Loading...
Loading...
Found 534 Skills
Use the local `5dive` CLI on a 5dive runtime VM to spawn, inspect, send to, and tear down sibling agents. Trigger this skill whenever the user asks for a worker, sub-agent, side task, parallel run, "another agent", "fan out", "delegate", or anything that needs more than one Claude/Codex/Gemini process running at once on the host. Also trigger when the user asks to inspect, restart, or pair an existing agent, when they mention `/var/lib/5dive/`, or when they need a machine-readable health check (`5dive doctor --json`). Always prefer `5dive` over running coding CLIs by hand — it is the only sanctioned way to keep agents under systemd.
Use when a codebase, product, workflow, runtime, or organization needs purpose-first whole-machine stewardship: understand what the whole system is trying to produce, then improve the machinery, tooling, feedback loops, operability, and developer flow that let it produce that output.
Code quality orchestrator enforcing TRUST 5 validation, proactive code analysis, linting standards, and automated best practices. Use when performing code review, quality gate checks, lint configuration, TRUST 5 compliance validation, or establishing coding standards. Do NOT use for writing tests (use moai-workflow-testing instead) or debugging runtime errors (use expert-debug agent instead).
Comprehensive testing and development workflow specialist combining DDD testing, characterization tests, performance profiling, code review, and quality assurance. Use when writing tests, measuring coverage, creating characterization tests, performing TDD, running CI/CD quality checks, or reviewing pull requests. Do NOT use for debugging runtime errors (use expert-debug agent instead) or code refactoring (use moai-workflow-ddd instead).
Use when building or reviewing service, job, or CLI runtime behavior in Python — designing startup validation, shutdown sequences, observability, and structured logging. Also use when startup crashes from late config, shutdown leaves orphaned processes, terminal states are implicit, or logs lack structure.
Calculates total power consumption and battery life for Arduino/ESP32/RP2040 projects. Use when user asks about battery life, power requirements, current draw, or needs to estimate runtime. Includes sleep mode analysis, power optimization tips, and battery sizing recommendations. Run scripts/calculate_power.py for accurate calculations.
Reverse engineer Single Page Applications built with React + Vite + Workbox — analyze SPA internals via Chrome DevTools Protocol (CDP), write browser extensions, intercept service workers, and extract runtime state for SDK integration.
Run post-deployment smoke checks with Makefile targets (`remote-status`, `remote-logs`) plus optional health URL checks. Use after deployment to verify runtime state before final acceptance.
Best practices for developing, deploying, and debugging Supabase Edge Functions (Deno runtime). Use when working with Edge Functions for tasks like ingest pipelines, webhooks, scheduled jobs, or database triggers. Covers authentication patterns (service role vs anon key), error debugging, database integration, and common pitfalls.
Invoked when user wants to implement specific state modules in TypeScript for Bun runtime environment in GraphiCode-managed projects. Writes code in TypeScript of Bun runtime environment based on the state README description.
Guides the agent through an Apple App Store preflight review for Capacitor apps before submission or after rejection. Covers guideline checklist selection, App Store metadata review, Capacitor and iOS project inspection, privacy manifests, Sign in with Apple, entitlements, and common rejection patterns. Do not use for Google Play review, generic store publishing only, or non-Apple mobile runtimes.
AnyCap CLI -- capability runtime for AI agents. One CLI for image generation, image read, video analysis, audio analysis, music composition, text-to-speech, web search, web crawling, file download, static site hosting, and cloud file storage. Use when the agent needs to generate images, analyze images, video, or audio, produce audio/music, search or crawl the web, download remote files, deploy static sites, or store and share files. Also use when the agent needs to authenticate with AnyCap (login, API key, credentials), or when encountering errors from AnyCap to submit feedback via 'anycap feedback'. Trigger on mentions of AnyCap, multimodal capabilities, AI-generated media, page hosting, or drive storage.