/code-review |
Review code for bugs, security, and quality |
/debug-error |
Diagnose errors and stack traces |
/generate-tests |
Generate unit tests (Arrange/Act/Assert) |
/refactor |
Clean Code, SOLID, DRY refactoring |
/explain-code |
Explain code at beginner → expert depth |
/git-commit |
Generate Conventional Commit messages |
/write-docs |
JSDoc, TSDoc, inline comments |
/prompt-engineering |
Design and improve LLM prompts |
/llm-cost-optimizer |
Analyze and reduce LLM inference costs |
/agent-designer |
Design AI agent architectures |
/security-guidance |
OWASP Top 10 security review |
/a11y-audit |
WCAG 2.2 accessibility audit |
/prompt-injection |
Detect and harden against prompt injection |
/benchmark-analyzer |
Interpret AI model benchmarks |
/model-eval |
Design LLM evaluation frameworks |
/data-quality-auditor |
Audit data pipelines for quality |
/agenthub |
Multi-agent collaboration |
/autoresearch-agent |
Autonomous experiment loops |
/chaos-engineering |
Chaos experiments and failure injection |
/docker-development |
Docker containerization best practices |
/terraform-patterns |
Infrastructure-as-code with Terraform |
/kubernetes-operator |
Build Kubernetes operators |
/slo-architect |
Define SLOs, SLIs, and error budgets |
/observability-designer |
Logs, metrics, traces design |
/feature-flags-architect |
Feature flag rollout strategies |
/mcp-server-builder |
Build MCP servers |
/rag-architect |
Design RAG pipelines |
/performance-profiler |
Profile and optimize performance |
/database-designer |
Relational and NoSQL schema design |
/api-design-reviewer |
REST/GraphQL API quality review |
/ci-cd-pipeline-builder |
GitHub Actions / GitLab CI pipelines |
/tdd-guide |
Test-driven development coaching |
/handoff |
Generate team handoff documents |
/write-a-skill |
Scaffold a new Runic skill |
