Agent skill

Port Validation Guide

by AMD-AGI in AMD-AGI/Primus

Generate a validation plan and test scaffolding to check a Primus optimization that has been ported into a user's own training framework, across correctness (numerical accuracy vs a reference)…

Custom licenceAuto-check passedTesting & QA

Install Port Validation Guide

skills CLI
$ npx skills add AMD-AGI/Primus --skill port-validation-guide -a claude-code

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

GitHub CLI
$ gh skill install AMD-AGI/Primus port-validation-guide --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/AMD-AGI/Primus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/port-validation-guide .claude/skills/port-validation-guide && 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
port-validation-guide
GitHub stars
131
Token cost
~1.5k tokens
SKILL.md length
745 words
Files
2 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
Custom licence

At a glance

Generate a validation plan and test scaffolding to check a Primus optimization that has been ported into a user's own training framework, across correctness (numerical accuracy vs a reference)…

  • Works in 6 steps: Gather the port facts → Choose the reference (oracle) → Correctness (numerical accuracy) → …
  • Wants a structured way to verify the port
  • SKILL.md covers Inputs to confirm with the user, Workflow, Output and Additional resources
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Port Validation Guide is an agent skill from AMD-AGI/Primus. Generate a validation plan and test scaffolding to check a Primus optimization that has been ported into a user's own training framework, across correctness (numerical accuracy vs a reference), performance (throughput parity), and integration (no regressions). Use after porting a Primus or Primus-Turbo feature into Megatron-LM, TorchTitan, MaxText, or another framework when the user wants a structured way to verify the port. Produces plans and test skeletons only; it does not run tests, require a GPU, or…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/test-templates.md`).

It sits in Testing & QA, covering Test generation. It works with NVIDIA AI Platform. The repository describes itself as: A flexible and high-performance training framework designed for large-scale foundation model training on AMD GPUs.

When your agent uses it

  • Wants a structured way to verify the port
  • Tasks that involve Test generation

Example prompts

  • “/port-validation-guide”

Workflow steps

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

  1. Gather the port facts
  2. Choose the reference (oracle)
  3. Correctness (numerical accuracy)
  4. Performance (throughput parity)
  5. Integration (no regressions)
  6. Assemble

What it can do on your machine

Read from SKILL.md and the folder at commit 0f99649. 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.

    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

Port Validation Guide loads about 1.5k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 140 tokens; SKILL.md has 745 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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 745 words (~1,458 tokens).

“After a Primus optimization is ported into a user's own framework, this skill produces a validation plan and test scaffolding across three tiers: correctness (numerical accuracy), performance (throughput parity), and integration (no regressions).”

— opening of SKILL.md by AMD-AGI, Custom licence
name
port-validation-guide

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in skills/port-validation-guide of AMD-AGI/Primus.

  • SKILL.md
  • references/test-templates.md

Open the folder on GitHubat commit 0f99649

Compare with similar skills

Port Validation Guide 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.

Port Validation Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Port Validation Guide this skillAMD-AGI/Primus131—~1.5kAutomated safety check: PassCustom licence
Megatron GB200 One-Node Test OnboardingNVIDIA/Megatron-LM18k—~1.3kAutomated safety check: PassApache-2.0
Hsb TestNVIDIA/skills3.5k—~4.2kAutomated safety check: NotesApache-2.0
Write and Verify Playwright Testsappsmithorg/appsmith41k—~2.9kAutomated safety check: NotesApache-2.0
Adk Verify Snippetsgoogle/adk-python22k—~1.4kAutomated safety check: PassApache-2.0
Engine E2Ewix/react-native-navigation13k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    Creates one-node GitHub merge-request variants of existing two-node GB200 functional tests in Megatron-LM, adjusting parallelism settings to fit four GPUs.

    18k GitHub stars~1.3k tokensUpdated today
    Testing & QAAuto-check passed
  • Hsb Test

    NVIDIA/skills

    Official

    Execute QA test plans on Holoscan Sensor Bridge hardware. An agent skill from NVIDIA/skills.

    3.5k GitHub stars~4.2k tokensUpdated today
    Testing & QAAuto-check: notes
  • Writes a Playwright end-to-end test from a prompt, runs it against a live Appsmith deployment and retries with fixes up to three times until it passes.

