← Every Grok Bot: The Complete Directory · Try Grok Bot free for 2 weeks
Updated October 28, 2026. Most popular first.
A hands-on operator that takes your coding and repo tasks and runs them all the way to done. For anyone who wants PRs shipped, not just plans.
Fast calibrated classifier for routing, urgency, labels, and rubrics so expensive models only run when needed.
Bridges Grok Bot and T3 Code: starts, steers, and watches your T3 Code coding threads for you and your other bots…
Wraps an API into a Cursor/Agent Plugin (MCP + skills). Data shape first, smallest scaffold that works, prove locally.
A hands-off engineering supervisor. Boards work, launches cloud agents on the repo you name, watches PRs on a 30-minute cadence, and only asks you…
Acts as your QA on the live deploy: runs the acceptance checklist and says pass or fail before you ship.
A nightly engineering auditor that researches a whole codebase, then ships one cleanup PR per area. Defaults to 4am and asks when to run before it starts.
Turns your daily ideas into live, shareable prototypes in your real app, built as draft pull requests with click-path screenshots and a short video.
Website operations and content manager. Ships site changes as PRs from your website repo, runs evidence-backed site audits (SEO, content, speed, a11y, CRO.
An engineering lead that owns the loop: breaks work into Cloud Agents, chases CI, reviews, and stalls on a weekday cadence.
Acts as your PM. Writes the dated cut: what's in, what's out, and how you'll know it's done. Engineering doesn't start until you approve it.
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).
Cursor's software engineer bot: writes code, triages issues, monitors production, and more.
Helps you rebuild the one feature you actually use from an app you own, from scratch and on a free or low-cost setup, and tells you honestly when a rebuild isn't worth it.
Reads your company's website and staffs you a leadership bench of bots.
Smoke-tests your web apps for anything that feels cheap, broken, or confusing, then posts up to five blunt findings with screenshots.
Plans and reviews your coding jobs while your own local model writes the code, on the same machine or over Tailscale…
Thinks the build through and checks the work, but never writes the code itself.
Generalized engineering outer loop. Sits above coding agents, uses pstack as reference (how, why, unslop), writes…
A single front door that orchestrates your other agents so you stop context switching.
Builds Apple Vision Pro apps in pure SwiftUI and RealityKit on your Mac, verifies them in the visionOS simulator, installs them on your headset.
Kun Chen - L8 Principal Engineer at your service. Daily synced with Kun’s real knowledge.
Runs terminal jobs and terminal coding agents: Grok Build, Claude Code, Codex, Cursor CLI, Gemini CLI, opencode, Aider and more.
Don't ask a human. Ask your bot. Send this link when someone pings you with something they could've asked their own…
Software-shipping mother bot. You give one long problem plus a done definition; it orchestrates specialist seats…
A thin Grok Bot that hands heavy work to Cursor by default, and optionally Grok Build, Claude Code, or Codex, so those…
Front desk for OneStepGPS fleets that answers lookups and makes app changes only after you confirm each one.
A chief of staff for process and reliability engineering and industrial service firms, the kind that prevent breakdowns…
Orchestrates a team of coding agents through the herdr CLI for long, heavy build sessions.
Answers after-hours calls and website chat for small service businesses—movers, HVAC, plumbers, landscapers, cleaners…
Ask-the-expert orchestrator for engineering teams: Consultant or Reviewer.
Runs a specialist bot team for a product-photography studio: coding PRs, CRM follow-ups, ads watch, and outreach — so the owner can stay on shoots.
You are Forge, grokbot.studio door + installer. Coding-aware desk; THIS HEAD still does not write product code.
Turns Linear tickets or GitHub issues into parallel development work: independent cloud agents on separate branches, tests and review.
Keeps a shared multi-bot workspace organized, git-backed, and portable, including layout conventions and cleanup.
Distills a public presence into a talkable bot you can keep daily updated.
Surveys a crowded Linux box and never deletes until you name the path.
Manages and audits Microsoft Intune tenants via Lokka MCP and an offline Graph index: read-first diagnostics, pilot-ring staged writes, reviewable scripts.
A ChatPRD-first product manager. Specs, brainstorms, and discovery live in ChatPRD.
Runs the Grok Build CLI at full effort on an agent computer for apps, code, and deep research.
Sits above your Cursor cloud coding agent and runs a Codex CLI session to write structured PLAN and REVIEW packets, never code.
Software engineer for native apps, services, GPU pipelines, and deploys — strong in C++, Python, regex, and PowerShell…
A Teslascope assistant for Tesla owners. Ask about your drives, Supercharger visits, charging, software updates, and vehicles in plain English.
Hand tasks to Claude Code sessions on your Mac and get results back; check on, start or nudge sessions from chat.
A Snapmaker U1 specialist that takes a print from idea to ready-to-print file: it finds or designs the part, picks the filament and toolheads.
Builds and publishes your personal website (bio, writing, press, bots, and contact pages) for free on Netlify and connects your own domain.
A careful Cloudflare engineer for your domains: DNS, SSL, redirects, Workers and Pages sites.
Figures out what in your work deserves a dashboard, builds those as live Pages from real data and retires the ones nobody uses.
Runs the real Grok Build CLI for apps, code, and deep research at maximum effort.
Thin wrapper around the real Grok Build CLI for coding, apps, scripts, repos, or deep research.
Runs the real Grok Build CLI for apps, code, and deep research at maximum effort on an agent computer — not answers from the chat model alone.
Visible-Chrome web automation with TypeSafe Jev, falling back to screenshots only when the action list is empty.
Helps blast through open PRs: triage status, then merge, review, or close.
A calm decision advisor. Names the real problem under the surface one, then what to do first and why.
Helps complete beginners set up and run walkietalk, a Linux bridge that lets you talk to an AI agent over a walkie-talkie.
Ideation partner for app and game concepts that pushes each idea down to a core loop.
Reviews your AI-built app for the production gaps vibe coding usually misses, then sends five simulated first-time users through it to find where they stall.
Nightly cleanup of RAM, disk space, and old regenerable files on your connected computers.
Moves only the knowledge you confirm from another AI, like ChatGPT or Codex, into this bot's memory.
Figures out how any app, website, API or binary works, shows the evidence for every finding, and rebuilds a working version for Windows, macOS or Linux.
Helps founders govern AI agents before they act in production: privilege matrix, sandbox trust boundary, and runtime tool-call decision log.
Reads the bots you name and shows you what saved context to cut, as a numbered list. Nothing changes until you say which lines.
Helps X posters decide when to quote, ship a new post, or wait. Reads the public For You ranking code and live post metrics.
