By flagos-ai
Automate multi-chip GPU AI inference workflows on the FlagOS platform: kernel generation and review, model migration from upstream vLLM, containerized stack installation and environment verification, and end-to-end performance benchmarking across NVIDIA, AMD, Ascend, and other hardware backends.
This skill should be used when reviewing FlagGems operator PRs, performing code review, self-reviewing before submission, or when the user mentions "review PR", "审PR", "代码review", "code review", "review #123", "self-review", "自审", "检查PR", "审查算子", "review operator". It fetches PR diffs, applies FlagGems domain-specific review rules (structural checks, naming, registration, tests, benchmarks), and posts inline review comments directly on GitHub.
This skill should be used when submitting FlagGems operator PRs, reviewing operator code before submission, preparing operator code for PR, or when the user mentions "提PR", "提交算子", "submit operator", "PR提交", "代码审核", "pre-commit". It automates code review, validates completeness and compliance, runs pre-commit and worktree tests, and directly submits PR to upstream with full description including speedup data.
Full FlagRelease pipeline orchestrator. Runs the complete LLM deployment, verification, and benchmarking pipeline for multi-chip GPU backends. Executes: install-stack → env-verify → model-verify → perf-test in sequence, passing state between steps and producing a final structured report. Assumes gpu-container-setup (Step 1) is already done — a running container with PyTorch + GPU access must exist.
Automatically detect GPU vendor, find appropriate PyTorch container image, launch with correct mounts, and validate GPU functionality. Supports NVIDIA, Ascend, Metax, Iluvatar, and AMD/ROCm. Use when user says "setup container", "start pytorch container", or invokes /gpu-container-setup.
Install the 5-package multi-chip software stack (vLLM, FlagTree, FlagGems, FlagCX, vllm-plugin-FL) inside a GPU container. Handles network mirror detection, dependency ordering, wheel selection, and per-package validation. Use after gpu-container-setup has produced a running container with PyTorch + GPU access.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
FlagOS is a fully open-source AI system software stack for heterogeneous AI chips, allowing AI models to be developed once and seamlessly ported to a wide range of AI hardware with minimal effort. This repository collects reusable Skills for FlagOS — injecting domain knowledge, workflow standards, and best practices into AI coding agents.
Skills are folder-based capability packages: each skill uses documentation, scripts,
and resources to teach agents to reliably and reproducibly complete tasks in a specific domain.
Each skill folder contains a SKILL.md file with YAML frontmatter (name + description)
followed by detailed agent instructions.
Skills can also include reference docs, scripts, and assets.
This repository follows the Agent Skills open standard.
FlagOS Skills are compatible with Claude Code, Cursor, Codex, and any agent supporting the Agent Skills standard.
Use the skills CLI to install skills directly — no cloning needed:
# List available skills in this repository
npx skills add flagos-ai/skills --list
# Install a specific skill into your project
npx skills add flagos-ai/skills --skill model-migrate-flagos
# Install a specific skill globally (user-level)
npx skills add flagos-ai/skills --skill model-migrate-flagos --global
# Install all skills at once
npx skills add flagos-ai/skills --all
# Install for specific agents only
npx skills add flagos-ai/skills --agent claude-code cursor
Other useful commands:
npx skills list # List installed skills
npx skills find # Search for skills interactively
npx skills update # Update all skills to latest versions
npx skills remove # Interactive remove
Note: No prior installation needed —
npxdownloads theskillsCLI automatically.
Register the repository as a plugin marketplace (in Claude Code interactive mode):
/plugin marketplace add flagos-ai/skills
Or from the terminal:
claude plugin marketplace add flagos-ai/skills
Install skills:
/plugin install flagos-skills@flagos-skills
Or from the terminal:
claude plugin install flagos-skills@flagos-skills
After installation, mention the skill in your prompt — Claude automatically
loads the corresponding SKILL.md instructions.
This repository includes Cursor plugin manifests (.cursor-plugin/plugin.json
and .cursor-plugin/marketplace.json).
Install from the repository URL or local checkout via the Cursor plugin flow.
Use the $skill-installer inside Codex:
$skill-installer install model-migrate-flagos from flagos-ai/skills
Or provide the GitHub directory URL:
$skill-installer install https://github.com/flagos-ai/skills/tree/main/skills/model-migrate-flagos
Alternatively, copy skill folders into Codex's standard .agents/skills location:
cp -r skills/model-migrate-flagos $REPO_ROOT/.agents/skills/
See the Codex Skills guide for more details.
gemini extensions install https://github.com/flagos-ai/skills.git --consent
This repo includes gemini-extension.json and agents/AGENTS.md for Gemini CLI integration.
See Gemini CLI extensions docs for more help.
For any agent that supports the Agent Skills standard,
point it at the skills/ directory in this repository.
Each skill is self-contained with a SKILL.md entry point.
The agents/AGENTS.md file can also be used as a fallback for agents that don't support skills natively.
npx claudepluginhub flagos-ai/skills --plugin flagos-skillsSkills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces, choose a path, validate your setup, and build practical NVIDIA-powered workflows.
Run AI models locally with Ollama - free alternative to OpenAI, Anthropic, and other paid LLM APIs. Zero-cost, privacy-first AI infrastructure.
TrueFoundry AI Gateway plugin — onboarding, model routing, MCP servers, prompts, Skills Registry workflows, observability, guardrails, and codebase migration. Works across Claude Code, Codex, and Cursor.
🤖 AI Engineer — AI Engineer + LLM Systems Specialist
从 gitcode-ascend 同步的 Ascend 技能集,包含 91 个技能: - analyse-coverage: 分析测试覆盖率盲区,生成覆盖率分析报告 - arxiv-recommendation-npu: 自动化推荐系统论文发现流水线。抓取 arxiv 推荐论文,检测源码,生成待迁移任务清单,由 npu-model-migration skill 完成 NPU 适配。 - ascend-inference-repos-copilot: 昇腾(Ascend)推理生态开源代码仓库智能问答专家旨在为 vLLM、vLLM-Ascend、MindIE-LLM、MindIE-SD、MindIE-Motor、MindIE-Turbo 以及 msM - ... 等 88 个技能
ML engineering plugin: Give your AI coding agent ML engineering superpowers.