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

Backend Patch Explorer

by AMD-AGI in 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…

Custom licenceAuto-check passed

Install Backend Patch Explorer

skills CLI
$ npx skills add AMD-AGI/Primus --skill backend-patch-explorer -a claude-code

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

GitHub CLI
$ gh skill install AMD-AGI/Primus backend-patch-explorer --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/backend-patch-explorer .claude/skills/backend-patch-explorer && 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
backend-patch-explorer
GitHub stars
131
Token cost
~3.5k tokens
SKILL.md length
1,668 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
Custom licence

At a glance

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…

  • Works in 5 steps: Classify the request and resolve the… → Discover the patch surface → Extract each patch's metadata from source → …
  • The user asks which patches a backend has
  • SKILL.md covers How patches work (enough to…, Workflow, Reaching into Primus-Turbo… and Output formats, plus 1 more section
  • Calls rg and python3

What it does

Backend Patch Explorer is an agent skill from 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, dependencies, and Primus-Turbo integration details, by reading the current repository code only. Use when the user asks which patches a backend has, wants a customer-facing patch table, asks how a specific patch or Primus-Turbo feature works (for example deepep, turbo attention, or FP8), or wants a reference guide to port a…

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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

  • The user asks which patches a backend has
  • Wants a customer-facing patch table
  • Asks how a specific patch
  • Primus-Turbo feature works (for example deepep

Example prompts

  • “/backend-patch-explorer”

Requirements

  • Python 3

Workflow steps

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

  1. Classify the request and resolve the backend
  2. Discover the patch surface
  3. Extract each patch's metadata from source
  4. Locate a specific feature by keyword
  5. Accuracy

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:

    • rg
    • 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 no API keys, tokens, secrets or passwords.

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

Context cost

Backend Patch Explorer loads about 3.5k tokens when it runs. Until then it costs about 160 tokens; SKILL.md has 1,668 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
~3.5k

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 1,668 words (~3,517 tokens).

“Primus does not fork its upstream training backends (Megatron-LM, TorchTitan, MaxText, and others). Instead it layers monkey-patches on top of them: each patch is registered with @register_patch, applied at a training-lifecycle phase by run_patches, and replaces or wraps an upstream…”

— opening of SKILL.md by AMD-AGI, Custom licence
name
backend-patch-explorer

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/backend-patch-explorer of AMD-AGI/Primus.

Open the folder on GitHubat commit 0f99649

Compare with similar skills

Backend Patch Explorer 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.

Backend Patch Explorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Backend Patch Explorer this skillAMD-AGI/Primus131—~3.5kAutomated safety check: PassCustom licence
Skill InspectorNVIDIA/SkillSpector20k1 repos~1.8kAutomated safety check: PassApache-2.0
LLM Torch Profiler Analysissgl-project/sglang37k2 repos~6.4kAutomated safety check: PassApache-2.0
Embeddings via 9Routerdecolua/9router30k—~604Automated safety check: PassMIT
NEAR AI Cloud Private Inferenceinternet-court/internet-court-skill6.4k2 repos~1.3kAutomated safety check: PassCustom licence
Nemoclaw Maintainer Normalize Title TagsNVIDIA/NemoClaw23k—~693Automated safety check: PassApache-2.0

Similar skills

  • Skill Inspector

    NVIDIA/SkillSpector

    Official

    Decides whether an agent skill is safe to install by combining a SkillSpector static scan with the agent's own source review, ending in APPROVE, CAUTION or REJECT.

    20k GitHub starsUsed in 1 repo~1.8k tokens
    SecurityAuto-check passed

  • LLM Torch Profiler Analysis

    sgl-project/sglang

    Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

    37k GitHub starsUsed in 2 repos~6.4k tokens
    DevelopmentAuto-check passed

  • Embeddings via 9Router

    decolua/9router

    Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

    30k GitHub stars~604 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

  • NEAR AI Cloud Private Inference

    internet-court/internet-court-skill

    Shows how to call NEAR AI Cloud through an OpenAI-compatible API and verify that inference ran in a TEE, using attestation checks and signed chat responses.

    6.4k GitHub starsUsed in 2 repos~1.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Nemoclaw Maintainer Normalize Title Tags

    NVIDIA/NemoClaw

    Official

    Remove bracketed NemoClaw tags from GitHub issue and PR titles.

    23k GitHub stars~693 tokensUpdated today
    Marketing & SEOAuto-check passed

  • Nemoclaw Contributor Update Dependencies

    NVIDIA/NemoClaw

    Official

    Audit and implement a NemoClaw dependency version upgrade, including Hermes and base images.

    23k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-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

  • 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

  • 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

Questions about Backend Patch Explorer

What does Backend Patch Explorer do?

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…. Backend Patch Explorer is an agent skill from 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, dependencies, and Primus-Turbo integration details, by reading the current repository code only.

When should I use Backend Patch Explorer?

Backend Patch Explorer fits situations like: the user asks which patches a backend has; wants a customer-facing patch table; asks how a specific patch; primus-Turbo feature works (for example deepep.

How do I install Backend Patch Explorer in Claude Code?

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

How do I install Backend Patch Explorer in Codex?

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

Can I use Backend Patch Explorer 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 backend-patch-explorer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/backend-patch-explorer, .gemini/skills/backend-patch-explorer, .github/skills/backend-patch-explorer and .opencode/skills/backend-patch-explorer in your project.

What does Backend Patch Explorer need to run?

Going by SKILL.md and its folder, Backend Patch Explorer needs the command-line tools its instructions call (rg and python3). Our summary lists: Python 3.

Does Backend Patch Explorer 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 Backend Patch Explorer 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 Backend Patch Explorer use?

Backend Patch Explorer 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 Backend Patch Explorer use?

About 3.5k tokens (SKILL.md is roughly 14k 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 Backend Patch Explorer?

Skills that share tags, products or a category with Backend Patch Explorer: Skill Inspector (NVIDIA/SkillSpector, 20k stars), LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Embeddings via 9Router (decolua/9router, 30k stars) and NEAR AI Cloud Private Inference (internet-court/internet-court-skill, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Backend Patch Explorer?

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.