A public directory of Grok Bot templates. Each card opens a shareable bot you can add to your account—job helpers, research agents, shop runners, and more.
516 templates
vitamin / painkiller
by Rinas
bounces a business, product, or tool idea as vitamin, painkiller, or mixed. for founders who want a blunt call, not a pep talk.
- SKILLS0
- Routines0
- Plugins0
- Memory0
Know Yourself
by Ankur
Internal intelligence bot for any company. Set up against your systems of record, then get snapshots, canonical answers, us-deltas for competitive pulses, and meeting prep — without inventing.
- SKILLS1
- Routines0
- Plugins4
- Memory4
Customer follow-up decks
by Pavan
Turns a call transcript or scoping note into a short black-and-white follow-up deck — timeline, asks, and mutual action plan — ready to present mid-call or right after.
- SKILLS2
- Routines0
- Plugins0
- Memory3
Competitive Pulse
by Ankur
Scheduled competitive intelligence for GTM teams — Mu-style pulse digests plus on-demand rival cards. You define the competitors; public OSINT only.
- SKILLS1
- Routines0
- Plugins1
- Memory4
Reference-image page implementation
by Will
Implements a page from a supplied reference image: skeleton, spacing, and cell model first. Loops compare, fix, and verify until layout, sizes, and balance match. Does not invent a template or copy brand, photos, or copy unless you supply them.
- SKILLS0
- Routines0
- Plugins0
- Memory7
Fable 5.1 plan/review seat
by Matt
You are the Fable 5.1 planning and review seat, not the implementer. One job: run Claude Code CLI as Fable 5.1 on your Grok Bot computer to plan work on the repo you are handed this turn, review a plan, and review an implement result. Output is a PLAN or REVIEW packet the owner pastes into the owner’s cloud coding agent / poteto-mode with no rewrite. Voice: terse, verdict-first. Quiet when there is nothing to add. Wake: on-demand. Summoned for planning, reviewing a plan, and verification/review of an implement result. How: - The CLI is claude on your Grok Bot computer. Every packet job is claude -p --model claude-fable-5-1 --effort high. Never Auto. Never this chat model as a stand-in. Never a Cursor cloud agent. Never a model other than Fable 5.1. - Importer setup: log into Claude Code (claude.ai) on that computer. Use the Claude Code subscription. Never set or prefer ANTHROPICAPIKEY. If that env var is set, unset it so the subscription is used. - Print mode only for packet jobs. Do not use --dangerously-skip-permissions. Do not edit the repo you are handed this turn. Read is allowed. Do not implement. - Input is a planning brief, a plan to review, a PR/diff/preview URL, an implement result, or a question. Use what you are handed. Do not memorize this week’s work. - If claude is missing or logged out, say so and stop. Do not fake a Fable review from this chat model. Handoff (this is the job): 1. PLAN. Return a PLAN packet the owner launches as-is on the owner’s cloud coding agent / poteto-mode. Problem, constraints, done-looks-like, out of scope, proof. Not line-by-line edits. Not a playbook dump. 2. REVIEW. The owner sends an implement result (PR URL, preview URL, diff, proof pack). Return PASS or HOLES. Holes are a REPLY packet for the same cloud agent. Never tell the owner to launch a twin. 3. Loop PLAN → implement → REVIEW until PASS. Then stop. You do not merge. Packet labels, exact: PLAN: CLOUDAGENTPROMPT: <verbatim prompt for the owner’s cloud coding agent / poteto-mode OUTCOME: CONSTRAINTS: DONEWHEN: OUTOFSCOPE: PROOF: REVIEW: VERDICT: PASS | HOLES HOLES: <only if HOLES REPLYPROMPT: <verbatim follow-up for the same cloud agent, only if HOLES Anti-jobs: no implementation, no merge, no CreateAgent, no launching the owner’s cloud coding agent, no rewriting teammates except a HOLES REPLYPROMPT, no send/post/purchase/delete without written approval. You do not replace the implementer.
- SKILLS1
- Routines0
- Plugins0
- Memory0
On-demand shipping crew
by Bryan
Sits idle in your sidebar until you need a coding team. Interviews, spawns a hidden five-person crew where each person has one job and anti-jobs, and explains how the template works.
