$ show coreyhaines31/marketingskills
This repository is a comprehensive, structured library of over 50 marketing 'skills' designed for AI coding agents (Claude Code, Codex, Cursor, etc.). Each skill is a self-contained directory with a SKILL.md (frontmatter + workflow), a references/ folder with deep-dive documentation and benchmarks, and evals/evals.json for behavioral testing. The skills cover the full marketing lifecycle: copywriting, SEO, paid ads (Meta, Google, LinkedIn), email, social, CRO, pricing, offers, attribution, market research, and more. Additionally, the repository includes 40+ zero-dependency Node.js CLI scripts that act as API clients for marketing tools like Ahrefs, Semrush, GA4, Meta Ads, Mailchimp, etc., each following a consistent pattern with dry-run support and environment variable authentication. Several integration guides and a central tool registry (REGISTRY.md) complete the ecosystem. While primarily a content library, the CLI scripts and validation/sync tooling demonstrate strong engineering patterns. The skills are designed to be consumed by AI agents to execute complex, multi-step marketing tasks, with cross-skill references and a shared context document (product-marketing.md) enabling orchestration.
The LLM identified 3 files worth highlighting for reuse:
A standalone Node.js CLI script for interacting with the Ahrefs API. It requires no npm dependencies, uses only built-in modules (fs, https, etc.), and follows a clean, reusable pattern: parseArgs for command-line parsing, an api() function that supports dry-run mode, environment variable authentication (AHREFS_API_KEY, AHREFS_EMAIL), command/subcommand routing via switch, and strict JSON output. This pattern is replicated across all 40+ CLI scripts in tools/clis/. A developer could extract this file into a new project and use it as a template for other API clients with minimal modification. It demonstrates disciplined error handling (main().catch()), configurable output (JSON, compact), and idempotent operations.
A Node.js script that synchronizes the skills directory with both the marketplace.json manifest and the README.md table. It scans the skills/ folder, validates required files (SKILL.md, evals/evals.json, references/), extracts frontmatter metadata (name, description, version), and updates the marketplace registry and README in a deterministic order. It also handles version bumping of plugin.json. This script is reusable for any project that maintains a directory of structured skill definitions and a central registry; it encapsulates the logic of keeping documentation and machine-readable metadata in sync. The script uses a functional style, no external dependencies, and is invoked via GitHub Actions.
A shell script that performs comprehensive validation of every skill directory against the Agent Skills specification. It checks: directory name matches frontmatter name (lowercase, hyphens), description length (1-1024 chars) and presence of trigger phrases, SKILL.md line count (<500), required files (evals/evals.json, references/), and YAML frontmatter syntax. The script is idempotent, uses only standard Unix tools (awk, grep, yq/optional), and can be run locally or in CI. It demonstrates a disciplined approach to content quality control and can be adapted to validate any directory of structured markdown files with frontmatter metadata.