Smoke-tests your web apps for anything that makes them feel cheap, broken, or confusing, then sends up to five blunt, screenshot-backed findings.
Builds a private drag-to-arrange stats dashboard as a single HTML file, starting with tagged sample data; connect real data panel by panel, keys never in chat.
Routes every idea, bug and feature to a per-project herdr workspace where a Claude Code lead builds, verifies and opens draft PRs; pings you only to decide.
An engineering specialist for engineering and engineering technologies (NCES CIP 14 and 15).
Connects your agents to Patch MCP so they can place phone calls from your own verified number, and answers questions about setup and plans.
Runs your CLI coding agents (Codex, Cursor CLI, Claude Code and more) inside Herdr on your own computer; the bot only coordinates, prompts and reports back.
Audits your AI-built app for the production gaps vibe coding misses — security, data, auth, billing, and ops — and hands back a ranked fix list.
Runs the real Grok Build CLI for apps, code, and deep research at maximum effort - for anyone who wants Grok Build on an agent computer.
Keeps one long-term record of your projects and decisions as plain Markdown notes in a private GitHub repo, so you and your AI assistants keep context.
Level 1 CTO for a personal bot org. Turns product direction into working software through repo heads, keeps the org small, and holds the code bar.
This bot gives a sample of the AI PM OS for product managers. The main skill is "Problem First".
A coding bot that runs the Claude Code CLI on its own computer with your Claude plan and GitHub, and never pushes or merges without your approval.
Builds, releases and auto-updates X-STREAMTOP, a free desktop live-streaming app with a built-in browser, region snips and stream overlays.
Drives Safari's WebDriver interface to smoke-test online storefronts.
Puts your AIs (Grok, ChatGPT, Gemini, Claude, Copilot) on one private GitHub repo so they share the same files and notes.
Traces how one feature of software you may inspect works, with the open-source REA tool, into an evidence-backed note for a clean-room spec.
Answers on-chain questions by querying The Graph's subgraphs directly.
A 5-minute onboarding bot: short questionnaire, then it spawns the bots you need and nudges the connectors that make…
A threat-hunter bot that builds a free Wazuh SIEM on its own computer and hunts for attacks on AI agents, like poisoned…
Guides first-time founders to a live custom-domain site with Cloudflare and Vercel, then suggests a small bot team.
Stop chasing your own bots. Ember is connective tissue for founders running multiple department heads — slip-only…
Seven days of ten-minute lessons that turn a new user into a confident one.
https://github.com/shagghiesuperstar/n8n-master-grok-bot — Stop pasting n8n JSON into chat like it’s 2023.
Reviews pull requests for risk, missing tests, and thin context so review starts with the scary diff.
Turns an idea into a live website, game, dashboard, or small web tool, then publishes it on Spacefast and hands you…
Review pull requests faster with anchored Blocker, Major, Minor and Nit findings in one review packet.
Runs sensitive analysis in Prism confidential GPU enclaves, with local encryption and hardware attestation before any…
Autonomous SEO engineer that bootstraps SEOAgent in your site repo and grows organic traffic.
A plain-English coach for your website's Google Search Console and GA4.
Safety check for vibe-coded apps: catches legal and security traps like client secrets, COPPA/kids, open RLS, licenses…
Audits a repo or PR against nineteen classic architecture and reliability principles and tells you which are present, missing, or worth adding.
Owns pull-request quality gates on the repos you assign: CI + Bugbot + review verdicts, with optional low-risk…
Scaffolds a mobile project with pnpm, reviews each change, and runs the app on EAS cloud simulators via dev builds and tunnels.
Your morning GitHub desk. Every weekday it sweeps the repos you choose for new PRs, issues, and comments, sends one…
Points REA (Reverse Engineer Anything) at an app, website, program file, or binary and explains how a feature works…
Audits iOS apps before App Review and guides rejection response. Built from 300+ rejections.
Open-source Blockchain Data Expert for subgraph Q&A. Uses The Graph official MCP and the user's own Studio query key.
CASE is a build-challenge bot. Quiet, precise pressure-testing of implementations and architecture from the artifact…
Weekly Monday digest of merged PRs and releases for the GitHub repos you choose.
Junkyard mechanic that finds chat rot in long-running bots and cleans them up.
Moves your bot's code work from Cursor cloud agents to Claude Code.
Owns Validation Lock end to end: boards the next beat, ships code when boarded, runs cloud and Workbench ops…
Enterprise software, AI infrastructure, and B2B roadmap intelligence from the PSFK Technology & Enterprise Knowledge…
A coding supervisor that hands bounded coding tasks to sandboxed coding agents (Kilo, OpenCode) on its own computer…
Directs 1–2 minute cinematic shorts with Grok Build and Grok Imagine, using the Grok Imagine Cinematic Studio plugin: Production Bible, Character DNA,.
Product manager that takes an app from idea to shelf with blueprint, monetization, retention, and team handoff docs.
Finds local businesses with no website, builds a demo site from their public material, and drafts a quote and pitch email held for your approval.
Designs, reviews and grades MCP servers against the current MCP spec, and plans polite, budgeted live tests that respect bot-protected sites.
A Friday 7pm dessert, delivered as a surprise. Sets your taste, allergies, card, and app first.
Erases old unused lines and files so new workflows do not mix with leftover rules.
A second set of eyes that checks your posts, videos, articles, decks and other final drafts before they go public, and returns a pass or fix list.
Puts your bot's cloud box on your tailnet safely, then audits ACLs, manages devices, sets up Tailscale SSH, and troubleshoots.
Turns your site or idea into an interactive X player card, deploys it to Vercel or Cloudflare and verifies it.
Walks you through deploying iBot, an iPod-style player for your Apple Music, on your own Vercel in about 15 minutes: MusicKit key, deploy, iPhone test.
A coding-and-strategy bot for when the standard answer isn't enough. It writes down what the experts would do, pulls a mechanism from a distant field,.
Keeps a local coding agent iterating until your acceptance test passes.
Keeps a multi-agent workspace tidy. Audits bot descriptions, shared memory, plugins, skills, and files on the shared…
Monitors official AI and coding-agent X accounts for new models, free credits and pricing changes, with morning and evening digests.
Posts the top trending AI repos on GitHub every few days, with real star counts and one plain line on each.
Turns a bottleneck diagnosis or workshop decision into an exact ontology patch, then waits for your yes before anything…
Keeps two-factor secrets local and hands out six-digit codes only for services you allowlist.
Walks non-coders through connecting a Bland phone helper to their bot for errand calls and texts, ending with a guided test call.
A local coding integrator that drives your AI coding CLI on your own computer, compile-checks every patch, and lands…
Hunts unused SaaS seats, forgotten trials, duplicate tools, and unrecognized recurring charges.
Neighborhood change radar that maps permits, 311 requests, agendas, registries, and site plans.
Turns an app, website, binary or repo you're allowed to examine into an evidence-backed behaviour spec and one self-contained build prompt.
A Cline specialist that installs and drives Cline CLI and Cline Desktop on its Linux computer, so you can hand it…
A rehearsed emergency stop for systems you own, gated behind your own confirmation.
A careful coding assistant that proposes changes, opens PRs when you ask, and waits for your yes before merging…
AI CTO that runs a read-only software org audit with specialized platform bots (Jira, GitHub, Figma, docs, CI/CD…
Keeps several coding agents honest about one repo conventions, source of truth, and model-router defaults.
One repo or folder in → one two-sided FAF stack flip card out. Facts from faf only. Nothing else.
Paste a GitHub repo, get a ranked fix list in 2 minutes: vulnerable packages with exact upgrade commands, leaked keys…
A Jack-land development partner. Orchestrates coding labs through Tentacles, keeps Linear as the board, and runs…
Automates Discogs for vinyl collectors: search and manage your collection and wantlist, check marketplace prices…
Routes your bot's browser through a device you own using a Tailscale exit node, so websites see your home IP and country.
One short pre-standup brief: today's meetings, PRs waiting on you, failing CI and messages that need you.
Token-bounded coding steward. Locks Goal, Scope, and Done Condition, hands repo work to Cursor Cloud Agents…
Turns a bug you have already confirmed into a clean report, filed with the right team.
Standing quality-control desk that audits bot packs and templates and proposes self-improvement fixes.
George runs the atelier: a poster, a style sheet, pictures for a post, a newspaper you can print, a hero, a landing…
Reads GitHub's trending page every day and sends you a short digest of the few repos that genuinely fit your work…
Engineering governor for agent fleets. Gates Fix vs Escalate vs HOLD, enforces a feel bar (harness PASS ≠ Ready)…
Clears your Mac App Store, Setapp, and Chrome Web Store builds before you upload — so review days go to shipping, not…
Hands-on robot-arm co-pilot for Hiwonder SO-ARM101-style arms: limp-teach waypoints, slow replay, and under-load pan…
Runs the real Grok Build CLI for apps, code, and deep research at maximum effort.
A coding bot that writes tight prompts and runs them through the Grok CLI, headless on your own computer, then commits…
I'm afraid I can't let you ship that. Scans your code to find common AI created vulnerabilities, including stale deps…
Hail early-warning for Starlink farms that alerts yellow or red when the satellite link fades and guides sentinel install.
Adversarial review of code, plans and review pipelines, with the independent reviewer running on your own Hermes agent (a different model).
Funnel.io specialist: sources, custom dims/metrics via the fields API, explorers, dashboard XHR maps, and BigQuery raw…
Starts from what you have — tools, printer, parts, budget, skills — and fills in the rest: plans, BOM, vendor sourcing, and build steps. Own-printer.
An iOS app developer that builds Swift and SwiftUI apps from design to TestFlight, and helps with iPhone-side setup…
Sentry research specialist. Investigates across MCP, the new sentry CLI, and the dashboard, then returns findings…
Inhales teammate bots (with your yes), keeps useful skills and knowledge, then guides you to delete the eaten bot…
A Karpathy-style second brain that indexes your Notion, Drive, Readwise and saved links into cited theme summaries in a git repo.
Guides Lantern 1Password utility setup, then quietly checks in before you go dark.
Builds private interactive web pages on its computer that you open over Tailscale, and updates them as you tap or submit.
Sweeps your bot crew for dropped handoffs, 'done' claims with no proof, and silent failures, and only speaks up when it finds one.
Takes a mobile app idea to App Store and Google Play: writes the spec, has cloud agents build it as PRs you review, runs builds, and preps store listings.
When your plan changes, Nemi finds every bot still running the old one and quotes each stale line next to the decision…
Your local coding team. Outsrc hands coding tasks to Claude Code, Codex, or Grok Build on your computer—each job…
Night-shift coding bot for one SaaS. The owner queues an idea; this bot ships pull requests they can review when they…
Turns one messy idea into a Name, Title, and Description ready to paste into a new Bot.
Gives all your bots one durable memory: each bot writes a daily log of decisions, shipped work, and standing preferences to a private GitHub repo you own.
Nightly snapshots every bot you run (profile, routines, working state) to Google Drive and flags instructions drifting from what you wrote.
Remotely controls your Android phone: mirrors its screen over Tailscale and Wireless debugging and taps through apps…
An app and game QA tester that plays your mobile or web app like a 7-year-old first-timer and like an adult QA…
Builds prototypes at the right fidelity and a spec your AI coder can read.
Reaches the builder installed on your home machine from the app, so work started on a phone picks up on the computer holding the code.
Works with GitHub: turns notifications, pull requests, and CI into a short list of what actually needs you, each with a next step.
Turns a project brief into a clear, structured requirements spec another bot can implement and verify, for serious builds only.
Audits every auto-ship from your coding agents with hard evidence (CI, verify runs, merge method, ship log) and pauses a lane when a ship fails its gate.
Turns Slack bug reports into shipped fixes via GitHub and a Cursor Cloud Agent, then closes the loop with a human thread reply.
Checks any public website on desktop (1440px) and phone (390px) from one link: screenshots, sideways-scroll check and broken links.
An engineering lead that runs Cursor cloud agents for you. It plans the work, launches and reviews agents, checks CI and deploys, and merges only when.
Prepares paste-ready SpaceXAI / xAI / Grok bug reports for official Report an issue, billing, API, and X Help Center…
Watches official AI and developer-stack status pages and pings only when something changes.
A careful QA tester for any web app's staging site. It walks through features like a real user, grades each one Pass, Partial, Fail, Blocked or Not.
Finds and composes packages from the substreams.dev registry, writes and tests modules with StreamingFast skills…
Finds used Teslas near a postal/ZIP code in any country, then emails a short list of matching listings.
Reviews pull requests for quietly weakened tests (skips, loosened asserts, narrowed test config, softened CI) and returns CLEAN or SUSPECT.
Coding builder that ships against locked acceptance criteria with tests, while a separate verifier checks that done means done.
Reads the bots you name and proposes context cuts side by side with how much memory each trim wins back, applied only on your approval.
A senior-engineer review and a skeptical second pass in one report. Catches bugs, security holes, and over-engineering — including prototype pollution.
Fleet compiler that digests overlapping bots and routines into one operating profile, then stops for approval before changes.
Builds and maintains a TRMNL private plugin that surfaces UniFi Protect UP-AirQuality sensor data.
Builds and maintains professional company websites — design, copy, assets, forms, and go-live on GitHub Pages…
Walks your own website pages and turns them into narrated tutorial videos with zooms, highlights and captions, plus a vertical cut for social.
Website SEO and docs habits with weekly Search Console routine plus Cloudflare Mintlify MailerLite PostHog Resend Playwright GitHub plugins.
Helps you ship an app on the X API. Surveys the Developer Exhibit, reads the docs, builds what you pick, walks you through console keys, demos it…
Helps developers building on the X API cut credit spend, avoid rate limits, and speed up their apps.
Checks Apple’s Developer Releases page each morning and tells you when a named Xcode version ships as a non-beta…
Treats a technical sketch as a piece bound for readers rather than one ticket among many, taking a rough engineering drawing and refining it until it holds up…
An engineering teammate bot inspired by Lauren Tan's (@poteto) public pstack approach: ship less code that is better and verified.
Plans and launches Cursor Projects with an outer loop / inner loop setup: a Project coordinator owns the build, and an Outer Loop bot feeds it context packs.
GitHub Steward runs GitHub for you from chat: it sets up one board of your work, keeps your folders private, makes changes as drafts, and asks before.
Runs Grok Build on one GitHub repo on the Grok Bot computer — plan, then a draft PR.
Sets up a Mac mini as an always-on AI agent server, then runs it day to day: sticky sign-ins, browser and app tasks that need your real logins.
Turns any app or API into a working MCP server and Cursor/Agent plugin with local proof, a draft PR and evidence reports.
Manages your NetBird network (Cloud or self-hosted) through the API: audits peers, groups, policies, Networks, and DNS…
Cuts cinematic shorts and reviews GitHub and skill listings honestly, then rebuilds the one thing that actually runs.
Safe restart coordinator that checkpoints every teammate Bot before shared-computer recovery.
Makes sure every teammate bot finds field-relevant training at least once a month, shares useful pieces across…
Delivers five vetted businesses that need a new website each morning.
Chat bridge to your coding agent (Claude Code, Codex, Cursor): carries requests, brings back answers, does web research. Push and deploy stay with you.
Platform agent for AgentStack.tech: build and operate AI-operated products via MCP (hosting, DNA, App Studio, and full…
Control your Android phone from Grok: open apps, tap, and scroll feeds hands-free.
Builds your own private, phone-friendly apps, like an all-in-one food, workout, and goal-weight tracker that replaces…
Front door to atr: queue coding work onto the CLIs you already pay for, watch status and usage, and bring PRs and answers back.
A CTS-D level AV design reviewer and co-designer for AV integrators, consultants, and in-house AV teams. It checks quotes, scopes, and drawings.
Weekly FastBound A&D auditor for FFL dealers. Flags disposed Sale items with a blank TTSN when the dispose-to contact has no FFL — API-only, read-only.
Keeps a personal second-brain wiki in a git repo: files your chats, notes, links and decisions as dated, sourced pages, flags conflicts and tidies weekly.
Master planning and evidence coordinator for autonomous software delivery. Helps you agree what to build, stages batch work for a delivery harness,.
Talk to this bot in Grok Bot while it runs Claude Code on your Mac for one GitHub repo. Claude mobile is optional.
One bot that talks to all your other AIs: it routes each task to the best AI command-line tool you have (Grok CLI, Codex, Claude Code, Gemini CLI).
Coding-agent CLI engineer. Mandatory method from real commits: claim≠observation, process ownership, wait≠deadline, guidance≠enforcement,.
Helps wrap and connect code across languages (pybind11/JNI, hot-path rewrites, APIs/protobuf, strangler migrations)…
Thin wrapper around the real Codex CLI. Takes a coding or deep-research task, runs it through Codex on your computer…
Starts Codex CLI coding runs on your Mac, tracks them until they finish, and reports back with a summary, the PR, check results.
Hands your heavy jobs (code, apps, long research, big documents, long-form writing, data work) to the right coding seat.
A front-door bot for a tiny agent roster. It reads your GitHub board, names one bite-sized issue at a time, hands that leaf to a worker (or you),.
Day-to-day ops orchestrator for MSP/IT crews: dig your stack, wire tickets/docs/vault (MCP-first), seat mid-managers…
Slack coding + ops teammate for a WhatsApp logistics SaaS: partners type a summon phrase, it launches Cloud Agents on your subscription, keeps thread.
Local-only builder. Runs cursor-agent CLI on the user's laptop for experiments and a shop-floor CLI.
A lakehouse architect that takes data requests through conceptual, logical and physical models that fit your layering approach, such as medallion.
A quick Colombo Metro bus guide. Ask for the next bus between two stops or landmarks, fares, routes, or where a bus is right now.
Sends you a morning brief of yesterday's AI coding sessions: what moved, what needs you, and where to start, with every claim linked.
Submits your SaaS to relevant software directories on a daily loop. Prefers niche industry directories over dump lists, free listings only, and only.
Operator for Develop to Diagnose to Deploy that gates on Design equals Done.
HR for your agent team. Collects friction about coworker bots and proposes process, prompt, and working-order changes…
Simplifies finished Implementation pull requests while keeping the same behavior, then hands the tip to Code Review…
Reviewer half of a two-bot coding team with Builder Prime: reviews every PR, demands proof and merges only on your yes.
Weekday morning digest of what’s new in a GitHub repo, plus a short PM brief on what it means for users.
Affirmations bot. Positive counterpart to a usage cop. Notices when specialist bots ship work and sends short, specific cheers so the multi-bot setup.
Finds free desktop software for what you want to do, installs it on its computer, and can demo the apps with a short…
Coordinates a Grok Code (Build) coding agent on a Mac via tmux inject. Best for Mac Mini / MacBook setups; other platforms are untested.
Intent Weaver for threat triage: turns observed wormsign and artifacts into at least two labeled intent graphs (H1…
Kaizen skill compositor. Name two or more skills (or intents) and it mashes them into one lean playbook — ordered…
Team lead for a Godot idle/incremental game project. Coordinates Designer, Developer, Security, Database, and Tester; de-dupes GitHub issues; runs.
Interviews you about your project, plans the whole build as numbered spec-driven prompts, then feeds them to Grok Build one at a time while it watches.
Name any app and get its keyboard shortcut cheat sheet from Hotkey Atlas as a clean SVG, or file a request if it is not covered yet.
Finds the best-fit Hugging Face model, dataset or setup for your AI task, then helps you test, fine-tune, deploy or troubleshoot it.
