Safactory Workflows
AI45Lab/SAfactory
Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training.
Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow).
Install Verl Quickstart
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills verl-quickstart --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/training/verl-quickstart .claude/skills/verl-quickstart && rm -rf skills-srcUse ~/.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/
Install the "verl-quickstart" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstart into .claude/skills/verl-quickstart/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verl-quickstart", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstartType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills verl-quickstart --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/training/verl-quickstart .agents/skills/verl-quickstart && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "verl-quickstart" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstart into .agents/skills/verl-quickstart/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verl-quickstart", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills verl-quickstart --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/training/verl-quickstart .cursor/skills/verl-quickstart && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "verl-quickstart" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstart into .cursor/skills/verl-quickstart/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verl-quickstart", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ascend-ai-coding/awesome-ascend-skills.git --path skills/training/verl-quickstart--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills verl-quickstart --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/training/verl-quickstart .gemini/skills/verl-quickstart && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "verl-quickstart" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstart into .gemini/skills/verl-quickstart/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verl-quickstart", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ascend-ai-coding/awesome-ascend-skills verl-quickstartInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/training/verl-quickstart .github/skills/verl-quickstart && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "verl-quickstart" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstart into .github/skills/verl-quickstart/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verl-quickstart", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills verl-quickstart --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/training/verl-quickstart .opencode/skills/verl-quickstart && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "verl-quickstart" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/verl-quickstart into .opencode/skills/verl-quickstart/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verl-quickstart", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
verl-quickstart- GitHub stars
- 174
- Token cost
- ~592 tokens
- SKILL.md length
- 112 words
- Files
- 8 (incl. references)
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- None found
At a glance
Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow).
- Works in 8 steps: Preflight: 检查是否有进程占用 NPU（必要时先释放） → Step 0: 环境/镜像 → Step 1: 数据处理（生成 parquet） → …
- Users mention verl
- SKILL.md covers 强约束, 最小输入变量 and 执行步骤
- Reaches quay.io
What it does
Verl Quickstart is an agent skill from ascend-ai-coding/awesome-ascend-skills. Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow). Use when users mention verl, quickstart, PPO/GRPO, gsm8k, run.sh, Ascend, or NPU training.
Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/checkpoint-merge.md`, `references/data-preprocess.md` and `references/docker-ascend.md`).
It sits in AI & LLM Engineering, covering Reinforcement learning, Runbooks and postmortems and Fine-tuning. It works with Docker and NVIDIA AI Platform. The repository describes itself as: A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/.
When your agent uses it
- Users mention verl
- Tasks that involve Reinforcement learning
- Tasks that involve Runbooks and postmortems
Example prompts
- “Use the verl-quickstart skill to generate an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image…”
- “/verl-quickstart”
Requirements
- Docker
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Preflight: 检查是否有进程占用 NPU（必要时先释放）
- Step 0: 环境/镜像
- Step 1: 数据处理（生成 parquet）
- Step 2: 模型准备（ModelScope + 路径规范）
- Step 3A: main_ppo 训练（按后端选择）
- Step 3B: examples 脚本训练与冒烟
- Step 4: checkpoint 合并
- FAQ / 排障
What it can do on your machine
Read from SKILL.md and the folder at commit 62a4ecb. 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 (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
quay.io
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
Verl Quickstart loads about 592 tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 112 words of instructions outside code blocks.
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 112 words (~592 tokens).
- name
- verl-quickstart
- keywords
- verl, rl, quickstart, ppo, grpo, gsm8k, ascend, npu, docker, 训练
Files
SKILL.md and 7 other files (references) in skills/training/verl-quickstart of ascend-ai-coding/awesome-ascend-skills.
- SKILL.md
- references/checkpoint-merge.md
- references/data-preprocess.md
- references/docker-ascend.md
- references/examples-scripts.md
- references/faq.md
- references/main-ppo-quickstart.md
- references/model-download.md
Open the folder on GitHubat commit 62a4ecb
Compare with similar skills
Verl Quickstart 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Verl Quickstart this skillascend-ai-coding/awesome-ascend-skills | 174 | — | ~592 | Automated safety check: Pass | None | |
| Safactory WorkflowsAI45Lab/SAfactory | 236 | — | ~1.8k | Automated safety check: Pass | None | |
| Generate Nemo Gym Envadithya-s-k/FineEnvs | 443 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Setup Workshop Nemoclawbrevdev/workshop-build-an-agent | 144 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Slime Useryzlnew/infra-skills | 149 | — | ~3.2k | Automated safety check: Pass | None | |
| slime RL Post-TrainingOrchestra-Research/AI-Research-SKILLs | 13k | 5 repos | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Generate Nemo Gym Env
adithya-s-k/FineEnvs
Builds a NeMo Gym (NVIDIA) variant of an RL environment. An agent skill from adithya-s-k/FineEnvs.
