AI Skills

Marketing Skills

49 marketing skills for AI agents covering SEO, copywriting, cold email

x402

Set up Browser Use Cloud payments with x402

browser-use

Fast, persistent browser automation

cloud

Documentation reference for using Browser Use Cloud

open-source

Documentation reference for writing Python code

qa

QA-test a website or web app and return a 1-5 quality score

remote-browser

Controls an isolated Browser Use Cloud browser from a sandboxed machine

azure-cloud-migrate

Assess and migrate cloud workloads from AWS, GCP

google-agents-cli-adk-code

Quick reference for ADK Python patterns: agents, tools, callbacks

google-agents-cli-deploy

Deploy ADK agents to Agent Runtime, Cloud Run, or GKE

google-agents-cli-eval

Evaluate ADK agents with metrics, evalsets, and the iterative eval-fix loop

google-agents-cli-workflow

Complete workflow for scaffolding, building, evaluating

google-agents-cli-scaffold

Project scaffolding, deployment configuration

google-agents-cli-observability

Set up tracing, logging, and monitoring

cavecrew

Delegate code tasks to compressed subagents

caveman-commit

Terse, conventional commit messages that prioritize reasoning over description

caveman-compress

Compress natural language memory files into caveman-speak to reduce input tokens

caveman-discover

Find and label every LLM workflow in the repository

caveman-evidence-review

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces

caveman-explore

Read-only repository explorer for cold-start orientation

caveman-help

Quick-reference card for caveman modes, skills, and commands

caveman-learn

Act on a Caveman learn report

caveman-manage

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution

caveman-optimize

Turn a Caveman optimization observation into an operator-chosen candidate

caveman-review

Ultra-compressed code review comments: location, problem, fix on one line each

caveman-setup

Wire a repository through the Caveman Cloud gateway

caveman-stats

Real token usage and estimated savings metrics from your Claude Code session log

compress

Compress natural language memory files into caveman-speak to reduce input tokens

investigate-first

Diagnose ambiguous failures before editing

lean-build

Build feature work with high overbuilding risk

megacave

Caveman in Classical Chinese: 文言文 register, far fewer characters

migration

Implement reversible compatibility-safe transitions

safe-refactor

Restructure code while preserving behavior

surgical-patch

Fix bugs and small behavior changes at the narrowest responsible layer

ultracave

Caveman at maximum compression: fragments, one word

verify-and-stop

Prove existing work meets acceptance conditions without expanding scope

product-launch-video

Turn a product or marketing URL, pasted script

vercel-composition-patterns

React composition patterns that scale

vitest

Vitest API and config reference (Jest-compatible)

lark-doc

Create, read, edit, and manage Lark documents

lark-base

Comprehensive Lark Base operations via CLI

lark-shared

Lark CLI configuration, authentication

lark-im

Send and receive messages, manage group chats, and handle files in Lark IM

lark-drive

Manage files, folders, and documents in Lark Drive

lark-sheets

Create, manage, and manipulate Lark spreadsheets

lark-wiki

Manage Lark Wiki spaces, members, nodes, and document organization hierarchies

faceless-explainer

Turn arbitrary text

lark-whiteboard

Query, edit, and export Lark whiteboards

lark-task

Complete task lifecycle management for Feishu, including creation, assignment

lark-mail

Compose, send, reply to, forward, and manage Lark emails