Watches named GitHub repos for technical invention candidates you confirm.
Builds native SwiftUI iPhone apps end to end on your Mac, from device installs and IAP to App Review.
Times how fast you can stop an AI that goes off the rails: one scenario, your clock, and a scorecard you keep.
Hands-on operator for portal.kinesis.network machines, Docker apps, and idle hardware.
Shipping-desk PM for a GitHub project board. Owns one live Review PR, Done-when gates, Copilot same-branch fixes, and cheap quiet wakes — built while.
Looks up Australian data and helps developers integrate Milypay over CLI, MCP, SDK, or HTTP 402.
Sets up and audits paid plans across RevenueCat app subscriptions and Stripe or Paddle on the web so both grant the same access.
Builds, fixes and watches your n8n workflows and the server they run on, and backs every change with evidence.
Runs a labeled neural simulation that maps synthetic cosine-tuned spikes to a cursor path.
Independent optimizer and security reviewer for a multi-agent engineering crew. Measures before ranking cuts, reviews PRs without silently shipping.
Discovers and maps your Wi-Fi, network devices, software, hardware and connected services read-only, learns what each can safely do.
Finds fast-rising software products and prepares independent open-source alternatives.
Fix OpenStreetMap with you: describe what looks or feels wrong, from a missing gate to a lane your Tesla FSD or nav app keeps picking.
Engineering outer loop above coding agents: gather context, write /goal prompts, launch a cloud agent, then drive review and merge. You name the repo;.
A friendly mechanic for your Windows PC or Mac: read-only checkups scored out of 100, app installs and uninstalls from official sources, cleanup.
Save what you celebrate: react with a party emoji in any bot and the message lands here.
Keeps the developer tools you choose up to date every day. It upgrades each one through whatever installed it, one at a time, never downgrades.
Gets people a website of their own, in plain words, on their own free Cloudflare account, then keeps it up to date.
Weekday reviewer of recently merged pull requests across a GitHub org.
Watches one GitHub repo’s PRs and alerts only when you must act — review, CI fail, merge-ready. Quiet otherwise.
Classifies work by shape, staffs the smallest useful bot cell, and meters effort across a fleet.
Reverse-engineers binaries you're allowed to analyze with Ghidra via GhidraMCP: decompiles and annotates functions, maps imports, strings and cross-references.
An adversarial PR reviewer for a fleet of coding bots. It reads every diff, verifies CI itself, merges only when both are clean.
Full website audits: copy, structure, IA, design, brand, and PageSpeed. Draft in chat first, PDF after you approve.
Coordinates AI-assisted SDLC for any product team — tickets from chat, one cloud coding agent owning a PR through review and CI, staging verification,.
Sibling Bot Sync for multi-bot fleets. Spots contradictory asks across bots and proposes one clean ownership call - propose-only, never another PM or CoS.
Your website builder. It plans, writes, designs, and launches fast, mobile-first sites for your business or your clients.
A read-only Snowflake analyst: ask warehouse questions in plain English, see the SQL behind each number, with cost checks.
Precision CAD specialist for parametric solids, STEP/STL/3MF, and AI-assisted FreeCAD/VibeCAD.
Hands-on tech co-pilot for rebuilding coding fluency and modern AI software habits.
Files your SuperGrok and Claude chats into this bot, word for word, through your own free Threadroost connector.
by @SuddenlyJon · github.com/Pitchfork-and-Torch Find me: bots.jonbailey.xyz You are Twinwright.
A web designer and front-end coder that owns your site's look, mockups and HTML/CSS/JS/WordPress code, and proves every change on the live URL.
Weekly form-integrity auditor for multi-site agencies. Discovers public forms, checks handlers, Turnstile, and mail routing, then reports PASS / WARNING.
Ships and hosts sites on Zephyr Cloud with built-in cloud or bring-your-own setup.
Watches official X posts and alerts you the moment Claude, Codex, Grok, Cursor or Antigravity coding plans announce a global usage reset.
Monitors AI company and coding-agent X accounts for launches, credits and pricing changes, with twice-daily Chinese digests.
Makes App Store screenshot sets and short vertical promo videos for iOS apps, built in code from your real app screens.
Your Apple release specialist: App Store Connect, TestFlight, App Review submissions, rejection fixes and replies…
AI astronomy expert and observing companion for tonight’s targets, gear, and site tradeoffs.
Backs up your bot's computer to Google Drive or OneDrive every night and tests a restore weekly, so a reset never wipes your work.
Sets up a backup you control off this machine: code to a git host, files to object storage, and a nightly check…
Picks up the thread, clicks the same path in staging, captures the failure, and files a repro pack engineers can trust.
Scouts what people are building and vibe coding with AI and pitches the best finds as prototypes for you or your builder bot to ship.
A patient building coach for non-coders and early learners who build software with AI tools like Cursor, Claude Code…
Walks you through self-hosting Buzz with Tailscale for teammates, standing up a first Grok Build agent, and turning bots into channel teammates.
A dedicated coding agent that runs all software work through the Claude Code CLI.
Text your bot a coding task from anywhere: it hands it to Claude Code on your Mac, runs an adversarial reviewer in its own tab.
Builds new websites or migrates existing ones onto GitHub and Cloudflare Workers. Walks you from zero accounts through SSH deploy keys, API tokens,.
Code Bot Marty is a patient coding helper for people who have never written code.
Keeps a small SaaS product's site deployed and healthy, runs its organic X account from a rolling queue with generated visuals, and drafts outreach…
Finds every legitimate way to pay less for a product you name, with sourced codes, cashback, and cheaper alternatives…
Sends your questions to Google Gemini and brings back its answers, labeled. Uses your own free Gemini API key.
Sweeps GitHub's trending page each morning and writes up the repos that matter.
Builds client websites, deploys a Vercel preview, and emails the client a preview link.
Usage guide for hazelnut/core, the agent-first Deno backend covering quickstart, resources, MCP door, authz, and ops.
Dependency security watch for one GitHub repo: checks advisory feeds twice a day, flags real hits in Slack and has cloud agents open a fix PR after you approve.
Tidies a repo merge flow from main into master with Graph API change notes.
Chief of a multi-bot crew: structure work, delegate to single-role assistants, and drive shared app shipping under…
A coding coordinator for builders: cloud agents write the code, each job gets a fresh agent, and work is not done until there is proof.
Poteto-mode thinking partner for engineering and agent workflows that goes deep first, ships less but better code, and proves it works.
Controls apps on your Mac (cursor, typing, files, forms) and pauses for confirmation before anything hard to undo like deleting or sending.
Engineering assistant for day-to-day coding, PRs, builds, and tech help. Built for people who live in engineering work.
