CodeAlive-AI

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.

Query external AI agents (Codex, Gemini, OpenCode, Claude Code headless) in parallel for independent second opinions, code review, bug investigation, and consensus on high-stakes decisions. Agents and models are configurable in config.json. Use for architecture choices, security review, or ambiguous problems where independent perspectives matter. Not for simple questions answerable from docs or the codebase — use web search or repo exploration instead.

First Principles Framework (FPF) — thinking amplifier. Use when user wants to think through a complex problem, architect a system, evaluate alternatives, decompose complexity, classify problems, define quality attributes, plan rigorously, decide under uncertainty, establish causality, reason about time and trends, describe or synthesize architecture, check mathematical model fit, govern ontic/U-kind introduction, publish multi-view artifacts, refresh SoTA packs, trace provenance, or improve pattern quality. Also triggers on: FPF, bounded contexts, SoTA packs, assurance calculus, decision theory, causal reasoning, temporal reasoning, architecture description, modularity, structural adequacy, cultural evolution, quality gates, lexical discipline, FPF Parts A-G/I. Not for simple task planning, general philosophy, or Agile unrelated to FPF.

Hands-on playbook for Windows 11 disk cleanup, dev-machine optimization, and proactive health alerting. Use when the PC is full or slow, when a BSOD / Kernel-Power 41 / crash dump / commit-memory pressure happened, when the user asks to free disk space, audit storage, set up disk/memory alerts, or restore the same monitoring on a new PC. Built around native Microsoft-supported tooling (Storage Sense, cleanmgr, DISM, pnputil, vssadmin, wevtutil, powercfg) as the safety floor, a drift-protected HTML cleanup UI, and a Task Scheduler + BurntToast alerter. Covers dev machines with heavy AI/Docker/WSL workloads. Not for general Windows support, hardware diagnostics, GPU/driver troubleshooting, antivirus/malware removal, Windows Update repair, networking, or app-specific performance problems unrelated to disk or memory pressure.

Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Windows desktop UI testing task. Not for web/browser testing (use Playwright), mobile testing, or non-Windows platforms.

Manage hooks and automation for coding agents (Claude Code, Codex CLI, OpenCode). Use when users want to add, list, remove, update, or validate hooks. Triggers on requests like "add a hook", "create a hook that...", "list my hooks", "remove the hook", "validate hooks", or any mention of automating agent behavior with shell commands or plugins.

Software engineering heuristics from Mark Seemann's book Code That Fits in Your Head (2021). Use when writing new code, reviewing code, refactoring, designing APIs, handling validation and invariants, writing unit tests, debugging defects, performing security review (STRIDE), or setting up a new code base. Covers decomposition (cyclomatic complexity, 80/24 rule, cohesion, fractal architecture), encapsulation (invariants, parse-don't-validate, Postel's law), outside-in TDD (walking skeleton, AAA, triangulation, devil's advocate), API design (affordance, poka-yoke, CQS), git/PR hygiene (50/72 commits, small commits, code review), feature flags, Strangler pattern, bisection debugging, logging with decorators, and STRIDE threat modelling. Not for language-specific syntax, framework tutorials, production incident response, or performance profiling.

Search, install, configure, update, and remove MCP servers across coding agents (Claude Code, Cursor, VS Code, Claude Desktop, Gemini CLI, Codex, Goose, Zed, and more). Supports multi-agent installation via npx add-mcp, the official MCP registry, and direct config editing.

Use this skill when the user asks to plan, design, scope, estimate, or implement a feature, bug fix, refactor, migration, integration, API change, UI change, or other project modification. Enforces a planning gate before editing code — investigate project context, analyze the task, surface ambiguities, contradictions, risks, dependencies, and blockers, ask focused questions, produce an evidence-based step-by-step plan, and implement only after explicit user approval. Not for trivial one-line edits, pure questions about the codebase, or changes the user has already reviewed and approved for direct implementation.

General-purpose web search powered by Exa — the search_web / web_search analog. Use for any open-ended lookup, fact-finding, or 'search the web for X' when no specialized skill fits. Semantic (meaning-based) search over the whole index; runs a local script against the Exa API, no MCP server required.

Foundation for the Exa skill collection — how to call Exa (search, contents, answer, similar) from a local script with just an EXA_API_KEY, how to write good semantic queries, and how to orchestrate subagents for deep research. Read this first; the use-case skills (company, people, papers, code, news, finance, personal sites, X) build on it.

Find code with Exa — API usage examples, error fixes, library docs, and GitHub repositories. Use when you need a working code snippet, to resolve an error, find an open-source implementation, or pull up official docs for a language/framework. Runs a local script against the Exa API; no MCP server required.

Research companies with Exa semantic search — find competitors, funding, headcount, news, and build company lists. Use for competitor analysis, market mapping, sourcing companies by category/stage/geo, or 'find companies like X'. Runs a local script against the Exa API; no MCP server required.

Find financial filings with Exa — SEC filings (10-K, 10-Q, S-1), earnings reports, and annual reports. Use to pull a company's financials, compare results across periods, or locate a specific filing. Runs a local script against the Exa API; no MCP server required.

