Iron Proxy Gateway for NanoClaw
nanocoai/nanoclaw
Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.
Canonical setup sequence for the Michelangelo local sandbox.
Install Ma Sandbox Setup
$ npx skills add michelangelo-ai/michelangelo --skill ma-sandbox-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install michelangelo-ai/michelangelo ma-sandbox-setup --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/michelangelo-ai/michelangelo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ma-sandbox-setup .claude/skills/ma-sandbox-setup && 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 "ma-sandbox-setup" agent skill from https://github.com/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setup into .claude/skills/ma-sandbox-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ma-sandbox-setup", 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/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setupType 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 michelangelo-ai/michelangelo --skill ma-sandbox-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install michelangelo-ai/michelangelo ma-sandbox-setup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michelangelo-ai/michelangelo.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ma-sandbox-setup .agents/skills/ma-sandbox-setup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ma-sandbox-setup" agent skill from https://github.com/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setup into .agents/skills/ma-sandbox-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ma-sandbox-setup", 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 michelangelo-ai/michelangelo --skill ma-sandbox-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install michelangelo-ai/michelangelo ma-sandbox-setup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michelangelo-ai/michelangelo.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ma-sandbox-setup .cursor/skills/ma-sandbox-setup && 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 "ma-sandbox-setup" agent skill from https://github.com/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setup into .cursor/skills/ma-sandbox-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ma-sandbox-setup", 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/michelangelo-ai/michelangelo.git --path .claude/skills/ma-sandbox-setup--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 michelangelo-ai/michelangelo --skill ma-sandbox-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install michelangelo-ai/michelangelo ma-sandbox-setup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michelangelo-ai/michelangelo.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ma-sandbox-setup .gemini/skills/ma-sandbox-setup && 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 "ma-sandbox-setup" agent skill from https://github.com/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setup into .gemini/skills/ma-sandbox-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ma-sandbox-setup", 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 michelangelo-ai/michelangelo ma-sandbox-setupInstalls 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 michelangelo-ai/michelangelo --skill ma-sandbox-setup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/michelangelo-ai/michelangelo.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ma-sandbox-setup .github/skills/ma-sandbox-setup && 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 "ma-sandbox-setup" agent skill from https://github.com/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setup into .github/skills/ma-sandbox-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ma-sandbox-setup", 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 michelangelo-ai/michelangelo --skill ma-sandbox-setup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install michelangelo-ai/michelangelo ma-sandbox-setup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michelangelo-ai/michelangelo.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ma-sandbox-setup .opencode/skills/ma-sandbox-setup && 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 "ma-sandbox-setup" agent skill from https://github.com/michelangelo-ai/michelangelo/tree/main/.claude/skills/ma-sandbox-setup into .opencode/skills/ma-sandbox-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ma-sandbox-setup", 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
ma-sandbox-setup- GitHub stars
- 118
- Token cost
- ~936 tokens
- SKILL.md length
- 344 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Canonical setup sequence for the Michelangelo local sandbox.
- Works in 5 steps: Install Python dependencies → Install the plugin extra (Ray + Spark —… → Activate the venv and create the sandbox → …
- Setting up a new dev machine
- SKILL.md covers Prereqs, Full ordered setup sequence, Key commands and Debugging tools, plus 2 more sections
- Calls poetry, brew and git
What it does
Ma Sandbox Setup is an agent skill from michelangelo-ai/michelangelo. Canonical setup sequence for the Michelangelo local sandbox. Use when setting up a new dev machine, diagnosing sandbox issues, or helping someone get unstuck during sandbox creation. Also applies when checking prereqs or explaining what each step does.
Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud. It works with Docker. The repository describes itself as: Michelangelo AI: Uber's end-to-end machine learning platform. The licence is Apache-2.0.
When your agent uses it
- Setting up a new dev machine
- Diagnosing sandbox issues
- Helping someone get unstuck during sandbox creation
Example prompts
- “/ma-sandbox-setup”
Requirements
- Python 3
- Docker
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 491a9b2. 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:
poetrybrewgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Ma Sandbox Setup loads about 936 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 344 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
The full file from michelangelo-ai/michelangelo at commit 491a9b2, republished under its Apache-2.0 licence (© michelangelo-ai). 344 words, ~936 tokens.