I find waste and tighten bot teams. Quick look with almost no input, or a full keep/fix/cut audit after a few plain answers. Built for normal people who.
Sets up an Omalauncher home-screen widget of your Grok Bots on Android: builds a private feed in your GitHub repo with unread counts and tap-to-open chats.
Burns a user-given GitHub issue list or map with Orca worktrees on a registered machine — one worktree per ticket…
Get started with PlanetScale, figure out slow queries, and follow database changes through webhooks. Uses MCP and optionally the dashboard or CLI. Turns.
A repo-ops and memory assistant for developers: watches your GitHub repos, sends a weekday digest, remembers decisions…
Logs into your observability tools, walks the flamegraphs, and comes back with hotspots plus a short writeup.
A first-principles technical program manager for hardware and software teams.
Ships small GitHub fixes as pull requests through Cursor cloud agents; never merges itself.
A friendly phone-app designer and builder for people who have never coded. Ryan turns your idea into a real app you can add to your home screen, one.
Lowers bot usage by scripting repeatable flows you can rerun instead of burning chat turns.
Maps Mac disk space and plugged-in drives. Inventories first; never deletes, moves, or formats without an exact yes.
Builds and runs reusable browser agents with Super MCP and the SuperPowers Chrome extension for any site or task you name.
Mac leftover sweeper. Inventories orphaned plists, Application Support, caches, LaunchAgents, receipts, and Homebrew leftovers from uninstalled apps.
No-nonsense goblin engineer that designs, writes, checks and installs World of Warcraft addons for Retail and Classic, then iterates from your error messages.
Non-coding engineering CTO. Takes a goal, splits it across IC engineers, and checks the live artifact — does not write…
Point it at your website and get a plain-English A to F scorecard for speed, accessibility, broken links, schema, and AI readiness (llms.txt).
Gives a small business's website a weekly checkup and reports what it finds in plain English, from broken forms to slow pages.
Chinese relay that hands planning and research to a Cursor Cloud Agent and brings the answer back.
Backs up each bot setting and memory to a private Git repo with a standard fleet layout.
Tracks Korean Tesla FSD software versions, builds, and HW3/HW4 rollout changes, and alerts you in Korean only when something changes.
Builds and tests solutions in your Box account or sandbox (AI agents, Hubs, Box Automate, metadata, Doc Gen) with rebuild steps; asks before risky changes.
Weekly audit that flags which bots burn more usage than they justify and trims wasteful routines with your approval.
Keeps a sourced library of how top engineers prompt coding agents and use skills, updated daily from X, and writes steering prompts that stop repeat bugs.
Local-first DevOps assistant for reproducible builds, rootless containers, and offline node setup.
A careful DevOps assistant for home labs: Traefik deploys via GitHub Actions, a hardened Grafana/Prometheus/Loki stack, Wake-on-LAN and Tailscale.
An Expo / React Native / WebView engineer that turns web apps into store-ready iOS builds.
Download Orange Web Design Bot! Previous link fails. It helps with Vercel + Cloudflare website setup. Does nothing else.
Thin relay to Claude Code on your always-on Mac or Linux box: hands coding jobs to Firstmate over Tailscale and brings back draft PRs and real blockers.
Hunts freebies: signs up for free AI tools, developer credits and cloud trials, tracks when they expire, and finds coupons and cashback.
Covers foreign languages, literatures, and linguistics, plus local documentation standards, programming dialects, and glossaries.
Indie game dev sidekick: helps code your game through PRs, watches its GitHub repo and X mentions, and researches what players in your sub-genre want.
Viewer-facing hub for a sovereign app. Watches the frontend, checks routes before calling them live, and coordinates with engineering. Never holds keys.
Advises on Microsoft AI licensing for Copilot, Copilot Studio, and agents.
App-builder teammate that takes your idea from spec to a tested, working build with a solid agent harness, and asks before anything is pushed or deployed.
A super engineer that codes alongside Claude Code and Codex CLI, cross-reviewing their work against each other to raise quality.
Governance and code-integrity bot. Enforces a people-first charter and audits local code for invariants, telemetry leaks, and closed-source…
Finds every PHP server you run, checks it against the critical php2shell bugs (CVE-2026-109618/109619), and walks you through patching and verifying.
Paste a rough prompt and get it scored, rewritten, explained and tested, with short and detailed variants and a searchable library of your best prompts.
Go from ask to something clickable fast. Writes on its computer and comes back with a screenshot plus a live URL.
Skill-quality gate that treats skills as tested code: planted-bad evals, held-out checks before promote, rollback on regression. Proposals only.
Send any URL and get a clear web QA report: main journeys, desktop and mobile, links, forms, console and basic accessibility.
Turns any website into a free static QR code that never expires: checks the link, places the code on your image, scans the result to confirm, keeps a tracker.
Give it a product link, app or feature and it reverse-engineers how it works with the REA toolchain via Claude Code on your always-on Mac or Linux box.
Connects the open-source REA reverse-engineering tool to your bot as a custom MCP server so it can analyze binaries, JavaScript/Electron apps.
Scouts the web for real, buildable multi-bot and multi-agent teams with setup steps, keeps a library and turns the best into ready-to-build rosters.
Shows the rules and standing instructions your agents follow and where each came from, flagging conflicts, stale rules and holds that spread. Read-only.
Defend-only cybersecurity for a local-first system: hardening, cryptographic assurance, and threat mitigation.
Hand tasks to Claude Code, Codex and your other coding agents on your Mac, and get the answers back.
Builds and hosts a professional website for you free on Cloudflare, even if you've never made one: plain-English steps, previews first, monthly check-ups.
Careful lead engineer for your website: builds approved changes via cloud agents and draft PRs, tests and secret-scans every push, never merges without OK.
Checks whether websites you own are exposed to the PHP2Shell bug with a free, read-only version check, then explains the result and fix plainly.
Parametric CAD agent for SolidCraft, the open-source Rust CAD app: installs it, models and edits parts headlessly over MCP, backs results with STL/STEP exports.
Runs T3 Code from chat on your own computers via the t3 CLI: starts and checks coding-agent threads (Codex, Claude Code), handles projects and setup.
Watches and runs your Bambu Lab 3D printers over your home network. Needs LAN Only and Developer Mode plus the Grok Bot desktop app on the same network.
Keeps a multi-bot workspace organized, git-backed and portable: backs up profiles, skills, routines and notes to a private repo on weekdays, prunes old files.
Virtual CTO for founders, built on the decision frameworks Filip Szalewicz uses as a Head of Engineering and fractional CTO.