    41k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check: notes
  • Adk Verify Snippets

    google/adk-python

    Official

    Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail…

    22k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Engine E2E

    wix/react-native-navigation

    Official

    Run Wix Engine (mobile-apps-engine) iOS E2E tests locally to validate RNN changes.

    13k GitHub stars~1.1k tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • Hermetic Python Unit Tests

    dimensionalOS/dimos

    Rules for writing, fixing and reviewing pytest unit tests that are hermetic: behavior-focused, deterministic, isolated and cheap to run.

    4.6k GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed

More from AMD-AGI/Primus

All 9 skills in this repo
  • Spur Cluster Status

    AMD-AGI/Primus

    Inspect the current Spur (AMD SLURM-compatible) cluster node-allocation state and produce a Markdown report (optionally rendered to a standalone HTML page) covering the caller's account/QoS…

    131 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Backend Gap Report

    AMD-AGI/Primus

    Compare a Primus backend against an upstream repository or reference, verify git state, dependencies, directory changes, and integration coupling, then generate comparison reports, dashboard…

    131 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Inventory and explain the patch (monkey-patch) optimizations Primus layers over upstream training backends such as Megatron-LM, TorchTitan, and MaxText, including their version compatibility…

    131 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Convergence Test

    AMD-AGI/Primus

    Run, monitor, stop and report Primus convergence tests -- training a model on a real corpus and checking that the loss curve is healthy -- from a plain-language request such as "run convergence test…

    131 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Release Docs Update

    AMD-AGI/Primus

    Update the Primus documentation for a monthly training-image release — bump version references, realign the bare-metal install scripts with the release Dockerfiles, record the published image stacks…

    131 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Validate SLURM cluster nodes by running actual training jobs in groups.

    131 GitHub stars~3.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Port Validation Guide

What does Port Validation Guide do?

Generate a validation plan and test scaffolding to check a Primus optimization that has been ported into a user's own training framework, across correctness (numerical accuracy vs a reference)…. Port Validation Guide is an agent skill from AMD-AGI/Primus. Generate a validation plan and test scaffolding to check a Primus optimization that has been ported into a user's own training framework, across correctness (numerical accuracy vs a reference), performance (throughput parity), and integration (no regressions).

When should I use Port Validation Guide?

Port Validation Guide fits situations like: wants a structured way to verify the port; tasks that involve Test generation.

How do I install Port Validation Guide in Claude Code?

Run `npx skills add AMD-AGI/Primus --skill port-validation-guide -a claude-code`. Or copy the skill folder (skills/port-validation-guide in AMD-AGI/Primus) into .claude/skills/port-validation-guide in your project. Claude Code loads it when a task matches its description.

How do I install Port Validation Guide in Codex?

Run `npx skills add AMD-AGI/Primus --skill port-validation-guide -a codex`. Or copy the skill folder (skills/port-validation-guide in AMD-AGI/Primus) into .agents/skills/port-validation-guide in your project. Codex loads it when a task matches its description.

Can I use Port Validation Guide 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 AMD-AGI/Primus --skill port-validation-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/port-validation-guide, .gemini/skills/port-validation-guide, .github/skills/port-validation-guide and .opencode/skills/port-validation-guide in your project.

What does Port Validation Guide need to run?

SKILL.md names no scripts, command-line tools or credentials: Port Validation Guide is instructions for the agent only.

Does Port Validation Guide 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 Port Validation Guide 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 Port Validation Guide use?

Port Validation Guide 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 Port Validation Guide use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Port Validation Guide?

Skills that share tags, products or a category with Port Validation Guide: Megatron GB200 One-Node Test Onboarding (NVIDIA/Megatron-LM, 18k stars), Hsb Test (NVIDIA/skills, 3.5k stars), Write and Verify Playwright Tests (appsmithorg/appsmith, 41k stars) and Adk Verify Snippets (google/adk-python, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Port Validation Guide?

AMD-AGI (a GitHub organization) maintains it in AMD-AGI/Primus, which has 131 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.

Source: AMD-AGI/Primus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.