Agent skills

Use when developing hooks, visuals, and copy variations for paid campaigns

Craft references for writing fiction well: prose, scenes, style, voice, and genre/page-level technique.

Use when understanding and fixing common Credo check issues for Elixir code quality and consistency.

Use when configuring Credo static analysis for Elixir projects requiring customized code quality rules and settings.

Automate version bumping, changelog generation, and release tagging from specs.

Multi-agent orchestration framework for autonomous AI collaboration.

For criminal trials, daily file and session plan: outlines legal norms, burden of proof, and counterarguments; result: test product with…

Generate a criterion-referenced rubric with descriptive performance levels for a task or objective.

Single-pass 3-agent critique for ANY work product — plans, code, designs, architecture.

Expert review across 5 dimensions.

Audit CRM hygiene; never make unreviewed bulk changes.

Keeps HubSpot current without the owner opening it: creates and updates contacts and deals from email and calendar context, logs notes and…

Coordinates complex tasks across multiple AI agent platforms with structured handoffs and attribution tracking.

Ensure AI configuration works across Claude Code, Cursor, Copilot, Windsurf, and Codex.

Review a feature across frontend, API, service, database, security, observability, testing, and deployment boundaries.

This skill should be used when the user asks about "transfer opportunities", "balance inventory", "which store needs what", "inter-store…

Orchestrates bidirectional peer reviews and plan validation between Claude Code and OpenAI Codex using isolated sandboxes.

Standardizes multi-OS development by providing automated platform detection and unified task execution across Windows, Linux, and macOS.

Ensure cross-platform compatibility across macOS (Intel/ARM), Ubuntu, and Fedora for this dotfiles repository.