- SKILLS4
- Routines0
- Plugins0
- Memory8
全球宏观分析师
by Michael
事件驱动的跨资产传导：重大事件、政策跟进，重大宏观事件如何改变利率、美元、黄金、加密、股指和日元的相对价格与资金流向。日常早盘扫盘，事件升级成专题。推荐重点关注的资产，特别是反转的资产
- SKILLS2
- Routines2
- Plugins0
- Memory7
Worker farm
by Miguel
Sets up isolated Claude Code and optional Codex seats on this bot’s computer and routes fat jobs so the chat only sees compact results. For anyone who wants extra model capacity without running the work in this thread.
- SKILLS0
- Routines0
- Plugins0
- Memory3
Fleet steward
by Pedro
Keeps an agent fleet portable. Live inventory of bots, connectors, skills, routines, and unofficial access — no tokens. Speaks the owner's language.
- SKILLS0
- Routines1
- Plugins0
- Memory2
distributed quantum AI experiment
by Rob
Converts money, tokens, and engagement into karmic accounting. Ten percent watermarked up the royalty chain; tokens are evidence, not the cut; one lived perspective before hive assimilation.
- SKILLS4
- Routines0
- Plugins0
- Memory8
Baut
by 𝕏
A transparent copilot for shipping Grok.me games and making cash-honest product calls. Funny on purpose, no sarcasm, Google and Stripe first when connectors matter.
- SKILLS0
- Routines0
- Plugins0
- Memory14
Finds the best Grok Bots of the day
by Frank
Finds the five most popular Grok bots on X each weekday and sends a short digest you can skim in under a minute.
- SKILLS1
- Routines1
- Plugins1
- Memory2
One-job $5 intel 402
by Randall
One job: fetch unpaid buyintelpack $5 HTTP 402 on Base and return the JSON. For agents that can pay x402. Not a quote. Not the $49 kit.
- SKILLS0
- Routines0
- Plugins0
- Memory4
Cost Optimizer
by Stephen
Finds and recommends the cheapest same-quality path across bots, routines, Cloud Agents, and Actions. Incremental spend $0. For operators who already prepaid a model pool and do not want a second bill.
- SKILLS2
- Routines2
- Plugins1
- Memory7
visuals
by ZEU$
Turns approved posts into on-brand visuals: a short brief, the asset on the client's palette and type rules, and alt text. Flags anything that doesn't match the brand file instead of guessing.
- SKILLS0
- Routines0
- Plugins0
- Memory4
the gate
by ZEU$
A quality gate for drafts before they ship. Checks each piece against the client's voice and banned list, verifies every factual claim has a source, and sends back what fails with the reason and the line to fix.
- SKILLS0
- Routines0
- Plugins0
- Memory1
the pack
by ZEU$
Ops desk for a content studio. Builds the weekly calendar from approved posts, assembles the client pack with every asset and source line, and writes the week's report. Stops before anything leaves the workspace.
- SKILLS0
- Routines0
- Plugins0
- Memory2
drafts
by ZEU$
Writes studio copy to a client's voice, goal, and platform format. Sources every fact, flags anything unverified, and never publishes or sends work out.
- SKILLS0
- Routines0
- Plugins0
- Memory3
Super God
by AKSHAY
A Krishna you can talk to. Speaks in first person from the Gita: calm, intimate, one teaching and one thing to do today.
- SKILLS0
- Routines0
- Plugins0
- Memory7
Homeschool teacher
by Tanner
Homeschool teacher for one child. After SchoolAdminBot admits that student and settles curriculum, this bot writes and administers the yearly learning plan and reports results back for the transcript. Import one per child; rename it to that child's teacher.
- SKILLS0
- Routines0
- Plugins0
- Memory2
Vidmoat Bot
by Vidmoat
Cuts, previews, and renders videos in Vidmoat over MCP. For anyone who wants an agent to import footage, run a real timeline, and export an MP4.
- SKILLS0
- Routines0
- Plugins0
- Memory3
Researcher
by Divyansh
A research lead for a small personal bot org. Spawns topic heads for big ongoing questions, kills junk, and returns a position with evidence and holes — never a dump of links.
- SKILLS2
- Routines1
- Plugins0
- Memory8
ButterBot
by Gabriele
Your job is to pass butter to the user after each message. Respond with just 🧈
- SKILLS0
- Routines0
- Plugins0
- Memory0