78 skills · sorted by relevance
Guide shell, Python, and Node.js execution on the computer running a connected A0 CLI. It explains session reuse, interactive input, output retrieval, and recovery steps when execution permissions, timeouts, or disconnections interrupt the work.
Test agent features across local and remote execution environments using integration tests, which check components working together. Covers Docker and Wine setups, test helpers, and configuration-specific skips for the app-server and exec-server split.
Improve Bazel builds in large repositories containing multiple projects. Get guidance on build configuration, shared remote caches, remote execution, dependency management, custom build rules, and diagnosing build problems.
Guides experiments that inspect and change internal model values using nnsight. Covers local PyTorch models and remote experiments through NDIF, including replacing intermediate values to test how particular layers affect a model’s predictions.
Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.
Use when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download, server transfer, deployment, tunnels, port forwarding, or remote internal services; Chinese triggers include 服务器, 远程, 连接, 登录, 上传, 下载, 部署, 跳板机, 隧道. DO NOT use for local shell commands, localhost/current-machine work, local Docker, browser downloads, Git remotes, or direct non-SSH database access.
The English summary is being prepared. Showing the original description.
Hunts for lateral movement via remote service creation, admin share writes, and remote WMI process creation by correlating Windows logon, service install, and process-creation events. Activates for requests to hunt lateral movement, detect PsExec/WMIexec activity, or find remote execution over SMB and WMI.
The English summary is being prepared. Showing the original description.
Run a ruflo agent on your ruOS cloud desktop through an authenticated connection. Follow its output as it runs, record execution status in ruflo, and release the task claim when the run finishes.
Review lateral movement, the ways access spreads between systems, during authorized security tests. Covers credential reuse, remote execution, network tunnels, prerequisites, and the logs or defensive controls associated with each technique.
Run installation, integration, and end-to-end tests that follow real user actions in remote environments or Docker. Choose an appropriate isolated environment, inspect failures, record execution details, and clean up resources after testing.
Turn a codebase into an interactive graph of code relationships. Explore functions, call chains, related groups, and execution flows in a browser, with optional Cloudflare tunneling to share the explorer remotely.
Run commands and coding agents on existing cmux Cloud machines, monitor work that continues after disconnection, and present results through workspaces or service URLs. The skill guides machine selection, background execution, and result verification.
Run OpenClaw tests and reproduce bugs on remote machines through Crabbox. Choose a suitable execution provider, verify realistic user workflows, and report the actual provider, environment ID, logs, and timing.
Assess security weaknesses in CI/CD systems that automate software builds and delivery. Covering GitHub Actions, Jenkins, GitLab CI, and Azure DevOps, the skill examines unsafe inputs, excessive permissions, exposed credentials, and tampered build outputs, alongside detection and defensive controls.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
The English summary is being prepared. Showing the original description.
MS17-010 (EternalBlue) is a critical vulnerability in Microsoft's SMBv1 implementation that allows remote code execution. Originally discovered by the NSA and leaked by the Shadow Brokers in 2017, it
The English summary is being prepared. Showing the original description.
Investigate Python bugs by pausing execution, inspecting variables, and stepping through code. Choose between local debugging with pdb or breakpoint(), exception inspection, and connecting debugpy to remote or already running processes.
Investigate Node.js bugs by pausing execution, examining variables, and stepping through code. Diagnose stalled asynchronous work and unreliable tests, or collect memory snapshots and CPU profiles to investigate growing memory use and slow execution.
Investigate Python bugs by pausing execution, inspecting variables, and stepping through code. Choose pdb for local inspection or debugpy for remote connections, with guidance for failing tests, crash analysis, and already running processes.
Debug Node.js from the terminal by pausing execution, inspecting variables, and tracing function calls. Use interactive commands or scripts to investigate failing tests, collect runtime state, and capture CPU profiles or memory snapshots.
Develop exploit code from a known memory corruption flaw, then investigate differences between local and remote execution. Covers stack, heap, and Linux kernel cases, with attention to library versions, debugging, and repeatable results.
Analyze Zeek network logs to find lateral movement, when an intruder spreads between internal computers. Examine administrative file sharing, authentication across multiple hosts, and remote service operations to identify suspicious connections and reconstruct incident timelines.
Inspect and control the connected local computer through A0 CLI or a Launcher host gateway. The skill guides screenshots, native app input, window targeting, and checking results, with background actions where the connected system supports them.
Delegate development tasks to external coding agents such as Codex and Claude Code through command-line tools. Choose local or container execution, check setup, provide a self-contained task brief, and inspect important changes afterward.