Agent Almanac

Agent Almanac

[](https://www.npmjs.com/package/agent-almanac) [](https://github.com/pjt222/agent-almanac/actions/workflows/validate-skills.yml) [](https://github.com/pjt222/agent-almanac/actions/workflows/update-readmes.yml) [](LICENSE) [](https://github.com/sponsors/pjt222)

A library of executable skills, specialist agents, and pre-built teams for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and compatible AI tools. Define repeatable engineering procedures once and have AI agents execute them with built-in validation and error recovery. Compose specialists into review teams that catch issues a single reviewer would miss. Built on the [Agent Skills open standard](https://agentskills.io).

At a Glance

undefined

How It Works

Building Block	Location	Purpose
Skills	skills//SKILL.md	Executable procedures (how)
Agents	agents/.md	Specialized personas (who)
Teams	teams/.md	Multi-agent compositions (who works together)
Guides	guides/.md	Human-readable reference (context)

Ask Claude Code to review your R package, and the [r-package-review](teams/r-package-review.md) team activates 4 agents — each following specialized skills for code quality, architecture, security, and best practices — then synthesizes their findings into a single report.

Works with

...