mcowger

Commit staged/working changes in an existing worktree with a Conventional Commit, push the branch to origin, and open a PR against the default branch. TRIGGERS - commit and push, open a PR, create pull request, ship this branch, commit push pr.

Comprehensive Open Terminal reference: a self-hosted terminal REST API for AI agents. Use this skill for any questions about Open Terminal: API endpoints, deployment (Docker, bare metal), configuration, integration with Open WebUI, architecture, debugging, and writing client code that interacts with Open Terminal. Also use it when working with the open-terminal codebase: project structure, runner.py, main.py, the MCP server, and Jupyter notebooks. Triggers: open-terminal, open terminal, remote terminal API, /execute, /files, sandbox API, terminal sessions, Open WebUI terminal.

Detailed reference for Open WebUI: architecture, authorization, functions, pipelines, API, RAG, scaling, debugging, and hidden features. Use this skill for any questions about Open WebUI — how it's built, how to deploy it, how to configure authorization (OAuth, LDAP, JWT), how to write a function or pipeline, how to connect a model (Ollama, OpenAI), how to configure RAG/knowledge base, how to scale for production, how to debug an issue. Also use it when writing code for Open WebUI: functions (filter, pipe, action), pipelines, configurations, docker-compose.

How to discover open-source tools and repositories on GitHub. Use this skill whenever the user asks to find tools, repos, libraries, or projects on GitHub — even if they don't explicitly say "GitHub." This includes requests like "find me tools for X", "what repos exist for Y", "show me alternatives to Z", or any exploration of the open-source ecosystem. Make sure to use this skill for any GitHub discovery task, including finding TUI tools, CLI utilities, libraries, frameworks, or any software project. Do NOT use general web search for GitHub discovery — use the GitHub-specific tooling described below.

Expert help for mise, the environment and dev-tool manager. Use whenever the user mentions mise, mise.toml, .tool-versions migration, runtime or CLI version management, installing tools like node/python/go/bun with mise, registry/backends, shell activation, shims, PATH issues, [env] config, dotenv loading, direnv interplay, or troubleshooting why the wrong tool/version is active. Also use when the user wants to edit mise config safely, explain backend choices, or debug a broken mise setup.

Push local commits directly to a contributor's fork and branch from a PR, without adding a git remote. Use when pushing changes to a PR branch, pushing fixes into someone else's PR, updating a pull request with local edits, or when the user says "push to the PR", "push to this PR's branch", "push my changes to the contributor's fork", or "update the PR with my local commits". Also use when the user is on a branch associated with an open PR and asks to push, especially when the branch tracks a fork rather than origin. Prefer this over manually adding remotes.

How to safely add or modify database schema in Plexus using Drizzle ORM. Use whenever adding tables, columns, or enum values — covers migration rules, schema organization, and dialect-specific timestamp patterns.

Use this skill to inspect or administer a running Plexus instance via the management API, or debug failures touching Plexus-proxied traffic (oauth, routing, model targets, raw provider passthrough, inference keys, MCP gateway) rather than searching the local codebase. Covers request logs, debug traces (lookup by UUID), enabling/disabling debug capture, providers, model targets, balances, quotas, aliases, target groups, keys, MCP logs, and runtime settings (failover, cooldowns, timeouts, backup/restore). Prefer this for any Plexus admin, operational, or live-debugging task, even if the user only says "check Plexus", "look at logs", "update a provider", "rotate keys", "configure quotas", "debug a request", "review debug trace", or "upstream error" — Plexus state lives behind the management API, not in local files.

Verify any Plexus admin-UI screen or component in the actually running app. Boots the worktree-safe dev stack (`bun run dev:agent`), auto-logs in, and drives a real browser (agent-browser) using the correct port/credentials. Use whenever you edit anything under `packages/frontend/src` (React, routes, forms, buttons, tables, modals, Tailwind/CSS, layout, dashboards) or when asked to look at or verify a screen (e.g., "screenshot the dashboard", "does the new tab show up", "verify UI", "does the button work", "test web app", "reproduce visual bug"). Prefer this over the generic agent-browser skill for local Plexus frontend because it knows port, credentials, and auto-login. Don't hand UI work back unverified.

Step-by-step checklist for adding a new quota checker to Plexus. Use whenever asked to implement a new quota checker type — covers backend registration, frontend components, display integration, and common pitfalls.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Configure pi-controls policies and locations. Use when the user wants to set up, modify, or troubleshoot access control rules for the pi-controls extension.