Spin up and ship real, multi-tenant websites and web apps on Loftur — a runtime you drive over MCP. Use when the user wants to create, edit, or deploy a site, page, or small app that needs hosting, a database, auth, secrets, email, file uploads, or a CMS, without setting up any infrastructure. With one account token…
Use AutoDL safely through its official developer APIs and documentation. Trigger for AutoDL balance, Container Instance Pro, elastic deployment, images, GPU stock, NFS, duration packages, WeChat notifications, container metrics, billing, storage, data retention, SSH/JupyterLab/VSCode, CUDA environments…
Comprehensive guide for setting up and configuring CodeQL code scanning via GitHub Actions workflows and the CodeQL CLI. This skill should be used when users need help with code scanning configuration, CodeQL workflow files, CodeQL CLI commands, SARIF output, security analysis setup, or troubleshooting CodeQL analysis.
Harden and audit SSH access across a host fleet via the tunnel-manager MCP server — set up passwordless key auth, build a full-mesh trust, rotate SSH keys fleet-wide, distribute a shared ssh config, and run security / compliance / vulnerability audits against a host. Use when the agent must move a fleet off password…
Default workflow for durable local, SSH, Slurm, Apple-signing, or GitHub publishing work through RunBeacon. Use whenever Codex needs to call a remote host, securely save or select SSH/GitHub credentials, run or recover a long task, monitor training, publish commits, wait without model polling, cancel a remote process…
Manage Docker containers and images via MCP. Use when the user asks to docker ps, tail container logs, restart a service, exec into a container, check CPU/memory stats, or clean up images on the local host.
Configures GKE observability, including Cloud Logging, Cloud Monitoring, and managed Prometheus. Use when configuring GKE monitoring, setting up GKE logging, or configuring Prometheus metrics collection. Don't use to configure local application logging frameworks or external APMs outside GKE.
Answers Alchemy (alchemy.run) questions from an indexed local copy of the full documentation. Covers Stacks, Resources, Actions, Outputs, bindings, the Effect-based deploy/runtime phase model, the alchemy CLI, state stores, stages, and provider guides for Cloudflare, AWS, Fly, Railway, Hetzner, Neon, PlanetScale…
An operations guide for working with terminals, JumpServer access, Grafana dashboards, and Nacos configuration and service discovery through the AT Series MCP server. JumpServer is a controlled gateway to remote machines; Grafana displays monitoring data; Nacos manages configuration and services.
Turn a project's FOSSA findings into NeuVector runtime controls and push them to the cluster. Two tracks — vulnerability findings become WAF sensors (regex-matched request inspection); license-conflict findings become a workload quarantine (network isolation / deploy hold). Use when asked to mitigate, compensate for…
Publish a static website (HTML, CSS, JS, images) to a live public URL with Just Publish, straight from the chat. Use when the user wants to publish, deploy, host, or share a site or files they built — with ChatGPT, Claude, Cursor, or by hand — or says "put it online", "give me a link", "make this a website"; also for…
Deploy a real multi-user web app from this conversation, then keep operating it. You author an HTML page plus a manifest; homespun deploy puts it live on its own URL with magic-link sign-in, a shared realtime database, per-role read/write/delete permissions, email notifications and file uploads. Owners invite other…
Classify a completed public GitHub Actions failure with FlakeVerdict before spending a retry. Use when deciding whether a failed workflow run is a confirmed flake, likely flake, recurring failure signature, new failure, inconclusive failure, or not currently failed by comparing attempts, same-commit outcomes, and…
Use Weavatrix Online only for configured Cloud or self-hosted endpoint status, current dependency advisory refresh, bounded installed-package malware review, owner-managed architecture contracts, or explicitly approved source-free graph synchronization. Do not use it for ordinary local code analysis or refactoring.
Stand up a Booboo brain end to end — scaffold the project, write booboo.config.yaml against a real Postgres/Supabase or JSON source, build the snapshot, then wire the REST API, the MCP server, the 3D viewer and the panel. Use when someone wants a brain built for the first time, wants to point Booboo at their own…
Run non-interactive builds, tests, benchmarks, and local, SSH, or Slurm commands through Awaitless's adaptive durable execution layer. Use by default when command duration is uncertain, work may outlive the current turn, a named scarce resource may be queued, multiple jobs should complete without polling, or bounded…
Lightweight AI security guard that intercepts risky install/download commands (npm, npx, pip, cargo, git clone) to block known malicious packages and scan for suspicious code. Invoke ONLY when user runs install/download/clone commands.
Give a repository a full health exam — doc rot, dependency staleness, CI decay, git hygiene, dead links, docs contradicting code — and grade it. Use when the user wants to know what quietly rotted, or a prioritized maintenance list.
Guide users through setting up or updating a local development environment for the Opentrons opentrons/opentrons monorepo. Use this skill whenever a user mentions setting up or updating Opentrons development, cloning the Opentrons repo, installing or refreshing dev dependencies for Opentrons, getting started…
★not rated 1 6mo agoA170 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: