow run, reporting signed percentage changes per test/model environment, and writing a PR-ready summary.”

— opening of SKILL.md by NVIDIA, Custom licence
name
update-golden-values

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/update-golden-values of NVIDIA/Megatron-LM.

Open the folder on GitHubat commit d5fbb65

Compare with similar skills

Update Megatron Golden Values 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.

Update Megatron Golden Values compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Megatron Golden Values this skillNVIDIA/Megatron-LM18k—~2.8kAutomated safety check: PassCustom licence
Ghbubbuild/bub1.7k—~798Automated safety check: PassApache-2.0
Pypi ReleasealchemiststudiosDOTai/tunacode125—~2.2kAutomated safety check: PassMIT
GitHub Workflow AutomationFNOSP/FlyNarwhal4958 repos~5.4kAutomated safety check: PassAGPL-3.0
Update Dependenciesalorence/django-modern-rpc111—~1.3kAutomated safety check: PassMIT
Python Pypi Package Buildergithub/awesome-copilot40k1 repos~4.6kAutomated safety check: PassMIT

Similar skills

  • Gh

    bubbuild/bub

    GitHub CLI skill for interacting with GitHub via the gh command line tool.

    1.7k GitHub stars~798 tokensUpdated today
    DevelopmentAuto-check passed

  • Pypi Release

    alchemiststudiosDOTai/tunacode

    This skill should be used when releasing tunacode-cli to PyPI.

    125 GitHub stars~2.2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • GitHub Workflow Automation

    FNOSP/FlyNarwhal

    Automate GitHub workflows with AI assistance. An agent skill from FNOSP/FlyNarwhal.

    495 GitHub starsUsed in 8 repos~5.4k tokens
    DevOps & CloudAuto-check passed

  • Update Dependencies

    alorence/django-modern-rpc

    Routine update of all project dependencies — uv itself, uv.lock (all groups), tool versions pinned in GitHub workflows and .pre-commit-config.yaml (uv, ruff, mypy...), and SHA-pinned GitHub Actions.

    111 GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed

  • Python Pypi Package Builder

    github/awesome-copilot

    Official

    End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI.

    40k GitHub starsUsed in 1 repo~4.6k tokens
    DevelopmentAuto-check passed

  • Code Review

    Azure/sap-automation

    Official

    Review pull requests in the SAP Deployment Automation Framework.

    145 GitHub stars~7k tokensUpdated today
    DevelopmentAuto-check passed

More from NVIDIA/Megatron-LM

All 14 skills in this repo

  • Megatron Core Testing Guide

    NVIDIA/Megatron-LM

    Official

    Guide to the Megatron-LM test system: layout, recipe YAML, running and adding unit and functional tests, golden values, marker filters and CI parity.

    18k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

  • Megatron-LM Container and Dependency Setup

    NVIDIA/Megatron-LM

    Official

    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.

    18k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Megatron-LM Base Image Bump

    NVIDIA/Megatron-LM

    Official

    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.

    18k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Megatron-LM CI/CD Guide

    NVIDIA/Megatron-LM

    Official

    Explains Megatron-LM's CI pipeline, PR scope labels, triggering the internal GitLab CI with a dry run first, and investigating CI failures.

    18k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Megatron-LM CI Failure Triage

    NVIDIA/Megatron-LM

    Official

    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.

    18k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Megatron GPT to Hybrid Migration

    NVIDIA/Megatron-LM

    Official

    Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.

    18k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Update Megatron Golden Values

What does Update Megatron Golden Values do?

Refreshes stored golden values from a GitHub Actions run, reports signed percentage changes per model, and writes a summary ready for a pull request description. The skill refreshes the stored golden values for functional tests from a GitHub Actions workflow run, reports how much each model's metrics changed, and writes a summary ready for a pull request description.json` files, the other diffs the working-tree goldens against git HEAD and reports each metric's signed average relative difference.

When should I use Update Megatron Golden Values?

Update Megatron Golden Values fits situations like: refreshing golden values after a CI workflow run changed expected results; fixing failing functional tests by downloading goldens from failed jobs only; producing a per-model percentage-change summary for a PR description.

How do I install Update Megatron Golden Values in Claude Code?

Run `npx skills add NVIDIA/Megatron-LM --skill update-golden-values -a claude-code`. Or copy the skill folder (skills/update-golden-values in NVIDIA/Megatron-LM) into .claude/skills/update-golden-values in your project. Claude Code loads it when a task matches its description.

How do I install Update Megatron Golden Values in Codex?

Run `npx skills add NVIDIA/Megatron-LM --skill update-golden-values -a codex`. Or copy the skill folder (skills/update-golden-values in NVIDIA/Megatron-LM) into .agents/skills/update-golden-values in your project. Codex loads it when a task matches its description.

Can I use Update Megatron Golden Values 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 update-golden-values -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-golden-values, .gemini/skills/update-golden-values, .github/skills/update-golden-values and .opencode/skills/update-golden-values in your project.

What does Update Megatron Golden Values need to run?

Going by SKILL.md and its folder, Update Megatron Golden Values needs the command-line tools its instructions call (git, python, gh, python3 and pip) and credentials named GITHUB_TOKEN and RO_API_TOKEN. Our summary lists: The gh CLI, authenticated, to derive a GitHub token; A Python virtual environment with the scripts' dependencies, including click; A checkout of the Megatron-LM repository.

Does Update Megatron Golden Values access the network?

SKILL.md contains no URLs. Its commands use git, gh and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Update Megatron Golden Values 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 Update Megatron Golden Values use?

Update Megatron Golden Values has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Update Megatron Golden Values use?

About 2.8k tokens (SKILL.md is roughly 11k 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 Update Megatron Golden Values?

Skills that share tags, products or a category with Update Megatron Golden Values: Gh (bubbuild/bub, 1.7k stars), Pypi Release (alchemiststudiosDOTai/tunacode, 125 stars), GitHub Workflow Automation (FNOSP/FlyNarwhal, 495 stars) and Update Dependencies (alorence/django-modern-rpc, 111 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Megatron Golden Values?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/Megatron-LM, which has 18,083 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 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.