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

Agent skill

Convergence Test

by AMD-AGI in 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…

Custom licenceAuto-check passedAI & LLM Engineering

Install Convergence Test

skills CLI
$ npx skills add AMD-AGI/Primus --skill convergence-test -a claude-code

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

GitHub CLI
$ gh skill install AMD-AGI/Primus convergence-test --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/convergence-test .claude/skills/convergence-test && 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
convergence-test
GitHub stars
131
Token cost
~2.1k tokens
SKILL.md length
1,156 words
Files
2
Skills in repo
9
Repo updated
First seen
Licence
Custom licence

At a glance

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…

  • Works in 5 steps: Read the request → Plan → Tell the user, then start → …
  • The user asks to run
  • SKILL.md covers 1. Read the request, 2. Plan, 3. Tell the user, then start and 4. Watch it, plus 2 more sections
  • Calls python3; needs HF_TOKEN

What it does

Convergence Test is an agent skill from 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 for llama2 7B fp8 on c4 with image rocm/primus:v26.7". Covers Megatron and MaxText, bundled recipes or configs generated from the model's example config, Hugging Face or local datasets, docker images, time budgets, baselines and result locations. Use when the user asks to run, start, check, stop or compare a…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `reference.md`).

It sits in AI & LLM Engineering, covering Model hubs and datasets, Plain language and style rules and Containers. It works with NVIDIA AI Platform, Docker and Hugging Face. 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

  • The user asks to run
  • Compare a convergence test
  • Accuracy regression run
  • Asks whether a model

Example prompts

  • “/convergence-test”

Requirements

  • Python 3
  • Docker

Workflow steps

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

  1. Read the request
  2. Plan
  3. Tell the user, then start
  4. Watch it
  5. Report

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

    Shell commands in SKILL.md call:

    • python3

    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 these keys or tokens, usually read from environment variables:

    • HF_TOKEN

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

Context cost

Convergence Test loads about 2.1k tokens when it runs. Until then it costs about 160 tokens; SKILL.md has 1,156 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~160
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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 1,156 words (~2,097 tokens).

“The user names a model and, optionally, a dataset, a docker image and a few other things; you plan the run with a script, launch it in the background, keep an eye on it, and report the verdict. The tool…”

— opening of SKILL.md by AMD-AGI, Custom licence
name
convergence-test

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/convergence-test of AMD-AGI/Primus.

  • SKILL.md
  • reference.md

Open the folder on GitHubat commit 0f99649

Compare with similar skills

Convergence Test 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.

Convergence Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Convergence Test this skillAMD-AGI/Primus131—~2.1kAutomated safety check: PassCustom licence
Generate Openenv Envadithya-s-k/FineEnvs443—~2.4kAutomated safety check: PassApache-2.0
Vllm Deploy Dockervllm-project/vllm-skills103—~2.5kAutomated safety check: NotesApache-2.0
Tao Port Huggingface ModelNVIDIA/skills3.5k—~4.5kAutomated safety check: NotesApache-2.0
Runpodericrisco/rsc-harness167—~2.8kAutomated safety check: PassMIT
Nemo Evaluator SDKOrchestra-Research/AI-Research-SKILLs13k3 repos~3.1kAutomated safety check: PassMIT

Similar skills

  • Generate Openenv Env

    adithya-s-k/FineEnvs

    Builds an OpenEnv (Hugging Face) variant of an RL environment.

    443 GitHub stars~2.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Vllm Deploy Docker

    vllm-project/vllm-skills

    Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.

    103 GitHub stars~2.5k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Tao Port Huggingface Model

    NVIDIA/skills

    Official

    Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

    3.5k GitHub stars~4.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

  • Runpod

    ericrisco/rsc-harness

    A skill your agent uses when running GPU compute on RunPod and deciding between Pods (hourly, always-on) and Serverless (per-second, autoscaling) for training, fine-tuning or inference — serverless…

    167 GitHub stars~2.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Nemo Evaluator SDK

    Orchestra-Research/AI-Research-SKILLs

    Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.

    13k GitHub starsUsed in 3 repos~3.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Spaces Deploy

    Vincentqyw/image-matching-webui

    Releases a new imcui version on GitHub, then deploys it to a test and a production Hugging Face Space from a dedicated huggingface branch.

    1.3k GitHub stars~721 tokensUpdated 2 days ago
    DevOps & CloudAuto-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

  • Backend Patch Explorer

    AMD-AGI/Primus

    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

  • 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

  • Slurm Training Node Validation

    AMD-AGI/Primus

    Validate SLURM cluster nodes by running actual training jobs in groups.

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

  • Port Validation Guide

    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)…

    131 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Convergence Test

What does Convergence Test do?

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…. Convergence Test is an agent skill from AMD-AGI/Primus.7".

When should I use Convergence Test?

Convergence Test fits situations like: the user asks to run; compare a convergence test; accuracy regression run; asks whether a model.

How do I install Convergence Test in Claude Code?

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

How do I install Convergence Test in Codex?

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

Can I use Convergence Test 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 convergence-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/convergence-test, .gemini/skills/convergence-test, .github/skills/convergence-test and .opencode/skills/convergence-test in your project.

What does Convergence Test need to run?

Going by SKILL.md and its folder, Convergence Test needs the command-line tools its instructions call (python3) and credentials named HF_TOKEN. Our summary lists: Python 3; Docker.

Does Convergence Test 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 Convergence Test 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 Convergence Test use?

Convergence Test 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 Convergence Test use?

About 2.1k tokens (SKILL.md is roughly 8.4k 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 Convergence Test?

Skills that share tags, products or a category with Convergence Test: Generate Openenv Env (adithya-s-k/FineEnvs, 443 stars), Vllm Deploy Docker (vllm-project/vllm-skills, 103 stars), Tao Port Huggingface Model (NVIDIA/skills, 3.5k stars) and Runpod (ericrisco/rsc-harness, 167 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Convergence Test?

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.