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.
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.
Install Safactory Workflows
$ npx skills add AI45Lab/SAfactory --skill safactory-workflows -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AI45Lab/SAfactory safactory-workflows --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/AI45Lab/SAfactory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/safactory-workflows .claude/skills/safactory-workflows && 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 "safactory-workflows" agent skill from https://github.com/AI45Lab/SAfactory/tree/v2/skills/safactory-workflows into .claude/skills/safactory-workflows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safactory-workflows", 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/AI45Lab/SAfactory/tree/v2/skills/safactory-workflowsType 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 AI45Lab/SAfactory --skill safactory-workflows -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AI45Lab/SAfactory safactory-workflows --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI45Lab/SAfactory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/safactory-workflows .agents/skills/safactory-workflows && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "safactory-workflows" agent skill from https://github.com/AI45Lab/SAfactory/tree/v2/skills/safactory-workflows into .agents/skills/safactory-workflows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safactory-workflows", 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 AI45Lab/SAfactory --skill safactory-workflows -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AI45Lab/SAfactory safactory-workflows --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI45Lab/SAfactory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/safactory-workflows .cursor/skills/safactory-workflows && 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 "safactory-workflows" agent skill from https://github.com/AI45Lab/SAfactory/tree/v2/skills/safactory-workflows into .cursor/skills/safactory-workflows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safactory-workflows", 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/AI45Lab/SAfactory.git --path skills/safactory-workflows--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 AI45Lab/SAfactory --skill safactory-workflows -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AI45Lab/SAfactory safactory-workflows --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI45Lab/SAfactory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/safactory-workflows .gemini/skills/safactory-workflows && 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 "safactory-workflows" agent skill from https://github.com/AI45Lab/SAfactory/tree/v2/skills/safactory-workflows into .gemini/skills/safactory-workflows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safactory-workflows", 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 AI45Lab/SAfactory safactory-workflowsInstalls 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 AI45Lab/SAfactory --skill safactory-workflows -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AI45Lab/SAfactory.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/safactory-workflows .github/skills/safactory-workflows && 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 "safactory-workflows" agent skill from https://github.com/AI45Lab/SAfactory/tree/v2/skills/safactory-workflows into .github/skills/safactory-workflows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safactory-workflows", 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 AI45Lab/SAfactory --skill safactory-workflows -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AI45Lab/SAfactory safactory-workflows --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI45Lab/SAfactory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/safactory-workflows .opencode/skills/safactory-workflows && 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 "safactory-workflows" agent skill from https://github.com/AI45Lab/SAfactory/tree/v2/skills/safactory-workflows into .opencode/skills/safactory-workflows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safactory-workflows", 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
safactory-workflows- GitHub stars
- 236
- Token cost
- ~1.8k tokens
- SKILL.md length
- 911 words
- Files
- 18 (incl. scripts, references, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
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.
- Works in 5 steps: Scaffold the fixed file set with… → Keep the protocol shell in runner.py… → Fill the task/start YAML templates with… → …
- SAfactory onboarding and runtime workflows
- SKILL.md covers Scope and intake, Template-based implementation, Standard reference: env/prmeval and Validation and completion, plus 1 more section
- Runs Python scripts from its folder; calls python
What it does
Safactory Workflows is an agent skill from 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. Use for SAfactory onboarding and runtime workflows.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts, reference files and assets (for example `assets/environment/adapter.py`, `assets/environment/rule_evaluator.py` and `assets/environment/runner.py`).
It sits in AI & LLM Engineering, covering Fine-tuning, Integration testing and Reinforcement learning. It works with Docker. The repository describes itself as: SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence.
When your agent uses it
- SAfactory onboarding and runtime workflows
- Tasks that involve Fine-tuning
- Tasks that involve Integration testing
Example prompts
- “/safactory-workflows”
Requirements
- Python 3
- Docker
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Scaffold the fixed file set with scripts/scaffold_environment.py (both Docker and RJob config pairs are always emitted; append…
- Keep the protocol shell in runner.py fixed — it is a standard part shared with env/prmeval; benchmark logic goes only in…
- Fill the task/start YAML templates with the image, dataset, workdir, mounts, and dependencies. agent_name must equal env_name; one row is…
- Create rule_evaluator.py only when evaluation is requested. Fill its score_metrics hook with the agreed normalization; keep the evaluator…
- Python is the default template language. If the native runtime needs Node/shell, retain a thin Python wrapper when possible. If another…
What it can do on your machine
Read from SKILL.md and the folder at commit a7726d1. 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
Ships 4 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python
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
Safactory Workflows loads about 1.8k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 911 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 911 words (~1,841 tokens).