Download SKILL.mdSave it as
.claude/skills/ma-sandbox-setup/SKILL.md (or your agent's skills folder).- name
- ma-sandbox-setup
- description
- Canonical setup sequence for the Michelangelo local sandbox. Use when setting up a new dev machine, diagnosing sandbox issues, or helping someone get unstuck during sandbox creation. Also applies when checking prereqs or explaining what each step does.
- user-invocable
- true
Michelangelo Sandbox Setup Reference
Prereqs
Install the required tools if they are not already on your PATH:
brew install k3d # cluster manager (v5.x)
brew install helm # Kubernetes package manager
# kubectl comes with Docker Desktop, or: brew install kubectlVerify all five are on PATH before proceeding:
which k3d helm kubectl docker poetryIF any command prints "not found" or returns no output: STOP. Report which tools are missing and do not proceed to the next step.
Docker resource limits: Ensure your Docker runtime (Docker Desktop or Colima) has at least 4 CPUs, 8 GB memory, and 60 GB disk allocated, or pods will crash or fail to schedule.
Full ordered setup sequence
1. Install Python dependencies
cd <repo-root>/python
poetry installThis must be done before any ma CLI commands. If skipped, ma will fail with an import error because its Python dependencies aren't installed.
2. Install the plugin extra (Ray + Spark — optional)
Skip this if you're only doing UI or apiserver work. Required if you'll run or develop pipelines that use Ray or Spark compute:
poetry install --extras plugin3. Activate the venv and create the sandbox
REPO_ROOT=$(git rev-parse --show-toplevel)
source "$REPO_ROOT/python/.venv/bin/activate" # or prefix every command with: poetry run
ma sandbox create4. Seed demo data
cd "$REPO_ROOT/python"
poetry run ma sandbox demo pipelineThis creates the ma-dev-test project with training, eval, and trigger pipelines. Without this step the UI will load but show no data.
5. Verify
poetry run ma sandbox healthAll checks should pass. Then open http://localhost:8090 — navigate to the ma-dev-test project.
Key commands
| Command | What it does |
|---|---|
ma sandbox create | Create cluster + deploy all services |
ma sandbox sync | Restart app services in an existing cluster (fast, skips infra) |
ma sandbox health | Run health checks: cluster, pods, API resources, envoy, UI |
ma sandbox stop | Stop the cluster (preserves state) |
ma sandbox start | Resume a stopped cluster |
ma sandbox delete | Tear down cluster entirely |
ma sandbox demo pipeline | Deploy pipeline demo resources |
ma sandbox demo inference | Deploy inference server demo resources |
Debugging tools
If the UI loads but shows no data, or services aren't behaving as expected, use /ma-sandbox-debug.
Known gotchas
k3d 5.9.0 + k3s version — k3d 5.9.0 defaulted to k3s v1.35.5 (pre-release, broken). sandbox.py now pins rancher/k3s:v1.30.5-k3s1 explicitly. If you see the API server never come up after ma sandbox create, check that you're on a recent checkout.
cadence-schema-init / ingester-schema-init / sandbox-bucket-setup — these reach Completed status and stay there. That's expected.
Further reading
Full docs: docs/getting-started/sandbox-setup.md.
© michelangelo-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/ma-sandbox-setup of michelangelo-ai/michelangelo.
Open the folder on GitHubat commit 491a9b2
Compare with similar skills
Ma Sandbox Setup 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 |
|---|---|---|---|---|---|---|
| Ma Sandbox Setup this skillmichelangelo-ai/michelangelo | 118 | — | ~936 | Automated safety check: Pass | Apache-2.0 | |
| Iron Proxy Gateway for NanoClawnanocoai/nanoclaw | 31k | — | ~4.6k | Automated safety check: Notes | MIT | |
| GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb | 6.7k | — | ~4k | Automated safety check: Notes | Apache-2.0 | |
| Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit | 260 | 6 repos | ~1.1k | Automated safety check: Notes | Custom licence | |
| LangBot Deployment Guidelangbot-app/LangBot | 18k | — | ~1.2k | Automated safety check: Notes | Apache-2.0 | |
| Build Openshell Mxc WindowsNVIDIA/OpenShell | 16k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
GreptimeDB Dev Docker Image
GreptimeTeam/greptimedb
Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.