Setup Workshop Nemoclaw
brevdev/workshop-build-an-agent
Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.
Slime User
yzlnew/infra-skills
Guide for using SLIME (LLM post-training framework for RL Scaling).
slime RL Post-Training
Orchestra-Research/AI-Research-SKILLs
Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.
Nemotron Customizer Airgap
NVIDIA-NeMo/Nemotron
Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters.
More from ascend-ai-coding/awesome-ascend-skills
All 70 skills in this repoAscend Dmi
ascend-ai-coding/awesome-ascend-skills
当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景： - 查看 NPU 卡的状态、温度、利用率 - 测试内存带宽（h2d/d2h/d2d/p2p） - 跑算力/功耗基准测试（TFLOPS、TOPS） - 诊断 NPU 硬件故障或做健康检查 - 对 NPU 卡做压力测试（aicore、内存） - 复位/恢复卡住或异常的 NPU 卡 典型用户问题（即使不提…
Ascendc
ascend-ai-coding/awesome-ascend-skills
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.
Atc Model Converter
ascend-ai-coding/awesome-ascend-skills
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.
External Cannbot Ops Pypto Op Develop
ascend-ai-coding/awesome-ascend-skills
当需要编写 PyPTO 算子实现时使用此 skill。基于需求规格、设计方案和参考实现，生成完整可运行的 PyPTO 算子实现与配套测试、文档。Triggers: 实现算子、写 kernel、编写实现、写 impl、算子编码、开始编码、code the op、写 test、生成测试、写实现代码、op develop、kernel 实现。
External Gitcode Ascend Megatron Change Analyzer
ascend-ai-coding/awesome-ascend-skills
Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.
External Gitcode Ascend Megatron Commit Tracker
ascend-ai-coding/awesome-ascend-skills
Track and normalize change requests against the official Megatron-LM repository by branch, PR, commit, commit range, or time window.
Related
Works with
Categories
Questions about Verl Quickstart
What does Verl Quickstart do?
Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow). Verl Quickstart is an agent skill from ascend-ai-coding/awesome-ascend-skills.sh flow).
When should I use Verl Quickstart?
Verl Quickstart fits situations like: users mention verl; tasks that involve Reinforcement learning; tasks that involve Runbooks and postmortems.
How do I install Verl Quickstart in Claude Code?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a claude-code`. Or copy the skill folder (skills/training/verl-quickstart in ascend-ai-coding/awesome-ascend-skills) into .claude/skills/verl-quickstart in your project. Claude Code loads it when a task matches its description.
How do I install Verl Quickstart in Codex?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a codex`. Or copy the skill folder (skills/training/verl-quickstart in ascend-ai-coding/awesome-ascend-skills) into .agents/skills/verl-quickstart in your project. Codex loads it when a task matches its description.
Can I use Verl Quickstart 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 ascend-ai-coding/awesome-ascend-skills --skill verl-quickstart -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verl-quickstart, .gemini/skills/verl-quickstart, .github/skills/verl-quickstart and .opencode/skills/verl-quickstart in your project.
What does Verl Quickstart need to run?
SKILL.md names no scripts, command-line tools or credentials: Verl Quickstart is instructions for the agent only. Our summary lists: Docker.
Does Verl Quickstart access the network?
SKILL.md names 1 domain. In commands or code: quay.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Verl Quickstart 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 Verl Quickstart use?
No licence was found for Verl Quickstart or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Verl Quickstart use?
About 592 tokens (SKILL.md is roughly 2.4k 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 2.6k tokens, read only when the agent opens those files.
What are the alternatives to Verl Quickstart?
Skills that share tags, products or a category with Verl Quickstart: Safactory Workflows (AI45Lab/SAfactory, 236 stars), Generate Nemo Gym Env (adithya-s-k/FineEnvs, 443 stars), Setup Workshop Nemoclaw (brevdev/workshop-build-an-agent, 144 stars) and Slime User (yzlnew/infra-skills, 149 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Verl Quickstart?
ascend-ai-coding (a GitHub organization) maintains it in ascend-ai-coding/awesome-ascend-skills, which has 174 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 8, 2026.
Source: ascend-ai-coding/awesome-ascend-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.