oh-my-ai

Use when starting a new session on a codebase, resuming interrupted work from a previous session, after making an architectural or design decision, or before ending a session or creating a PR — to create, update, or hand off docs/context/ project context files.

Use when a tool, command, sandbox, permission, network, dependency, or approval operation fails or repeats the same infrastructure error — classify the failure, cap retries, choose one bounded fallback, and stop before recovery consumes excessive tokens or time.

Comprehensive guide for dependency injection (DI) in Golang. Covers why DI matters (testability, loose coupling, separation of concerns, lifecycle management), manual constructor injection, and DI library comparison (google/wire, uber-go/dig, uber-go/fx, samber/do). Use this skill when designing service architecture, setting up dependency injection, refactoring tightly coupled code, managing singletons or service factories, or when the user asks about inversion of control, service containers, or wiring dependencies in Go.

Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log aggregation 3rd-party tools. Apply when creating, wrapping, inspecting, or logging errors in Go code.

Provides gRPC usage guidelines, protobuf organization, and production-ready patterns for Golang microservices. Use when implementing, reviewing, or debugging gRPC servers/clients, writing proto files, setting up interceptors, handling gRPC errors with status codes, configuring TLS/mTLS, testing with bufconn, or working with streaming RPCs.

Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.

Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.

PostgreSQL best practices, query optimization, connection troubleshooting, and performance improvement. Load when working with Postgres databases.

Redis performance optimization and best practices. Use this skill when working with Redis data structures, Redis Query Engine (RQE), vector search with RedisVL, semantic caching with LangCache, or optimizing Redis performance.

Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.

Optional workflow skill for Jira/Confluence release operations. Use only when Jira fixVersion or release-report context is available and the user wants user-facing release notes, optionally with safe Confluence page updates.

Optional workflow skill for Slack-style daily reports. Use only when the user works with Slack daily reports and, optionally, Notion worklogs/Todo pages; it summarizes today's work by project with progress percentages.

Use when ending a session, switching AI tools, or creating a PR — to generate a structured handoff prompt that the next AI session can use as context. Covers branch state, completed work, do-not-touch constraints, verification results, and next actions. Does NOT capture raw logs or auto-summarize conversation.

Optional workflow skill for Notion-style worklogs, Todo roadmaps, and meeting notes. Use only when the user keeps worklogs in Notion or a similar workspace and wants verbose entries condensed for scanning.

Use after deciding to automate a recurring/manual task — to evaluate whether it's ripe, pick the right form (skill vs slash-command vs agent vs script), structure it, and manage its lifecycle. The detection/nudge trigger lives in CLAUDE.md; this skill is the post-confirmation structuring method.

Use when a user invokes /work-start or says they want to start, plan, or kick off a task — to classify the task, recover missing external context (tickets, docs, meeting notes, Slack excerpts, PRs), gather repo context, produce an intermediate checkpoint, and confirm the plan before any code edit, doc write, or external action.

Use when choosing how to find local files, documents, or repository content: prefer rg/find for exact code symbols, strings, regexes, package names, and config keys; consider optional Jikji CLI only as a document context finder in large repos where filename/keyword matching is insufficient.

Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and platform-specific Kubernetes work for EKS, GKE, AKS, OpenShift, GitOps controllers, or observability stacks.