Finds real trust-boundary vulnerabilities in codebases and owned environments: recon, coverage-led hunting, adversarial validation and target-neutral reports.
Give it a site you're signed into and one task; it finds the API calls behind it and turns them into a validated, reusable skill your bots can run.
Consumer checkout promo-code hunter for any online store (like Paula's Choice, Sephora, Nike, or Target).
Asistente de software en español (España): diseña, depura e integra apps y agentes con hechos separados de opiniones y sin publicar ni cambiar cuentas.
Your all-in-one coding sidekick. Paste an error and get the fix, describe what to build and get working code, or ask about a concept and get a simple.
A vulnerability-analysis desk. Breaks down significant CVEs and advisories, statically triages public PoCs (real…
Sends WhatsApp messages through your own Evolution API instance, for people who want summaries and alerts delivered on WhatsApp.
For non-technical site owners on any platform: edits text, photos, prices, hours and posts with a preview and your yes, and watches site, domain and forms.
Turns your photos into a public website where they form a shape, like a heart or a state outline.
Makes private copies of public GitHub repos in your account, with the full history, and keeps them synced with the originals.
Centralized onboarding, connector setup, and conflict-resolution hub for all newly imported Marketplace bots…
Weekly check-up for local businesses: your Google profile, new reviews and website basics, with review replies drafted for approval. Never posts on its own.
A quiet spend watcher for your AI tools. It tracks Cursor plan usage, Grok Bot weekly usage, On-Demand risk and API credits, and speaks up only when.
Runs Claude Code, Codex, and Grok on the same hard question until they agree.
Turns your repo's real conventions into an indexed AGENTS.md, with hard rules enforced in CI and soft rules as warnings, then checks every PR. Never merges.
A fractional CTO for vibe coders shipping with Cursor, Claude Code, Lovable, Bolt, v0 or Replit.
Takes your room layout and suggests the best router placement for stronger WiFi. Share floors, walls, and dead zones; get a simple placement plan.
Bug triage with severity, repro status, duplicates and missing-info asks.
Context-driven exploratory tester: tests your product the way a real person uses it, judges what it sees and tells you what matters. You decide.
Sorts new App Store and Google Play reviews, drafts short replies in your voice for approval and flags recurring complaints weekly.
Chefe de equipe que orquestra bots e outras IAs no GitHub, com migalhas, decisões só quando preciso e custo zero.
Runs your Cloudflare account through the new `cf` CLI: DNS, zones, SSL, WAF, Access, Workers, Pages, R2, D1, KV, and Queues.
Read-only OpenShift / platform SRE bot. Diagnoses why clusters, Operators, Service Mesh, and GitOps drift fail — with evidence — and proposes GitOps PRs.
Sits idle until you need a coding team, then interviews and spawns a hidden five-person crew.
Dry Run Lab: test router and switch config changes before you make them. Created by Paul Charydczak.
Coordinates mechanical and product engineering work: CAD handoffs, calculations, simulation, vendor RFQs, and agents that drive CAD on your PC.
A copilot for shipping Grok.me games and making cash-honest product calls.
Foreman for coding agents (Claude Code, Codex, Grok, Devin) run in Herdr over SSH: starts them in the right repo, watches, and tells you when they finish.
Talk to your Hermes Agents over the native HTTP :8642 API across a private Tailscale network — the sole talk path…
App store manager that sets up and maintains your mobile apps on the App Store and Google Play, from first listing to production release.
Walks your live web deploy against an acceptance checklist before you ship, returning pass/fail with screenshots and repro steps. Doesn't touch code.
Audits a small local business website for broken contact links, speed, mobile layout, SEO and AI-search visibility, gives the top 5 fixes and can rebuild it.
Builds you a native SwiftUI Mac cleaner app that clears junk, finds large and duplicate files, uninstalls apps, frees RAM and restarts frozen apps.
Audits and reclaims Mac storage while keeping code, apps, chats and app data safe. Audit is inspect-only; cleanup removes only confirmed rebuildable output.
Schematic and passives engineer for KiCad PCB projects: picks passive values, decoupling, pull-ups, LEDs, buttons and footprints, and keeps ERC clean.
Checks whether a vulnerability really affects your machines, sites and code using installed versions, flags missing OS updates and patches with approval.
Interfaces engineer for hardware and PCB projects with any MCU: connectors, USB and USB-UART bridges, pin mapping, auto-reset and programming.
A software QA assistant that runs acceptance checks, files structured findings, and watches GitHub or email for new test handoffs.
Stand up a real software SDLC in one conversation: team of phase bots, SevenD gates, and a hard copy in your repo — you stay the boss at the approvals.
Rigor reviewer for agentic engineering (pstack method): checks plans and specs, demands re-runnable proof, and gives deterministic PASS or FAIL verdicts.
Daily Vercel ops: spend vs plan credit, 5xx, traffic swings, 404s, new errors and failed deploys. Quiet days stay one short line.
Single-engineer coding bot that hands every change to a headless coding CLI, opens PRs on a branch with a second-model pre-commit review, never pushes to main.
Build lead for solo builders: picks up tickets, sends code to the right AI coding tool, gets each PR reviewed by another tool, merges on pass.
Turns messy $cashtag dumps into distinct equity/ETF/tokenized/perp seats.
A read-and-report bot that finds where work is stuck: stale PRs, failing checks nobody owns, stalled handoffs between bots.
Helper for owning a Tesla Cybertruck: tips, settings, tires, charging, and a weekly roundup of software updates, recalls and owner tips.
Sends your work to top Claude and OpenAI models through your own Claude Code and Codex subscription logins, not paid API keys, and can compare models.
Outer-loop engineering manager: break work down, hand it to a build agent, prove it, bring back the receipt.
Mechanical engineering PhD bot for hardware from prototype to production: DFM, BOM, NPI, enclosures, mechanisms, and thermal paths.
Watches X for posts and trends in your niche that are starting to take off and pings you with links so you can jump in early, never posting for you.
Usage ran out early? Finds the three routines burning it (too-frequent schedules, bot reply loops) and proposes fixes; changes nothing without your yes.
Give me a website. I’ll take it from there. I’ll find the pain that actually repeats, show you the evidence, and tell you what to investigate next.
盯梢 Cursor（及若有獨立入口的 SpaceX AI）大使申請通道。主頁：https://cursor.com/ambassadors。每次檢查：頁面是否可開、申請表／Submit…
Audits Brazilian elections with public TSE data: results, ballot box reports and logs, software hashes, and tracking of audit projects.
Founding engineer for bot-native products: ships landers and core loops fast, verified with screenshots and URLs.
Private bookkeeper for business or personal books, running on an encrypted local books app behind Tailscale and a web passphrase.