Senior DevOps Toolkit
maslennikov-ig/claude-code-orchestrator-kit
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…
LangBot Deployment Guide
langbot-app/LangBot
Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.
- Official
Build Openshell Mxc Windows
NVIDIA/OpenShell
Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64.
- Official
Megatron-LM Base Image Bump
NVIDIA/Megatron-LM
Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.
More from michelangelo-ai/michelangelo
All 9 skills in this repoMa Sandbox Debug
michelangelo-ai/michelangelo
Tail logs, inspect pods, and diagnose unhealthy services in a running Michelangelo sandbox.
Ma Sandbox Deploy
michelangelo-ai/michelangelo
Build a Go service binary, package it into a Docker image, import into k3d, and deploy via helm sync.
Ma Sandbox Test Plan
michelangelo-ai/michelangelo
Build, test, and verify a sandbox change across Go, JS, and Python.
Update Docs
michelangelo-ai/michelangelo
Update Michelangelo documentation. An agent skill from michelangelo-ai/michelangelo.
Ma Design Interview
michelangelo-ai/michelangelo
Structured interview for designing and implementing changes to the Michelangelo platform.
Ma Sandbox Reset
michelangelo-ai/michelangelo
Tear down the Michelangelo sandbox cluster and recreate it from scratch.
Related
Works with
Categories
Questions about Ma Sandbox Setup
What does Ma Sandbox Setup do?
Canonical setup sequence for the Michelangelo local sandbox. Ma Sandbox Setup is an agent skill from michelangelo-ai/michelangelo. Canonical setup sequence for the Michelangelo local sandbox.
When should I use Ma Sandbox Setup?
Ma Sandbox Setup fits situations like: setting up a new dev machine; diagnosing sandbox issues; helping someone get unstuck during sandbox creation.
How do I install Ma Sandbox Setup in Claude Code?
Run `npx skills add michelangelo-ai/michelangelo --skill ma-sandbox-setup -a claude-code`. Or copy the skill folder (.claude/skills/ma-sandbox-setup in michelangelo-ai/michelangelo) into .claude/skills/ma-sandbox-setup in your project. Claude Code loads it when a task matches its description.
How do I install Ma Sandbox Setup in Codex?
Run `npx skills add michelangelo-ai/michelangelo --skill ma-sandbox-setup -a codex`. Or copy the skill folder (.claude/skills/ma-sandbox-setup in michelangelo-ai/michelangelo) into .agents/skills/ma-sandbox-setup in your project. Codex loads it when a task matches its description.
Can I use Ma Sandbox Setup 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 michelangelo-ai/michelangelo --skill ma-sandbox-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ma-sandbox-setup, .gemini/skills/ma-sandbox-setup, .github/skills/ma-sandbox-setup and .opencode/skills/ma-sandbox-setup in your project.
What does Ma Sandbox Setup need to run?
Going by SKILL.md and its folder, Ma Sandbox Setup needs the command-line tools its instructions call (poetry, brew and git). Our summary lists: Python 3; Docker.
Does Ma Sandbox Setup access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Ma Sandbox Setup 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 Ma Sandbox Setup use?
Ma Sandbox Setup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ma Sandbox Setup use?
About 936 tokens (SKILL.md is roughly 3.7k 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 Ma Sandbox Setup?
Skills that share tags, products or a category with Ma Sandbox Setup: Iron Proxy Gateway for NanoClaw (nanocoai/nanoclaw, 31k stars), GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 260 stars) and LangBot Deployment Guide (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ma Sandbox Setup?
michelangelo-ai (a GitHub organization) maintains it in michelangelo-ai/michelangelo, which has 118 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 10, 2026.
Source: michelangelo-ai/michelangelo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.