Safety (Essential for Everyone)
> Safety skills that prevent accidental data loss. Recommended for all users.
```bash
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 |
---
Developer (For Software Developers)
> Git workflows, code intelligence, and debugging tools β 19 skills total.
```bash
npx skills add latestaiagents/agent-skills/skills/developer --all
```
#### Git Mastery (6 skills)
| 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 β 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 |
#### Code Intelligence (7 skills)
| 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 β verify β fix |
| doc-sync-automation | Keep docs updated when code changes |
| code-explanation-generator | Clear explanations for complex code |
#### Debug Detective (6 skills)
| Skill | What It Does |
|-------|--------------|
| error-pattern-analyzer | Group errors by root cause, find patterns |
| log-forensics | Extract insights from log files |
| stack-trace-decoder | Parse and explain complex stack traces |
| reproduction-builder | Create minimal reproduction cases |
| performance-profiler | Identify bottlenecks systematically |
| dependency-conflict-resolver | Untangle version conflicts |
---
MLOps (For Architects & Platform Engineers)
> Multi-agent systems, LLMOps, and production AI patterns β 20 skills total.
```bash
npx skills add latestaiagents/agent-skills/skills/mlops --all
```
#### Agent Architect (13 skills)
| Skill | What It Does |
|-------|--------------|
| agent-supervisor-pattern | Hub-and-spoke orchestration with reasoning transparency |
| agent-mesh-architecture | Peer-to-peer resilient agent networks |
| agent-handoff-protocols | Clean task delegation between agents |
| agent-memory-systems | Working, short-term, and long-term memory patterns |
| agent-tool-routing | Dynamic tool selection and MCP integration |
| agent-error-recovery | Circuit breakers, retry policies, graceful degradation |
| agent-cost-budgeting | Token allocation across agent swarms |
| agent-testing-harness | Unit and integration testing for agents |
| langgraph-workflows | LangGraph 1.0 state machines and graph patterns |
| durable-state-patterns | Persistent agent state across failures/restarts |
| human-in-loop-agents | Approval workflows and agent supervision |
| agent-checkpointing | Recovery, replay, and debugging patterns |
| a2a-protocols | Agent-to-Agent communication and MCP integration |
#### LLMOps Guardian (7 skills)
| Skill | What It Does |
|-------|--------------|
| token-cost-analyzer | Audit usage with 2026 pricing (Claude, GPT-4, etc.) |
| prompt-caching-patterns | Reduce costs by 73%+ with semantic caching |
| model-routing-strategy | Route to cheaper models when appropriate |
| llm-rate-limiting | Token bucket, exponential backoff, circuit breakers |
| ai-audit-logging | EU AI Act compliant audit trails |
| prompt-injection-guard | Input validation, canary tokens, output filtering |
| llm-fallback-chains | Multi-provider failover strategies |
---
RAG Architect (For AI/ML Engineers)
> Build production-ready RAG systems with 2026 best practices β 7 skills total.
```bash
npx skills add latestaiagents/agent-skills/skills/rag-architect --all
```
| Skill | What It Does |
|-------|--------------|
| hybrid-retrieval | Vector + keyword search with RRF fusion and reranking |
| chunking-strategies | Optimal chunking: semantic, parent-child, late chunking |
| graphrag-patterns | Knowledge graph + RAG for multi-hop reasoning |
| agentic-rag | Agent-driven retrieval with planning and reflection |
| corrective-rag | Self-healing RAG with document grading and fallbacks |
| rag-evaluation | RAGAS metrics, testing, and benchmarking |
| production-rag-checklist | End-to-end production deployment guide |
---
Security (For Security Engineers & All Developers)
> Comprehensive security skills including OWASP Top 10 and common securit
|