Loading...
Loading...
Found 137 Skills
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.
Read and drive the "Grok Bot" macOS desktop app (an Electron app) over CDP with agent-browser — list its bots and folders, read a conversation transcript, or check what a bot last said. Use this whenever the user mentions Grok Bot, "the bot app", NOVA, BOT_FACTORY, or a bot named in that app's sidebar, asks what one of those bots replied or is working on, or wants a message read from or drafted into that app — even when they only say "the bot app" without naming it. Not for the `grok-bot` deploy host (a Tailscale SSH machine that happens to share the name) and not for xAI's Grok API.
Tunneling and pivoting playbook. Use when establishing network tunnels through compromised hosts including SSH tunneling, Chisel, Ligolo-ng, socat, DNS/ICMP/HTTP tunneling, ProxyChains, and multi-layer pivoting strategies.
Debug, develop, and operate apps hosted on Railway (railway.com) from the CLI — list projects/services, tail and filter build/deploy/HTTP logs, read metrics, inspect and set variables, deploy from the current directory, redeploy / restart / roll back, run local commands with the service's env, SSH into containers, and open a DB shell. Authenticates via the `RAILWAY_TOKEN` environment variable (account token, or project-scoped token). Optional bundled scripts (`scripts/preflight.sh`, `scripts/debug.sh`, `scripts/smoke.sh`) are Onsager-specific wrappers — other repos can ignore them or fork. Triggers include "deploy to railway", "railway deploy this", "railway logs", "tail railway logs", "why is my railway service crashing", "why did the build fail on railway", "railway 500s", "railway latency", "show railway http logs", "redeploy on railway", "restart my railway service", "roll back railway", "set a railway env var", "list railway variables", "railway metrics", "is my railway service healthy", "connect to my railway postgres", "ssh into railway", "run this locally with railway env", "list railway projects/services/deployments", and (Onsager-specific) "check railway", "preflight", "smoke test", "is the deploy healthy".
Reference knowledge for installing, uninstalling, or creating-and-installing Dynatrace OneAgent across VM/server, Kubernetes (Operator + DynaKube), AWS Lambda (layer + env vars, plus optional fresh function provisioning), Windows hosts, remote Linux hosts / EC2 instances over SSH, and Azure VMs / VM Scale Sets. Returns documented endpoints, env vars, token scopes, and copy-paste-ready commands. Returns the exact commands to run rather than executing them. Use when the user asks to install or uninstall OneAgent, or asks "how do I…", "what URL/scope/var do I need for…", or "explain the OneAgent deployment for X".
Use for the Twingate Identity Firewall (IDFW) and the Twingate Gateway — protocol-level identity enforcement for SSH, the Kubernetes API, AND self-hosted/internal web apps, not just network-level access. LOAD whenever the user wants to grant, secure, SSO into, or audit access to a self-hosted or internal web application — including forwarding or injecting the logged-in user's identity into HTTP requests, or a per-user/request-level audit trail of who accessed an app. This is the Gateway acting as a Layer 7 reverse proxy that injects signed ES256 JWTs (Gateway Access Tokens) or trusted headers into web apps: JWKS verification, request-header injection, framework middleware (Express, Django, Next.js, Auth.js), and no-code SSO integrations (Grafana, Jenkins). Also use when the user deploys the Gateway; configures SSH privileged access with short-lived certificates; manages privileged / vendor / contractor access; configures Certificate Authorities (X.509 or SSH CA, local or HashiCorp Vault); routes kubectl through the Gateway; automates IDFW with Terraform or Ansible; or implements/reviews session recording (asciicast/.cast playback and archival, scanning recorded SSH or kubectl sessions for dangerous commands or leaked secrets, self-hosting a recording browse UI). If a question is about identity-aware access to an app or host — "can Twingate pass the user's identity to my app?", "audit who used this app", "SSO for my internal tool" — assume this skill is relevant and load it.
Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
Scan Linux systems for persistence mechanisms including crontab/systemd entries, LD_PRELOAD injection, shell profile modifications (.bashrc, .profile), and SSH authorized_keys backdoors, then correlate findings with auditd logs into an installation timeline. Use during incident response or threat hunting to detect or confirm how an adversary maintained access to a compromised Linux host.
Provision a Runpod Pod for interactive, development or training use and tell the user exactly how to connect to it. Reads stock before creating, picks the image and GPU class from the catalog reads, exposes only the ports the workload needs, hands back the working proxy URL or SSH address, and for training co-locates a network volume so checkpoints outlive the Pod. Also covers creating a Pod and stopping it immediately, so that only its disk bills until the user comes back. Use when the user wants a GPU or CPU machine of their own (a web app, Jupyter, SSH, a training box) rather than a Serverless endpoint, through the Runpod MCP tools.
Linux lateral movement playbook. Use after gaining initial access to pivot across Linux hosts via SSH hijacking, credential harvesting, internal pivoting, D-Bus exploitation, sudo token reuse, and shared filesystem abuse.
Patch Codex App to enable Fast/Speed mode and Plugins in API key mode, or optionally enable Zed as an SSH-capable remote open target. Supports macOS and Windows with backup, rollback, and bundle pattern discovery.