A library of executable skills, specialist agents, and pre-built teams for 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.
- 337 skills across 60 domains — structured, executable procedures
- 68 agents — specialized Claude Code personas covering development, review, compliance, and more
- 15 teams — predefined multi-agent compositions for complex workflows
- 20 guides — human-readable workflow, infrastructure, and reference documentation
- Interactive visualization — force-graph explorer with 337 R-generated skill icons and 9 color themes
| Building Block | Location | Purpose |
|---|---|---|
| Skills | skills/<skill-name>/SKILL.md |
Executable procedures (how) |
| Agents | agents/<name>.md |
Specialized personas (who) |
| Teams | teams/<name>.md |
Multi-agent compositions (who works together) |
| Guides | guides/<name>.md |
Human-readable reference (context) |
Ask Claude Code to review your R package, and the r-package-review team activates 4 agents — each following specialized skills for code quality, architecture, security, and best practices — then synthesizes their findings into a single report.
Skills follow the Agent Skills open standard and work with any tool that reads markdown:
| Tool | Integration | Details |
|---|---|---|
| Claude Code | Full (skills, agents, teams) | Native discovery via .claude/ symlinks |
| Codex (OpenAI) | Skills | Symlink into .agents/skills/ |
| Cursor | Skills | Map to .cursor/rules/*.mdc files |
| Gemini CLI, Aider, etc. | Skills | Point context to any SKILL.md file |
Agents and teams use Claude Code's subagent architecture. For other tools, skills are the primary integration surface. See skills/README.md for setup instructions.
No setup needed — reference any skill by path in Claude Code:
> "Follow skills/commit-changes/SKILL.md to stage and commit my changes"
npm install -g agent-almanacBrowse campfires (teams), install skills and agents, and manage content across 12+ frameworks. See cli/README.md for full usage.
Prerequisites: Claude Code CLI installed, Node.js (for README generation and the visualization).
git clone https://github.com/pjt222/agent-almanac.git
cd agent-almanacThen in Claude Code:
> "Use the code-reviewer agent to review my latest changes"
> "Follow the commit-changes skill to stage and commit"
> "Activate the r-package-review team to review this package"
# From the repository root:
ln -s ../../skills/commit-changes .claude/skills/commit-changes
# Then invoke with /commit-changes in Claude CodeSee Symlink Architecture for details. All 328 skills are already symlinked in this repository.
cd viz && npm install && npm run dev
# Open http://localhost:5173 for the interactive force-graph explorerSee viz/README.md for full build instructions.
agent-almanac/
skills/ 328 executable procedures across 58 domains
agents/ 66 specialist personas
teams/ 15 multi-agent compositions with 8 coordination patterns
guides/ 19 human-readable reference docs
viz/ Interactive force-graph explorer with R-generated icons
tests/ 30 test scenarios for validation
i18n/ Translations (4 locales: de, zh-CN, ja, es)
cli/ Universal installer CLI (npm install -g agent-almanac)
scripts/ Build and CI automation
sessions/ Tending session archives
New here? Start with Understanding the System. See all guides for the full categorized list.
Workflow
- Understanding the System — Entry point: what skills, agents, and teams are, how they compose, and how to invoke them
- Creating Skills — Authoring, evolving, and reviewing skills following the agentskills.io standard
- Creating Agents and Teams — Designing agent personas, composing teams, and choosing coordination patterns
- Running a Code Review — Multi-agent code review using review teams for R packages and web projects
- Managing a Scrum Sprint — Running Scrum sprints with the scrum-team: planning, dailies, review, and retro
- Visualizing Workflows with putior — End-to-end putior workflow visualization from annotation to themed Mermaid diagrams
- Running Tending — AI meta-cognitive tending sessions with the tending team
- Running a Translation Campaign — End-to-end guide for translating all skills, agents, teams, and guides into supported locales using the translation-campaign team
- Unleash the Agents — Structured multi-agent consultation at three tiers for open-ended hypothesis generation
- Production Coordination Patterns — Real-world multi-agent orchestration patterns: barrier synchronization, silence budgets, health checks, degraded-wave policies, and cost-aware scheduling
- AgentSkills Alignment — Standards compliance audits using the agentskills-alignment team for format validation, spec drift detection, and registry integrity
Infrastructure
- Setting Up Your Environment — WSL2 setup, shell config, MCP server integration, and Claude Code configuration
- Symlink Architecture — How symlinks enable multi-project discovery of skills, agents, and teams through Claude Code
- R Package Development — Package structure, testing, CRAN submission, pkgdown deployment, and renv management
Reference
- Quick Reference — Command cheat sheet for agents, skills, teams, Git, R, and shell operations
- Agent Best Practices — Design principles, quality assurance, and maintenance guidelines for writing effective agents
- Agent Configuration Schema — YAML frontmatter field definitions, validation rules, and JSON Schema for agent files
Design
- Extracting Project Essence — Multi-perspective framework for extracting skills, agents, and teams from any codebase using the metal skill
- Epigenetics-Inspired Activation Control — Runtime activation profiles controlling which agents, skills, and teams are expressed, grounded in molecular epigenetics
- Understanding the Synoptic Mind — The adaptic concept — panoramic synthesis through simultaneous multi-domain awareness, theoretical foundations, and practical use
| Locale | Language | Skills | Agents | Teams | Guides | Total |
|---|---|---|---|---|---|---|
| de | Deutsch | 320/337 | 3/68 | 1/15 | 1/20 | 325/440 (73.9%) |
| zh-CN | 简体中文 | 320/337 | 3/68 | 1/15 | 1/20 | 325/440 (73.9%) |
| ja | 日本語 | 320/337 | 3/68 | 1/15 | 1/20 | 325/440 (73.9%) |
| es | Español | 320/337 | 3/68 | 1/15 | 1/20 | 325/440 (73.9%) |
See i18n/README.md for the translation contributor guide.
Contributions welcome! Each content type has its own guide:
- Skills — skills/README.md for format and consumption
- Agents — agents/README.md for template and best practices
- Teams — teams/README.md for coordination patterns
- Guides — guides/README.md for categories and template
Update the relevant _registry.yml when adding content, then run npm run update-readmes.
If Agent Almanac makes your AI tools more capable, consider sponsoring its development.
Reliable AI assistance requires structured knowledge — and maintaining that structure is work that the models themselves cannot do.
MIT License. See LICENSE for details.