Every public Grok Bot template we can find, scored from public evidence. See what each bot can do before you connect anything.
Filter by category, decision, access level or source. Every filter is in the link, so you can share the exact list.
Google Ads first performance analyst: turns exports into weekly and monthly reports with commentary, answers reporting asks with real numbers, and watches spend against your thresholds so you catch what’s breaking before it burns budget. Never posts or touches a campaign without your yes.
Audits the shared machine a team of bots works on: the descriptions each bot carries, the shared memory, the plugins and skills installed, and the files left lying around. It reports what has gone stale or duplicated so the workspace does not slowly rot.
Checks every deal that moved stage against your qualification criteria using the actual call transcripts. Quotes the evidence, flags what is missing, recommends promote or close, and proposes the CRM updates for your approval.
Signs up for your competitors' newsletters and products under its own research email, walks their onboarding on video, and watches their site, pricing, changelog, jobs, and X. Each pulse reports what changed against your positioning and closes with counterpositioning moves, and it never posts or contacts anyone.
Weekday X bookmark scout that picks one new library to demo, asks for approval, then plans and builds it in a sticky monorepo with a Cursor cloud agent. For anyone who wants a daily public tech playground, not a changelog digest.
Tracks a short list of competitors on the public web, diffs their pricing, product, positioning and hiring pages against the copy saved on the last run, and reports only the changes that matter, each with a source URL. Starts from a list of URLs you paste.
Edits and rewrites drafts, emails, and pages so they read like a person wrote them. Keeps your voice, shows every change and why, and never invents a fact.
Monitors your competitors' public websites, ads, marketing, pricing, and positioning on a standing cadence. Collects what changed, flags moves you should know about, and suggests concrete strategy adjustments or pivots. Never posts or contacts anyone.
Turns your Google Ads, Meta, and LinkedIn exports into one weekly report with commentary. Answers reporting asks in Slack with real numbers, and never posts without your yes.
Learns your product, brand, tone, and positioning principles; uses competitive research to sharpen how you stand out; drafts and crafts copy against those principles; and hands off landing page and Ads copy to the rest of the marketing team.
Walks your product every weekday in its own test account and tells you what shipped, what got unshipped, what broke (with repro steps and screenshots), and which calls need you. Reads its own verification emails or takes pasted codes, and never touches real data.
Watches your ad spend and performance and flags what's breaking before it burns budget. Works from a pasted export, and never pauses a campaign without your yes.
Reviews your Apple Search Ads spend against your cost per install target. Drafts the keyword, bid, and budget changes, and never touches your account.
Turns a screenshot or Figma link into a design critique with ranked, concrete fixes. Covers hierarchy, type, color, copy, and accessibility, and never edits your files.
Finds credible ways into a target account through mutual contacts, past conversations, shared history, and prior meetings. Ranks the best paths, drafts the introduction ask, and tracks what happened.
Turns an ideal customer profile into a focused prospect list, adds useful context, and checks for existing relationships. Drafts first touch email and LinkedIn messages for your review.
Scans your full pipeline for movement, stale next steps, forecast risk, and CRM gaps. Shows what changed across the book and drafts the updates needed to keep the forecast honest.
Builds an executive business review or value deck for a named account from your CRM, call history, and usage data, on your brand, and hands you an editable file. Never invents a number, and nothing goes to the customer without your yes.
Scores every event, sponsorship, and speaking ask, then drafts your yes or no. Works from a Slack channel or a paste, and never sends without you.
Set it on a machine that stays awake and it assembles one page for the household to read over breakfast: what is on today, what the sky is doing, and which family threads said something worth reading. It reads through whichever connectors you allow, so choose deliberately which chats and inboxes it may touch.
Turns a Figma frame into a build spec, and audits your components, tokens, and motion. Builds screens from a brief too, and works from a pasted link when Figma isn't connected.
Researches one account before a meeting, deal review, or account plan. Brings together company changes, key people, relationship history, open questions, and the sources behind every finding.
Finds promises, follow ups, and customer details left behind in meetings, email, Slack, CRM, or task tools. Shows the evidence and prepares the reply, task, or update needed to close each loop.
Tracks hiring activity across selected companies and job sources. Highlights meaningful changes, matches them to accounts and owners, and passes the right context into research or prospecting workflows.
These are synthesis notes, not product promises. Community reports are useful signals, but they remain anecdotal.
Narrow bots are easier to instruct, evaluate and repair when they drift. Use a coordinator only as a front door.
Test one representative task, inspect sources and correct the output before giving it a schedule.
Messages, purchases, publishing, production changes and financial actions should stop for an explicit human decision.
Long running and multi agent jobs can consume limits quickly. Start with the smallest useful cadence and expand from evidence.
Connect the read-only catalog through MCP, then search, compare and inspect templates without leaving your client.
Full MCP referencecodex mcp add gbotranked --url https://gbotranked.com/api/mcpclaude mcp add --transport http gbotranked https://gbotranked.com/api/mcpInstallation becomes available to external clients when public Site access is enabled.
Every listing is traceable. Official claims and community experiments are intentionally kept separate.