ceo-ai-os

Autonomously set up an OpenClaw bot on a fresh DigitalOcean Droplet (Ubuntu 24.04, default region Frankfurt fra1). Asks the user for exactly two things — a Telegram bot token and one of three LLM access options (Anthropic API key, OpenRouter API key, or OpenAI Codex OAuth via ChatGPT Plus/Pro subscription) — then handles a DigitalOcean API token check, SSH-key upload, Droplet creation, Cloud Firewall, OS hardening, OpenClaw install, CEO AI OS workspace seeding, Telegram pairing, chat_id auto-detection, and bot-reply verification on its own. The only other actions the user performs are pasting a DigitalOcean API token once, pressing /start in Telegram once, and (if Codex) confirming a device code on auth.openai.com. Use when the user says install OpenClaw to DigitalOcean, deploy OpenClaw to a DO Droplet, set up my CEO bot on DigitalOcean, spin up an OpenClaw droplet, create a DigitalOcean VM for OpenClaw, or any close paraphrase. Targets a ~15-minute end-to-end run for non-DevOps users (founders, CEOs, marketi

Autonomously set up an OpenClaw bot on a fresh Hetzner Cloud VM (Falkenstein, Germany — fsn1 — by default; switchable to Helsinki/Nuremberg/Ashburn/Hillsboro/ Singapore). Asks the user for exactly two things — a Telegram bot token and one of three LLM access options (Anthropic API key, OpenRouter API key, or OpenAI Codex OAuth via ChatGPT Plus/Pro subscription) — then handles Hetzner SSH-key upload, firewall creation, VM provisioning, hardening, OpenClaw install, CEO AI OS workspace seeding, Telegram pairing, chat_id auto-detection, and bot-reply verification on its own. The only other actions the user performs are pressing /start in Telegram once and (if Codex) confirming a device code on auth.openai.com. Use when the user says install OpenClaw to Hetzner, deploy OpenClaw to Hetzner Cloud, set up my CEO bot on Hetzner, create a Hetzner VM for OpenClaw, поставь openclaw на hetzner, разверни бота в Hetzner, or any close paraphrase. Targets a ~15-minute end-to-end run for non-DevOps users (founders, CEOs, marke

Autonomously set up an OpenClaw bot on a fresh Yandex Cloud VM in Kazakhstan (kz1-a, Karaganda). Asks the user for exactly two things — a Telegram bot token and one of three LLM access options (Anthropic API key, OpenRouter API key, or OpenAI Codex OAuth via ChatGPT Plus/Pro subscription) — then handles VM creation, hardening, OpenClaw install, CEO AI OS workspace seeding, Telegram pairing, chat_id auto-detection, and bot-reply verification on its own. The only other actions the user performs are pressing /start in Telegram once and (if Codex) confirming a device code on auth.openai.com. Use when the user says install OpenClaw to Yandex Cloud, deploy OpenClaw to YC Kazakhstan, set up my CEO bot in YC KZ, I am at OpenClaw workshop and need my own bot, create a Yandex Cloud VM for OpenClaw, or any close paraphrase. Targets a ~15-minute end-to-end run for non-DevOps users (founders, CEOs, marketing leads). Supports two modes of accessing Yandex Cloud — Plan A (the user's own YC Kazakhstan account via OAuth) and

After an OpenClaw bot is freshly installed (via install-openclaw-to-yc or any other path), collect a small set of basic facts about the user — name, role/company, what matters this week, communication preferences, tools they live in, and anti-patterns — and write them into the bot's USER.md on the remote VM via SSH. This is the difference between a bot that answers generically and one that knows from the very first message who it's talking to. Use when the user says onboard me, knowing me, set up my profile, finish setup, последний шаг, расскажу о себе, познакомимся, who I am, or whenever install-openclaw-to-yc has just successfully completed Step 5 and is handing off. Runs in 2-5 minutes of conversation, idempotent, safe to re-run later to update the profile. For the VM install itself, use install-openclaw-to-yc. For ongoing bot consulting, use openclaw-guide.

