Complete multi-agent systems toolkit: LangGraph workflows, agent orchestration patterns, supervisor hierarchies, human-in-the-loop, A2A protocols, memory systems, and production deployment.
Implement checkpointing for agent recovery, debugging, and replay. Use this skill when building recoverable agents, implementing replay, debugging agent failures, or creating resumable workflows. Activate when: agent checkpoint, agent recovery, resume agent, agent restart, workflow replay, agent debugging, failure recovery, state snapshot.
Implement persistent agent state that survives failures and restarts. Use this skill when building stateful agents, implementing checkpointing, persisting agent memory across sessions, or recovering from failures. Activate when: durable state, agent persistence, checkpointing, agent recovery, stateful agents, state persistence, cross-session memory, agent restart.
Build agent workflows with LangGraph 1.0 state machines and graph patterns. Use this skill when creating agent graphs, implementing state machines, building multi-step agent workflows, or using LangGraph. Activate when: LangGraph, agent graph, state graph, agent workflow, graph nodes, conditional edges, agent state machine, ReAct agent.
Implement Agent-to-Agent (A2A) communication for cross-framework interoperability. Use this skill when building multi-agent communication, implementing agent protocols, connecting agents across frameworks, or standardizing agent interfaces. Activate when: agent to agent, A2A, agent communication, agent protocol, cross-framework agents, agent interoperability, MCP, agent discovery.
Use this skill when managing AI agent costs. Activate when the user needs to control token usage, implement cost limits for agents, optimize LLM spending, track agent costs, or prevent runaway API bills in agent systems.
Requires secrets
Needs API keys or credentials to function
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
67 professional skills + 7 full-featured plugins for AI coding agents — organized by audience so you can find exactly what you need.
Works with Claude Code, Claude Cowork, Cursor, Codex, Windsurf, and 35+ other AI agents.
# Cross-platform skills (works with any AI agent)
npx skills add latestaiagents/agent-skills --all
# Claude Code / Cowork plugins (with MCP integrations)
/plugin marketplace add latestaiagents/agent-skills
/plugin install devops-sre@latestaiagents-agent-skills
Works with Claude Code, Cursor, Codex, Windsurf, Cline, Aider, and 35+ other AI agents.
npx skills add latestaiagents/agent-skills --all
Full plugins with MCP tool integrations and slash commands. Works with Claude Code CLI and Claude Cowork desktop app.
# Step 1: Add our marketplace
/plugin marketplace add latestaiagents/agent-skills
# Step 2: Install plugins you need
/plugin install devops-sre@latestaiagents-agent-skills
/plugin install qa-testing@latestaiagents-agent-skills
/plugin install hr-people-ops@latestaiagents-agent-skills
| You Are | Skills CLI | Claude Plugin |
|---|---|---|
| Everyone | npx skills add latestaiagents/agent-skills/skills/safety --all | /plugin install safety@latestaiagents-agent-skills |
| Developer | npx skills add latestaiagents/agent-skills/skills/developer --all | /plugin install developer-toolkit@latestaiagents-agent-skills |
| DevOps/SRE | npx skills add latestaiagents/agent-skills/skills/mlops --all | /plugin install devops-sre@latestaiagents-agent-skills |
| RAG Engineer | npx skills add latestaiagents/agent-skills/skills/rag-architect --all | /plugin install rag-plugin@latestaiagents-agent-skills |
| Security Engineer | npx skills add latestaiagents/agent-skills/skills/security --all | /plugin install security-guardian@latestaiagents-agent-skills |
| QA/Testing | — | /plugin install qa-testing@latestaiagents-agent-skills |
| HR/People Ops | — | /plugin install hr-people-ops@latestaiagents-agent-skills |
Skills are instructions that teach AI agents how to handle specific tasks. After installation, your AI assistant automatically knows:
No special commands needed — skills activate automatically based on what you're doing.
Safety skills that prevent accidental data loss. Recommended for all users.
npx skills add latestaiagents/agent-skills/skills/safety --all
| Skill | What It Does |
|---|---|
destructive-operation-guard | Core safety protocols for all destructive operations |
migration-safety | Safe database migrations with backup requirements |
database-safety | Prevent accidental DELETE, DROP, TRUNCATE |
file-operation-safety | Protection against rm -rf and bulk deletions |
git-safety | Guard against force push, reset --hard, history loss |
Git workflows, code intelligence, and debugging tools — 19 skills total.
npx skills add latestaiagents/agent-skills/skills/developer --all
| Skill | What It Does |
|---|---|
merge-conflict-surgeon | Step-by-step conflict resolution with context analysis |
commit-message-crafter | Conventional commits that tell a story |
branch-strategy-advisor | GitFlow vs trunk-based — choose what fits |
git-history-detective | Find exactly when and where bugs were introduced |
rebase-safely | Interactive rebase without losing work |
git-undo-wizard | Recover from reset, rebase, and force push disasters |
| Skill | What It Does |
|---|---|
codebase-context-builder | Create CLAUDE.md and optimal context for AI |
ai-code-reviewer | Systematic review of AI-generated code |
refactor-with-ai | Safe, incremental refactoring workflows |
test-generation-patterns | AI-driven test creation that actually works |
debug-with-ai | Structured debugging: hypothesize → verify → fix |
doc-sync-automation | Keep docs updated when code changes |
code-explanation-generator | Clear explanations for complex code |
npx claudepluginhub latestaiagents/agent-skills --plugin agent-plugin39 professional skills + 10 slash commands for AI coding agents — Git workflows, debugging, multi-agent architecture, LLMOps, and safety guardrails.
Complete RAG (Retrieval-Augmented Generation) toolkit: chunking strategies, hybrid retrieval, GraphRAG, Agentic RAG, Corrective RAG, evaluation, and production deployment patterns.
Complete application security toolkit: OWASP Top 10 protection, secure code review, vulnerability detection, secrets scanning, and security best practices for modern applications.
Complete HR and People Operations toolkit: job descriptions, recruiting, performance reviews, onboarding, policy management, and employee engagement for modern workplaces.
Complete DevOps/SRE toolkit: incident response, observability, reliability engineering, on-call management, and automation. The most comprehensive open-source DevOps plugin available.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.
Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.
Multi-agent orchestrator — supervisor loop that launches agents to implement plans