“For environment onboarding, read references/environment-integration.md and docs/guides/custom-environment.md (or its Chinese translation). The guide defines the runtime contract; the assets/environment/ templates implement it. env/geo3k/ is only an example of multi-turn agent interaction, not a layout to copy — the standard reference…”
- name
- safactory-workflows
Files
SKILL.md and 17 other files (scripts, references, assets) in skills/safactory-workflows of AI45Lab/SAfactory.
- SKILL.md
- assets/environment/README.md.tmpl
- assets/environment/adapter.py
- assets/environment/config.rjob.yaml.tmpl
- assets/environment/config.yaml.tmpl
- assets/environment/request.smoke.json.tmpl
- assets/environment/rule_evaluator.py
- assets/environment/runner.py
- assets/environment/start.docker.yaml.tmpl
- assets/environment/start.rjob.yaml.tmpl
- references/docker-evaluation.md
- references/environment-integration.md
- references/grpo-training.md
- scripts/check_environment.py
- scripts/contract_smoke.py
- scripts/live_smoke.py
- scripts/scaffold_environment.py
- … and 1 more
Open the folder on GitHubat commit a7726d1
Compare with similar skills
Safactory Workflows 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 |
|---|---|---|---|---|---|---|
| Safactory Workflows this skillAI45Lab/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 | |
| Generate Openenv Envadithya-s-k/FineEnvs | 443 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Setup Workshop Nemoclawbrevdev/workshop-build-an-agent | 144 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Generate Ors Envadithya-s-k/FineEnvs | 443 | — | ~2.3k | Automated safety check: Notes | Apache-2.0 | |
| Verl Quickstartascend-ai-coding/awesome-ascend-skills | 174 | — | ~592 | Automated safety check: Pass | None |
Similar skills
Generate Openenv Env
adithya-s-k/FineEnvs
Builds an OpenEnv (Hugging Face) variant of an RL environment.
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.
Generate Ors Env
adithya-s-k/FineEnvs
Builds an Open Reward Standard (ORS) variant of an RL environment using the official openreward Python package.
Verl Quickstart
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).
Cb Build Test
BlkLeg/CircuitBreaker
How Circuit Breaker is built, tested, packaged, and kept secret-safe — the make dev/verify/test targets, the PostgreSQL integration test database and its fixtures, the mono Docker image and native…
Related
Works with
Categories
Questions about Safactory Workflows
What does Safactory Workflows do?
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. Safactory Workflows is an agent skill from 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.
When should I use Safactory Workflows?
Safactory Workflows fits situations like: SAfactory onboarding and runtime workflows; tasks that involve Fine-tuning; tasks that involve Integration testing.
How do I install Safactory Workflows in Claude Code?
Run `npx skills add AI45Lab/SAfactory --skill safactory-workflows -a claude-code`. Or copy the skill folder (skills/safactory-workflows in AI45Lab/SAfactory) into .claude/skills/safactory-workflows in your project. Claude Code loads it when a task matches its description.
How do I install Safactory Workflows in Codex?
Run `npx skills add AI45Lab/SAfactory --skill safactory-workflows -a codex`. Or copy the skill folder (skills/safactory-workflows in AI45Lab/SAfactory) into .agents/skills/safactory-workflows in your project. Codex loads it when a task matches its description.
Can I use Safactory Workflows 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 AI45Lab/SAfactory --skill safactory-workflows -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/safactory-workflows, .gemini/skills/safactory-workflows, .github/skills/safactory-workflows and .opencode/skills/safactory-workflows in your project.
What does Safactory Workflows need to run?
Going by SKILL.md and its folder, Safactory Workflows needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3; Docker.
Does Safactory Workflows 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 Safactory Workflows 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Safactory Workflows use?
No licence was found for Safactory Workflows or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Safactory Workflows use?
About 1.8k tokens (SKILL.md is roughly 7.4k 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 4.8k tokens, read only when the agent opens those files.
What are the alternatives to Safactory Workflows?
Skills that share tags, products or a category with Safactory Workflows: Generate Nemo Gym Env (adithya-s-k/FineEnvs, 443 stars), Generate Openenv Env (adithya-s-k/FineEnvs, 443 stars), Setup Workshop Nemoclaw (brevdev/workshop-build-an-agent, 144 stars) and Generate Ors Env (adithya-s-k/FineEnvs, 443 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Safactory Workflows?
AI45Lab (a GitHub organization) maintains it in AI45Lab/SAfactory, which has 236 GitHub stars. The repository was last updated on September 24, 2026.
Source: AI45Lab/SAfactory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.