Loading...
Loading...
Found 34 Skills
Live chat and chatbot for sales and support — widget setup, routing, chatbot flows, agent management, visitor tracking, chat-to-lead conversion, proactive messaging. Covers strategy and implementation across Brevo Conversations, Drift (Salesloft), Intercom, HubSpot, Crisp, LiveChat, Zendesk, Tidio, Freshdesk, and ZoomInfo Chat. Use when setting up live chat, building chatbot flows, optimizing chat-to-lead conversion, routing chats to agents, or choosing a live chat tool. Do NOT use for email sequences (use /sales-cadence), email marketing (use /sales-email-marketing), or meeting scheduling (use /sales-meeting-scheduler). For platform-specific help, use /sales-brevo or /sales-salesloft.
Transactional and triggered email delivery — order confirmations, password resets, welcome emails, receipts, shipping notifications, account alerts. Covers provider selection, template design, deliverability, API integration, SMTP relay, and monitoring across SendGrid, Postmark, Mailgun, Brevo, Braze, Iterable, Customer.io, Mailchimp/Mandrill, GetResponse (MAX only), and Amazon SES. Use when building transactional email flows, choosing a transactional email provider, debugging delivery issues for triggered emails, or setting up SMTP relay. Do NOT use for marketing email campaigns (use /sales-email-marketing), cold outbound sequences (use /sales-cadence), cross-platform deliverability strategy (use /sales-deliverability), or SendPulse-specific questions (use /sales-sendpulse). For platform-specific help, use /sales-braze, /sales-iterable, /sales-sendgrid, /sales-postmark, /sales-mailgun, /sales-brevo, /sales-customerio, /sales-mailchimp, /sales-getresponse, or /sales-sendpulse.
Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.
Shell scripting and terminal integration patterns for building tools that integrate with Zsh, Bash, and Fish. Covers completion systems (compdef/compadd, complete/compgen, fish complete), ZLE widgets, hooks (precmd/preexec/chpwd, PROMPT_COMMAND), readline, bindkey, parameter expansion, ZDOTDIR loading order, event systems, abbreviations, POSIX shell scripting, terminal control codes (ANSI/CSI escape sequences), tput, stty, signal handling, process management (job control, traps), and shell plugin distribution patterns. Use when building shell plugins, writing completion scripts, implementing terminal UI with escape sequences, managing dotfiles, creating installation scripts, handling signals and process management, or integrating native binaries with shell wrappers.
Designs and manage customer loyalty programs — points, tiers, rewards, referrals, VIP programs, retention mechanics. Covers strategy, structure, and implementation across Brevo Loyalty, Smile.io, LoyaltyLion, Yotpo, Stamp.me, and custom-built programs. Use when designing a loyalty program, choosing loyalty software, setting up points/tiers/rewards, optimizing member engagement, or measuring program ROI. Do NOT use for affiliate/referral programs with commission payouts (use /sales-affiliate-program), email marketing to loyalty members (use /sales-email-marketing), or checkout optimization (use /sales-checkout). For Brevo-specific help, use /sales-brevo.
Generate Chinese broadcast audio from text files via the MiniMax TTS API, which automatically handles common pronunciation errors such as polyphonic characters, English abbreviations, mixed model names, and number pronunciations. Triggered when the user says "Generate broadcast audio using MiniMax".
Run AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune training hyperparameters for any TAO network. Platform-agnostic — runs on any SDK (Lepton, Brev, SLURM, Kubernetes, Docker).
Optimize tool descriptions in ToolUniverse JSON configs for clarity and usability. Reviews descriptions for missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance. Use when reviewing tool descriptions, improving API documentation, or when user asks to check if tools are easy to understand.
Checks that test method and function names read as complete sentences describing behavior. Flags cryptic names like test1, testFoo, or abbreviated names that do not describe what is being tested. Designed to run on every PR. Do NOT use for test coverage, test structure, or non-test code.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.