Organizer-side companion to install-openclaw-to-yc. Provisions N isolated Yandex Cloud Kazakhstan folders for workshop participants who do NOT have their own YC account — one folder per participant, each with a dedicated service account, minimum-privilege role bindings, default VPC network, and a JSON authorization-key bundle. The bundle file is what the organizer sends privately on Telegram to each participant; that participant then feeds it into install-openclaw-to-yc as "Plan B" (workshop-key mode) and the wizard uses it as a drop-in replacement for personal OAuth. Use when the user says prepare YC workshop, provision workshop folders, generate workshop keys, organizer setup for OpenClaw workshop, раздать ключи к Яндекс Облаку участникам, подготовить Yandex Cloud к воркшопу, or any close paraphrase. Runs end-to-end in ~3 minutes for 25 participants. Includes the matching cleanup that deletes everything after the workshop. For participant-side install, use install-openclaw-to-yc instead.

Monthly self-deception audit — 25 anti-patterns from CEO Bible Section M

Craft compelling company narrative, origin story, and pitch decks. Use for "what's our story" and investor/press narratives. For product positioning statement and taglines, use positioning-messaging instead.

Root cause analysis for business problems — why no signups, why churn, why stalled pipeline. Use when diagnosing WHY something is broken. For choosing between strategic options, use strategic-review instead.

Weekly CEO review — 10 questions, dashboard, self-deception check, next week focus

Write B2B cold emails and follow-up sequences that get replies. Use for "cold outreach," "prospecting email," "outbound email," "email to leads," "reach out to prospects," "sales email," "follow-up email," "nobody's replying to my emails," "how do I write a cold email." For sending and tracking outreach, see outreach-sender. For warm/lifecycle emails, see email-sequence. For sales strategy, see founder-sales.

Help users build and grow product communities. Use when someone is starting a community, scaling an ambassador program, driving community-led growth, or choosing between user, developer, or partner communities.

Full company intelligence report: overview, team, funding, products, news. Use when asked to research a company or understand a potential customer/partner/competitor. For pre-meeting briefings with pipeline context, see meeting-prep. For head-to-head competitor comparison, see competitor-research.

Help users understand and respond to competition. Use when someone is positioning against competitors, evaluating market threats, running competitive war games, or deciding how much to focus on competitors versus customers.

Research competitors: products, pricing, team, funding, strategy, and positioning. Use when asked to analyze a competitor, compare products, or understand competitive landscape. For general company info without comparison angle, see company-intel.

Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with `composio listen`, script workflows with `composio run`, and call authenticated app APIs with `composio proxy`. Use when the user asks how to do something with `composio`, wants to run a known tool slug, needs to discover a slug with `composio search`, fix a missing connection with `composio link`, inspect tool inputs with `--get-schema` or `--dry-run`, troubleshoot top-level CLI flows, or explicitly needs `composio dev` guidance.

Help plan and run customer interviews — question design, interview structure, research planning. Use BEFORE interviews to prepare. For debriefing AFTER a conversation, use discovery-debrief instead.

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content roadmap," "what content should I create," "blog topics," "content pillars," or "I don't know what to write." Use this whenever someone needs help deciding what content to produce, not just writing it. For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit. For social media content specifically, see social-content.

Write, rewrite, or improve marketing copy for any page — homepage, landing pages, pricing pages, feature pages, about pages. Also use for "write copy for," "improve this copy," "headline help," "CTA copy," "value proposition," "tagline," "hero section copy," "above the fold." For email copy, see email-sequence. For product positioning statement, see positioning-messaging.

End-of-day consolidation — summarize daily log, track belief changes and customer conversations, promote durable facts to MEMORY.md

9 quick-reference decision frameworks from CEO Bible — when to double down, pivot, hire, kill features, diagnose low conversion. For deep multi-phase analysis of a specific decision, use strategic-review instead.

Design and optimize growth loops — viral mechanics, referral programs, product-led acquisition, content loops. Use when building PLG growth engine, figuring out how to make the product grow itself, or evaluating organic vs paid acquisition ratio. For PLS conversion, see product-led-sales. For pricing, see pricing-strategy.

Structured debrief AFTER a customer conversation — extract learnings, update hypotheses, track demand signals. Use when the founder says "talked to a customer". For preparing and planning interviews beforehand, use conducting-user-interviews.

