Optimizes SQL queries, designs database schemas, and troubleshoots performance issues. Use when a user asks why their query is slow, needs help writing complex joins or aggregations, mentions database performance issues, or wants to design or migrate a schema. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis, covering index creation, recursive queries, EXPLAIN/ANALYZE interpretation, before/after query benchmarking, or migrating queries between database dialects (PostgreSQL, MySQL, SQL Server, Oracle).

Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies, NetworkPolicies, storage configuration, performance optimization, GitOps pipelines, and multi-cluster management.

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.

Audit a workspace for recurring friction, pick the highest-leverage one, and build the automation that removes it. Use when the user asks "what should I automate", "what's wasting my time", "find the friction in my workflow", wants a self-improvement pass over their own tooling, or runs this on a recurring loop.

Diagnose and resolve RevenueCat integration issues — inspects dashboard configuration through the RevenueCat MCP, walks the SDK debug logs, and covers code-side gotchas. Use when the user says offerings are empty, products not loading, entitlement not active after purchase, paywall won't load, transactions not appearing, customer info shows no entitlements, sandbox purchase not working, or RevenueCat is broken on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.

End-to-end RevenueCat integration — sets up the dashboard side via the RevenueCat MCP or the `rc` CLI (project, app, public API key) and installs/configures the Purchases SDK in the app. Use when the user asks to add RevenueCat, integrate Purchases, install the RevenueCat SDK, set up a RevenueCat API key, configure Purchases on launch, or set up a brand new RevenueCat integration on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.

Use when working with the Resend email API — sending transactional emails (single or batch), receiving inbound emails via webhooks, managing email templates, tracking delivery events, managing domains, contacts, broadcasts, webhooks, API keys, automations, events, viewing API request logs, or setting up the Resend SDK. Always use this skill when the user mentions Resend, even for simple tasks like "send an email with Resend" — the skill contains critical gotchas (idempotency keys, webhook verification, template variable syntax) that prevent common production issues.

One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push --force, gh repo delete) enforced as a PreToolUse/pre-exec guard across every AI coding agent on the machine — Cursor, Claude Code, Codex, OpenCode, Pi, Hermes, Grok, Droid, Devin. Use when adding or tuning blocked-command patterns, wiring the guard into a new agent or a new machine, debugging why a command was (or was not) blocked, or when the user mentions command guard, guardrails, dangerous command hook, or PreToolUse safety.

Control Philips Hue lights and scenes via the OpenHue CLI.

Vitest unit and integration testing patterns, commands, mocking (vi.mock), and coverage. Use when writing .test.ts files, configuring the test runner, or adding coverage thresholds.

Implement Apollo.io reference architecture. Use when designing Apollo integrations, establishing patterns, or building production-grade sales intelligence systems. Trigger with phrases like "apollo architecture", "apollo system design", "apollo integration patterns", "apollo best practices architecture".

Execute use when provisioning Vertex AI infrastructure with Terraform. Trigger with phrases like "vertex ai terraform", "deploy gemini terraform", "model garden infrastructure", "vertex ai endpoints terraform", or "vector search terraform". Provisions Model Garden models, Gemini endpoints, vector search indices, ML pipelines, and production AI services with encryption and auto-scaling.

Validate use when validating GitHub Actions workflows for Google Cloud and Vertex AI deployments. Trigger with phrases like "validate github actions", "setup workload identity federation", "github actions security", "deploy agent with ci/cd", or "automate vertex ai deployment". Enforces Workload Identity Federation (WIF), validates OIDC permissions, ensures least privilege IAM, and implements security best practices.

Execute use when provisioning Vertex AI ADK infrastructure with Terraform. Trigger with phrases like "deploy ADK terraform", "agent engine infrastructure", "provision ADK agent", "vertex AI agent terraform", or "code execution sandbox terraform". Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.

Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners. Use when setting up or migrating GitHub Actions workflows to use Depot runners, choosing runner sizes (CPU/RAM), configuring runs-on labels, setting up ARM or Windows or macOS runners, troubleshooting GitHub Actions runner issues, configuring egress filtering, using Depot Cache with GitHub Actions, or running Dagger/Dependabot on Depot runners. Also use when the user mentions depot-ubuntu, depot-windows, depot-macos runner labels, or asks about faster/cheaper GitHub Actions runners.

Diagnose interface errors, drops, CRCs, duplex mismatches, flapping, speed negotiation issues, and counter trends on routers, switches, and Linux hosts. Use when an interface shows errors, drops, CRCs, flapping, or a duplex or speed mismatch.

Deploys static HTML to a public URL instantly with no authentication required. Use when asked to "host this", "deploy this site", "get a public link", "share this HTML", "quick deploy", "publish this page", or any request to make an HTML file publicly accessible via URL. Supports self-contained HTML files with inline CSS/JS.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Control Philips Hue lights and scenes via the OpenHue CLI.