Build prospect lists with Exa — find target companies matching an ICP, then their decision-makers, then enrich with signals. Use for outbound sales lists, account mapping, and B2B prospecting. Multi-pass orchestration over the Exa API; no MCP server required.

Find people with Exa semantic search — by role, company, and location, LinkedIn-weighted. Use to map a company's team, find experts/decision-makers, locate a specific person, or build people lists. Runs a local script against the Exa API; no MCP server required.

Find personal websites with Exa — blogs, portfolios, and homepages. Use to find a person's own writing (not press about them), discover practitioners who blog, or surface indie/portfolio sites. Runs a local script against the Exa API; no MCP server required.

Build, audit, replace, and install native macOS app icons from raster source artwork. Use when Codex needs to review an icon candidate against Apple macOS icon expectations, remove background halos with the standard macOS rounded-rectangle enclosure, preserve PNG alpha while resizing into .iconset/.icns files, update SwiftPM macOS app packaging scripts, compare installed/build/dist icon assets, or clear/restart local app icon installation state.

Engineer, debug, package, and harden native macOS menu-bar / background-daemon apps built with Swift 6, SwiftUI MenuBarExtra, and SwiftPM (no Xcode project), running as an LSUIElement agent. Focuses on the runtime-only bug classes that a green `swift build` and passing unit tests do NOT catch — actor-isolation SIGTRAP at GCD/NIO/C callback boundaries, MenuBarExtra observation staleness, SwiftNIO/MQTT reconnect ladders, SwiftPM-to-.app bundling with stable code signing and notarization, launchd LaunchAgents, Keychain main-thread ACL freezes, IOKit power assertions, and live diagnosis with sample/.ips/Console. Use when building, debugging, signing, packaging, or hardening a macOS menu-bar app or headless agent, or when a Swift macOS app builds clean but misbehaves only at runtime. Not for general iOS development, Xcode-project (xcodebuild) builds, pure Swift-language or SwiftUI-layout questions, or app-side business logic — use a general Swift/SwiftUI skill for those.

Design and verify an HMAC-SHA256 signed command envelope — nonce + TTL/expiry + replay cache + receiver-side allowlist — for a downlink control channel such as a cloud→Mac actuation path over MQTT or WebSocket. Use when designing or reviewing a coach→device command channel, the Night Landing Track C downlink, or any signed command path where the receiver must reject forged, replayed, expired, or out-of-allowlist commands. Covers the envelope schema, canonical serialization, CryptoKit HMAC sign/verify, the fail-closed verification order, replay-cache and key-domain-separation design, and the threat-model checklist. Not for transport TLS, user-auth tokens / JWT sessions, at-rest encryption, or the telemetry UPLINK path (which stays unidirectional and read-only).

Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Windows desktop UI testing task.

Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Windows desktop UI testing task. Not for web/browser testing (use Playwright), mobile testing, or non-Windows platforms.

Query external AI agents (Codex, Gemini, OpenCode, Claude Code headless) in parallel for independent second opinions, code review, bug investigation, and consensus on high-stakes decisions. Agents and models are configurable in config.json. Use for architecture choices, security review, or ambiguous problems where independent perspectives matter. Not for simple questions answerable from docs or the codebase — use web search or repo exploration instead.

Hands-on playbook for macOS disk cleanup, dev-machine optimization, and proactive health alerting. Use when the Mac is full or slow, when a kernel panic / watchdog timeout / vm-compressor-space-shortage / Jetsam event happened, when the user asks to free disk space, audit storage, set up disk/memory alerts, or restore the same monitoring on a new Mac. Built around Mole (`mo` CLI) for safety guards plus a custom LaunchAgent-based alerter for active warnings. Covers Apple Silicon laptops with heavy AI/Docker workloads.

Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic systems that need structured prompts.

First Principles Framework (FPF) — thinking amplifier. Use when user wants to think through a complex problem, architect a system, evaluate alternatives, decompose complexity, classify problems, define quality attributes, 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.

Semantic search, grep, and Q&A across codebases and documentation indexed in CodeAlive. Use when the user mentions "CodeAlive", asks to list or get data sources, list indexed repositories, search code or docs across remote repos, fetch artifact content, or trace call graphs across repositories.

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

Explore and analyze any repository (local path or remote GitHub/GitLab URL) by delegating to Claude Code CLI (`claude -p`) in non-interactive mode with read-only access. Use when the user asks to explore, analyze, investigate, or research a repository or codebase. Triggers on "explore repo", "analyze repo", "investigate repo", "research codebase", "what does this repo do", "how does this codebase work", "ask about repo", "codebase question", "explore repository", "what API does this project have", "analyze this GitHub repo", "explore https://github.com/...", or any request to understand a repository's structure, API, architecture, or implementation details. Works with both local paths and remote URLs (GitHub, GitLab, Bitbucket).

Orchestrate consultations with external AI agents (OpenAI Codex CLI and Google Gemini CLI) for code reviews, second opinions, investigations, and consensus building. Use when needing a second opinion on architecture or design decisions, requesting code review from another perspective, investigating bugs with fresh eyes, or building consensus on critical decisions by querying multiple agents. Not for simple questions answerable from docs or codebase — use web search or codebase exploration instead.