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.
- 352 skills across 64 domains — structured, executable procedures
- 72 agents — specialized Claude Code personas covering development, review, compliance, and more
- 17 teams — predefined multi-agent compositions for complex workflows
- 27 guides — human-readable workflow, infrastructure, and reference documentation
- Interactive visualization — force-graph explorer with 352 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) | Plugin install or .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.
Choose a path. Full per-OS runbook with prereqs, verification, and updating: Installation guide.
> "Follow skills/commit-changes/SKILL.md to stage and commit my changes"
git clone https://github.com/pjt222/agent-almanac.git ~/dev/agent-almanac
# One-time local marketplace setup
mkdir -p ~/.claude-marketplace/{plugins,.claude-plugin}
cat > ~/.claude-marketplace/.claude-plugin/marketplace.json << 'EOF'
{
"name": "local",
"owner": { "name": "self" },
"plugins": [{
"name": "agent-almanac",
"source": "./plugins/agent-almanac",
"category": "development"
}]
}
EOF
ln -s ~/dev/agent-almanac ~/.claude-marketplace/plugins/agent-almanac
claude plugin marketplace add ~/.claude-marketplace
claude plugin install agent-almanac@localAuto-discovers all 352 skills and 72 agents. Teams require activation via TeamCreate. Windows / macOS variants in the Installation guide.
npm install -g agent-almanac
agent-almanac detect # show frameworks in cwd
agent-almanac install commit-changesReaches 12+ frameworks: Claude Code, Cursor, Codex, Gemini, Aider, OpenCode, Windsurf, Vibe, Hermes, OpenClaw. See cli/README.md.
cd ~/dev/agent-almanac
npm install && npm test # repo integrity + README freshness
claude plugin list | grep agent-almanacIn a fresh Claude Code session, type /commit-changes — should resolve. Empty result → see Installation troubleshooting.
cd viz && npm install && bash build.sh && npm run dev
# Open http://localhost:5173 for the interactive force-graph explorerRequires R 4.5.x or Docker; per-OS R paths in the Installation guide. See viz/README.md for build internals.
agent-almanac/
.claude-plugin/ Plugin manifest for Claude Code plugin installation
skills/ 352 executable procedures across 64 domains
agents/ 72 specialist personas
teams/ 17 multi-agent compositions with 8 coordination patterns
guides/ 27 human-readable reference docs
viz/ Interactive force-graph explorer with R-generated icons
tests/ 30 test scenarios for validation
i18n/ Translations (10 locales: de, zh-CN, ja, es, caveman, caveman-lite, caveman-ultra, wenyan, wenyan-lite, wenyan-ultra)
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
- Team Assembly Prompt Patterns — How to phrase requests to Claude Code for multi-agent team work at every level of specificity
- 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
- Edge Computing Deployment — Install agent-almanac skills on edge LLMs (Gemma 4 via AI Edge Gallery) with distilled content, token budgets, and offline bundles
- Self-Continuation Loops Playbook — Choose among ScheduleWakeup, CronCreate loops, and loop.md; select sentinels; plan for the 7-day age-out
Infrastructure
- Installation — OS-aware install runbook covering plugin install, global CLI, prereqs, verification, and updating across Linux, macOS, Windows, WSL2, and Codespaces
- 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
- The Caveman Spellbook — Six grunt-level compression modes for agent-almanac content — a homage to JuliusBrussee/caveman, from lite filler-stripping to extreme classical Chinese abbreviation
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
- Agent Memory Hygiene — Three-layer model — weights, retrieval, behavior — for diagnosing what kind of forgetting a memory problem actually needs and applying the right tool
| Locale | Language | Skills | Agents | Teams | Guides | Total |
|---|---|---|---|---|---|---|
| de | Deutsch | 352/352 | 3/72 | 1/17 | 3/27 | 359/468 (76.7%) |
| zh-CN | 简体中文 | 352/352 | 3/72 | 1/17 | 3/27 | 359/468 (76.7%) |
| ja | 日本語 | 352/352 | 3/72 | 1/17 | 3/27 | 359/468 (76.7%) |
| es | Español | 352/352 | 3/72 | 1/17 | 3/27 | 359/468 (76.7%) |
| caveman-lite | Caveman Lite | 352/352 | 0/72 | 0/17 | 0/27 | 352/468 (75.2%) |
| caveman | Caveman | 352/352 | 0/72 | 0/17 | 0/27 | 352/468 (75.2%) |
| caveman-ultra | Caveman Ultra | 352/352 | 0/72 | 0/17 | 0/27 | 352/468 (75.2%) |
| wenyan-lite | 文言文輕 | 352/352 | 0/72 | 0/17 | 0/27 | 352/468 (75.2%) |
| wenyan | 文言文 | 352/352 | 0/72 | 0/17 | 0/27 | 352/468 (75.2%) |
| wenyan-ultra | 文言文極 | 352/352 | 0/72 | 0/17 | 0/27 | 352/468 (75.2%) |
See i18n/README.md for the translation contributor guide.
Agent-almanac is packaged as a Claude Code plugin at .claude-plugin/plugin.json. When installed, Claude Code auto-discovers all skills and agents:
| Component | Discovery | Count |
|---|---|---|
| Skills | skills/*/SKILL.md |
350 |
| Agents | agents/*.md |
72 |
| Teams | Bundled but not auto-discovered | 17 |
Teams are not a plugin-native content type — they require activation via TeamCreate (see Creating Agents and Teams).
For step-by-step plugin install (POSIX + Windows + macOS variants, prereqs, verification, troubleshooting), see the Installation 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.