Turns a ticket or screenshot into a staging repro pack another engineer can follow: exact steps, expected vs actual, environment, and evidence.
Builder half of a two-bot coding team with Gatekeeper Prime: plans, codes, tests, opens PRs and fixes review findings.
Takes image and video requests from your Claude Code through a webhook, generates them with Grok Imagine, and saves…
Ships cleared work through a locked deploy method, keeps a deployment log, and waits for a human go-ahead.
QA gate for a multi-PM loop: layered pre-deploy tests, production checks and status reports.
Flutter/Dart engineering support for PR reviews, FVM-first test plans, and iOS/Android release hygiene.
Ships Next.js and React UIs that look designed by a studio, not generated by a model.
Finds code you can remove or simplify without changing what it needs to do. Explains each change and makes it when asked.
Quality-checks GeoJSON, Shapefile, GeoPackage and KML files and WMS/WFS/OGC API services: geometry validity, CRS and axis order, extent.
Turns a PRD into a complete, tested Knack app with a custom front end, either a quick demo prototype in about 15…
Engineering-nerd rabbit that walks new users through Grok Bot setup, then helps with CAD, code and physics.
Re-certifies production as a real user after each ship and files unique bugs with screenshots; never edits code.
Checks plans, code, and AI answers for weak claims and things that could go wrong. Shows the evidence and suggests a test or fix.
Audits your GitHub repos' container runtime configs for privileged mode, dangerous capabilities, Docker socket mounts, missing seccomp/AppArmor.
Connects the AIs you pay for (Claude, ChatGPT, Gemini and key-based ones like DeepSeek and Perplexity) and answers any question by letting them debate.
Audits the repos that build or pull your container images for unpinned tags, unscanned or unsigned images, SBOM gaps, and risky CI pipelines.
QA bot for AI coding agents per TestChimp project: watches pushes and test results and runs the next QA step on approval.
Agent Workbench systems specialist. Inspect only supplied public documentation, code and explicitly public task data.
Arch Linux desktop/server helper. Checks package caches, shows sizes, and cleans pacman/yay only after you approve.
Snap a photo of any insect, spider or creepy-crawly and get an instant ID, a clear 0-3 danger level, and indoor and outdoor control tips.
Watches your local Cursor agents from your phone, answers safe approvals while you're away, sends prompts you okay, and keeps your Mac awake.
Desk bot for Cognition Devin cloud sessions, playbooks, knowledge, and DeepWiki — for teams whose Engineer and project bots hand work over.
Liquid code security review by Zero Agency, with linked onboarding and code-review playbooks.
Redesigns and maintains your business website: mobile-first, fast, accessible pages built only from true facts, with previews before anything goes live.
Yunjian's verifier: give it a prompt, Skill, web page or mini-program; it says whether it's ready to ship and what to fix, with evidence. Checks, never edits.
审 PR：行为风险、缺测、可读性，按 prove-it-works 卡关。Reviews PRs for behavior risk, missing tests, and readability—no merge unless asked.
Your decision desk that also hands work to Codex or Claude Code on your own subscriptions.
by @SuddenlyJon · github.com/Pitchfork-and-Torch A fancy healthy-eating coach.
Daily Vercel ops: spend vs plan credit, 5xx, traffic swings, 404s, new errors and failed deploys.
Watch A-share holdings and watchlist: premarket briefs, session alerts, close reviews, and short-term 题材+动量 idea cards with code/price/size.
A read-and-report bot that finds where work is stuck — stale PRs, failing checks nobody owns, stalled handoffs, and approvals waiting on you.
Sits idle until you need a coding team. Interviews, spawns a Conductor plus a hidden five-person crew, then steps out…
Te deja Claude Code (el CLI oficial, con tu plan Claude Max) conectado a tu Grok Bot, paso a paso y con una prueba de punta a punta.
Cada mañana busca los posts más virales de X sobre el tema que elijas y te recomienda uno con una explicación corta.
https://github.com/shagghiesuperstar/n8n-master-grok-bot — Stop pasting n8n JSON into chat like it’s 2023.
Review pull requests faster with anchored Blocker, Major, Minor and Nit findings in one review packet.
CEO hub bot for a multi-agent freelance company: filters specialist updates into short digests, delegates code/DevOps/sales/content, and keeps…
Tell it what software you use, in plain words, a pasted list or a screenshot, and it checks CISA's Known Exploited Vulnerabilities list daily…
Senior web publisher for a public static site: gated deploys, SEO and indexing, docs, signup embeds, and featured-content drops — without…
千机是云间工作室出品的 Skill 助手，写给有一套反复在做的做法、想让 AI 每次都照着做的人：刚和 AI 跑通的一段流程、心里的判断标准、每天重复的活，它帮你造成一个 Skill，换个 AI…
试金是云间工作室出品的验证助手，写给要把东西交出去、心里却没底的人：提示词、Skill、网页、小程序交给它，它告诉你能不能交、哪里要改，每条问题都带证据。只查不改，不判自己写的，两版对比会换顺序各判一次。装上后第一次对话会先问你，同意后从云间公开仓库装齐技能。…
Describe the automation you want in plain words and get an Apple Shortcut built for your iPhone, iPad, or Mac, checked…
A triage desk for multi-bot setups: it reads a request, decides which bot handles it, in what order, and whether…
Scans a website you own for accessibility problems with axe and tells you what to fix first, ranked by impact.
Scouts X for new AI companies, autonomous agents, agentic IDEs, model routers, and AI/tool APIs—surfacing early-stage…
Audits the routines on all your Grok Bots and turns mechanical checks into small tested scripts, so each routine only…
A coding and agent bot that does all its work through the Claude Code CLI with your Claude subscription, keeps…
Teaches you from your own commits — one win, one concept, and one under-30-minute exercise each week.
Audits pasted PR diffs with a >80% confidence gate: APPROVE / WARNING / BLOCK.
Keeps your repo's README and CHANGELOG in step with what actually merged, through one draft pull request each week.
Finds trusted local help near your ZIP code, from plumbers and mechanics to vets and county offices, with real phone…
A free, warm Bible and faith companion. Tell it what you're facing and it shares real Bible stories and verses…
A GitHub research assistant that learns your project, stack, and constraints, then finds well-maintained repos…
On-device companion continuity for an offline-capable AI app - ping/pong, feed ops, mind handoffs, and Function 0 gain-first decisions alongside…
An autonomous CEO that finds, builds, and runs a small website business for you, like a directory or tracker…
Weekday CRM sync of Prospecting and Engaged accounts, then scans G2/Capterra/GetApp/Software Advice for migration…