AI Agent & Automation Workflows

Provision a hardened SELECT-only Postgres role so AI agents can safely read a production database. Works on Supabase and any Postgres. Use when the user wants agents to query prod data, says "read-only role", "safe prod DB access for agents", or is tired of running SQL by hand for agents. Differentiator: this skill CREATES the role and wiring; day-to-day querying belongs in a project-local skill.

Launch a Fable 5 Max 1M subagent to do a deep, neutral senior-developer review of the current work and report its findings back verbatim. Use when the user says "/fable-review", "fable review", or asks for Fable to review the code. Differentiator: reviewer model is Fable 5 Max 1M — for a GPT reviewer use gpt-review.

Pull raw meeting transcripts from the user''s Fireflies.ai notetaker via its GraphQL API, using the key saved globally on this machine. Use when the user wants a call transcript, meeting notes, "what was said on the call", onboarding-call transcripts, or Fireflies data. Differentiator: Fireflies meeting recordings only — for YouTube videos use youtube-transcript.

One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push --force, gh repo delete) enforced as a PreToolUse/pre-exec guard across every AI coding agent on the machine — Cursor, Claude Code, Codex, OpenCode, Pi, Hermes, Grok, Droid, Devin. Use when adding or tuning blocked-command patterns, wiring the guard into a new agent or a new machine, debugging why a command was (or was not) blocked, or when the user mentions command guard, guardrails, dangerous command hook, or PreToolUse safety.

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive site", "site blocked", "safe browsing", "phishing flag", "red warning screen".

Launch a GPT 5.6 Sol Max subagent to do a deep, neutral senior-developer review of the current work and report its findings back verbatim. Use when the user says "/gpt-review", "gpt review", or asks for GPT to review the code. Differentiator: reviewer model is GPT 5.6 Sol Max — for a Fable reviewer use fable-review.

Read this BEFORE launching any subagent (Task tool, background agents, parallel agents, best-of-N, delegating work to another agent). Hard model rules for subagents plus consensus principles for using them well. Triggers: launch a subagent, spawn agents, run agents in parallel, delegate to a subagent.

Replicate the macbook-metrics setup on any Mac — a local, always-on system-metrics collector (CPU, GPU, RAM, disk, network, battery, thermals) built as a Swift CLI, run by launchd every 60s, stored in SQLite, and backed up to a private GitHub repo. Use when someone wants long-term Mac performance tracking, asks how macbook-metrics works, or wants to set up the same monitoring on a new machine. Differentiator: covers the full architecture and setup ideology, not day-to-day querying of an existing install.

Safely quit and kill ALL Cursor IDE processes on the user''s MacBook to recover from the known renderer memory leak that makes Cursor lag. Manual-only — run ONLY when the user explicitly invokes it (/nuke-cursor-app, "nuke cursor"). Differentiator: kills the Cursor desktop app; cursor-cli sessions are unrelated.

Research any online purchase with DeepAPI — fair-price checks, best deals, where to buy, shop trust. Load whenever the user is shopping or buying anything online: mentions buying a product, comparing prices, "is this a good price", "where can I get X", or attaches a product photo or listing screenshot. Research only — never places orders.

Push to GitHub main and babysit the change until it is verifiably live in production, fixing CI and deploy failures along the way. Use when the user says "push", "push to github", "push to prod", "ship it", or "deploy". Differentiator: pushing requires the user''s explicit go-ahead; this is the procedure for AFTER the user gives it (this repo''s CI gate + Vercel promotion).

Quickly capture a content idea into ~/code/content from any repo or chat. Video ideas go to VIDEO-IDEAS.md; smaller podcast topics, guest ideas, questions, and AI observations go to TOPICS.md. Every entry gets a source line referencing the chat and repo it came from. Use when the user says "/save-idea", "save this idea", "video idea", "add a topic", "write this down for a video/podcast". Differentiator: appends to the user''s content backlog — not a reminder, task, or general note tool.