shipyard-sandbox
A guide that introduces available Python libraries, tools, and resources in the sandboxed environment for various tasks such as file manipulation, PDF processing, data analysis, and more. Use this guide to understand the capabilities of the sandbox and how to leverage them effectively.
agent-repo-init
One-click initialization of a multi-agent repository from the Antigravity template. Use this skill when users want to scaffold a new project quickly (`quick` mode) or with runtime defaults (`full` mode) including LLM provider profile, MCP toggle, swarm preference context, sandbox type, and optional git init.
bzfs-experimental-script-generator
Generate or change idiomatic minimal Bash and Python scripts that use bzfs and bzfs_jobrunner for ZFS snapshot management workflows in a sandboxed test VM: snapshot creation, replication/backup, restore rehearsal, snapshot pruning, snapshot monitoring, and snapshot list comparison. Use when asked to create or change ad hoc/manual or periodic/automatic scripts for these tasks. Do not use this skill for general ZFS administration or non-bzfs tooling.
Mcp Reverse Engineering
A sandboxed MCP tool for reverse engineering with multiple tool integrations
getdesign
Generate a grounded, production-grade `design.md` for any public URL using the coding agent's own tools. This skill is the portable twin of the hosted [getdesign.app](https://getdesign.app) agent â same 9-section output, no sandbox required.
flue
Work with Flue, the sandbox agent framework for OpenCode. Use when asked to "install Flue", "set up Flue", "create a Flue workflow", "add a workflow", "deploy to GitHub Actions", or "run agents in CI".
Io.Github.Gradion Ai/Ipybox
An MCP server for sandboxed Python code execution with IPython and Docker, and file transfer.
add-agent
Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.
RLM Tools
Persistent Python sandbox for token-efficient codebase exploration in MCP clients
config-hardener
Audit and harden your OpenClaw configuration. Checks AGENTS.md, gateway settings, sandbox config, and permission policies for security weaknesses.
using-wt
Manages git worktree-based sandboxes with the wt CLI tool, both locally and on remote hosts over SSH. Use when the user wants to create, enter, run commands in, list, remove, or manage isolated worktree sandboxes, configure remote hosts, or troubleshoot wt issues.
claude-agent-ruby
Implement or modify Ruby code that uses the claude-agent-sdk gem, including query() one-shot calls, Client-based interactive sessions, streaming input, option configuration, tools/permissions, hooks, SDK MCP servers, structured output, budgets, sandboxing, betas/tools presets, control-timeout handling, session resumption/rewind, session browsing (list_sessions/get_session_messages), task lifecycle messages, MCP server control (reconnect/toggle/stop), Rails integration, and error handling.
symbiont
AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, CommunicationPolicyGate for inter-agent governance, ToolClad declarative tool contracts, knowledge bridge, zero-trust security, multi-tier sandboxing, webhook verification, markdown memory, skill scanning, metrics, scheduling, symbi init/run/up CLI, and a declarative DSL
agent-smoke-e2e
End-to-end smoke check of the moraine MCP server. Exercises every MCP tool against a live moraine stack and prints a per-tool PASS/FAIL matrix. Use inside the dev sandbox after a fresh build to confirm the MCP binary actually serves its tools and returns shaped responses.
sv
This skill should be used when the user invokes `/sv` or asks to "hand this off to sandvault", "continue in the sandbox", "sandvault this task", or to clone the current repo into a sandboxed Claude session with per-repo deploy-key access. Writes a task briefing to the sandvault shared workspace and launches `sv-clone` in a new terminal window, pointing the sandboxed Claude at the briefing as its first prompt.
Runno
MCP Server for the Runno Sandbox
e2b-code-interpreter
Execute code in E2B sandboxes and integrate with LLMs for tool calling. Use when building AI agents that need to run Python/JS code, analyze data, generate charts, or use LLM function calling with E2B.
Python Exec Sandbox
Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.
hacker
Red team agent for vm2 sandbox escape testing. Systematically attempts to break out of the vm2 JavaScript sandbox by exploiting known and novel attack vectors. Use this skill whenever the user makes changes to vm2's sandbox code (bridge.js, setup-sandbox.js, setup-node-sandbox.js, vm.js, nodevm.js, transformer.js) and wants to verify the sandbox still holds. Also use when the user asks to "hack", "attack", "test security", "try to escape", "red team", or "pentest" the sandbox. Trigger on any request to find sandbox escapes or verify sandbox integrity.
Flow Nexus
Cloud-powered AI platform with multi-agent swarms, sandboxes, and workflow automation
sandbox
Execute commands in isolated sandboxes for security. Use when running untrusted code, system commands, or operations that could affect the host system. Automatically detects the right runtime (Python, Node, Rust, Go, Ruby, etc.) from the command.
Browser Automation with dev-browser
dev-browser is a CLI that controls browsers using sandboxed JavaScript scripts. Scripts run in a QuickJS WASM sandbox (not Node.js) with Playwright Page API access plus dev-browser extensions (notably `snapshotForAI()`). Pages persist between script runs via named handles, enabling incremental multi
awrshift
Adaptive decision framework â one dynamic flow with user checkpoints at every phase. Guides from problem to solution through structured research, metrics, factcheck, and sandbox testing. Use when you face a non-trivial decision, need to research before building, plan a feature or experiment, evaluate trade-offs, or the user says 'awrshift', 'let's think this through', 'research first', 'experiment', 'investigate', 'what's the best approach', 'compare options'. Also trigger on: 'иÑÑледÑй', 'ÑазбеÑиÑÑ', 'пÑоанализиÑÑй', 'ÑкÑпеÑименÑ', or when starting any new project phase, migration, launch, or architecture decision. Do NOT use for simple tasks with clear instructions â just do those directly.
te-config
Use this skill when users ask "add MCP server", "remove MCP", "configure tool executor", "add new tool", "environment variables for tool executor", "regenerate registry", or need to modify which MCP servers are available in the sandbox.
enclave
A sandbox environment. You should use this skill when you need to check if the sandbox is enabled or not, or when you need to execute commands outside the sandbox.
Mcp Mailtrap
MCP server for the Mailtrap email platform — analytics, sending, contacts, sandbox
aenvironment-deploy
Deploy sandboxed environment instances and services using AEnvironment. Use when deploying agent instances, web services, or applications to AEnvironment sandbox infrastructure. Supports three workflows - (1) Build image locally and deploy, (2) Register existing image and deploy, (3) Deploy from registered environment. Handles instance deployment (temporary, IP-based access for agents) and service deployment (persistent, domain-based access with storage for apps).