菜单
Replace with a description of the skill and when Claude should use it. This should be one or two complete sentences explaining what the skill does and what triggers it.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
Unified GPU kernel operator generation and optimization skill. Automatically detects the target repository type (FlagGems, vLLM, or general Python/Triton) and dispatches to the appropriate specialized sub-skill. Includes operator generation, MCP-based iterative optimization, and feedback submission sub-skills. Use this skill when the user wants to generate or optimize a GPU kernel operator, create a Triton kernel, or says things like "generate an operator", "create a kernel for X", "optimize triton kernel", or "/kernelgen-flagos".
| name | template-skill |
| description | Replace with a description of the skill and when Claude should use it. This should be one or two complete sentences explaining what the skill does and what triggers it. |
| user-invokable | true |
| compatibility | Describe environment requirements here |
| metadata | {"version":"1.0.0","author":"flagos-ai","category":"replace-category","tags":["replace","with","relevant","tags"]} |
| allowed-tools | Bash(python3:*) Read Edit Write Glob Grep AskUserQuestion TaskCreate TaskUpdate TaskList TaskGet |
Brief explanation of:
-> Tell user: Status update
Explain what to do, with executable examples:
command --example
-> Tell user: Status update
Continue the workflow.
Verify the result:
verification_command
-> Tell user: Report results. On failure, diagnose and fix.
Example 1: Typical usage
User says: "/skill-name argument"
Actions:
1. Parse input
2. Execute workflow
3. Verify result
Result: Description of expected outcome
Example 2: Edge case
User says: "alternative trigger phrase"
Actions:
1. Handle the edge case
2. Adapt workflow accordingly
Result: Description of expected outcome
| Problem | Cause | Fix |
|---|---|---|
| Common error 1 | Typical cause | How to fix |
| Common error 2 | Typical cause | How to fix |