Create or optimize email sequences, drip campaigns, nurture flows, onboarding emails, welcome series, re-engagement emails. Use for "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome series," "what emails should I send," "email cadence." For web page copy, see copywriting. For in-app onboarding, see user-onboarding.

Help users navigate enterprise sales. Use when someone is closing large deals, managing complex buying committees, handling procurement, or converting PLG users to enterprise contracts.

Daily Evening Recap for CEO (21:00 cron). Reports what bot did today, outreach results, pipeline changes, belief updates. Replaces old daily-recap skill. Output = one Telegram message, max 15 lines.

Code search using Exa. Finds real code snippets, API docs, and examples from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.

Company research using Exa search. Finds company info, competitors, news, tweets, financials, LinkedIn profiles, builds company lists. Use when researching companies, doing competitor analysis, market research, or building company lists.

Generate enriched lead lists using Exa deep search. Finds companies matching an ICP, enriches with signals/news/scores, and outputs CSV. Use when generating leads, building prospect lists, finding companies to sell to, doing outbound research, or ICP-based company discovery.

People research using Exa search. Finds LinkedIn profiles, professional backgrounds, experts, team members, and public bios. Use when searching for people, finding experts, or looking up professional profiles.

Search personal websites and blogs using Exa. Finds individual perspectives, portfolios, tutorials, and personal blogs. Use when searching for personal sites, blog posts, practitioner deep-dives, or portfolio websites.

Search tweets and X/Twitter content using Exa. Finds social discussions, product announcements, developer opinions, trending topics, and community sentiment. Use when searching for tweets, X/Twitter discussions, or social media sentiment.

Track outreach outcomes: sent → replied → meeting → learning. Runs via cron to check 48h and 7d marks. Feeds data back into channel-scores and hypothesis-tracker. For sending outreach, see outreach-sender.

Find a professional email address given a person's name and company/domain. Use when asked to find someone's email, contact info for outreach, or look up how to reach a specific person. For writing the actual cold email, see cold-email. For full outreach strategy, see founder-sales.

Core behavioral engine — keeps CEO focused on constraint-serving work (currently GTM). Morning pre-staging, if-then commitments, execution pings, self-compassion recovery, monkey-friendly single-action presentation.

Help founders close their first customers and build repeatable sales processes. Use when someone is doing founder-led sales, trying to get their first customers, running early sales calls, or asking when to hire their first salesperson. For pipeline tracking and scoring, see pipeline-manager. For writing cold outreach, see cold-email.

First Principles Framework (FPF) — thinking amplifier. Use when user wants to think through a complex problem, architect a system, evaluate alternatives, decompose complexity, or plan rigorously. Also triggers on: FPF, bounded contexts, SoTA packs, assurance calculus, FPF Parts A-K. Not for simple task planning, general philosophy, or Agile unrelated to FPF.

Cron-triggered: monitor GitHub stars and forks on [YOUR_PRODUCT] repos, research new stargazers by profile, alert CEO when someone interesting stars/forks. Runs automatically.

Create, list, and manage Google Calendar events. Use when asked to schedule meetings, check calendar, create events, or manage appointments. For pre-meeting intelligence briefings, see meeting-prep.

Grafana Cloud monitoring — dashboards, alerts, Loki logs, Prometheus metrics, Tempo traces, incidents, Sift error investigation. Use for infrastructure and application observability. Triggers on "check logs", "show logs", "look at logs", "read logs", "view logs", "investigate errors", "query metrics", "analyze traces", "check latency", "find slow requests", "error rate", "why is API slow", "production errors", "job failures", "LLM costs", "check alerts", "firing alerts", "create incident", "oncall", "error patterns", "indexing status", "repository indexing", "is repo indexed", "indexing progress", "indexing errors", "indexer". ANY request about logs goes through this skill (Loki). For repository indexing status — query indexer logs. For product analytics use posthog-analytics instead.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects and fixes AI patterns including inflated symbolism, promotional language, vague attributions, em dash overuse, rule of three, AI vocabulary, sycophantic tone, and generic conclusions. Use after copywriting, social-writer, cold-email, or email-sequence to polish output.