Development skills

Comprehensive Elixir/Phoenix code review with optional parallel agents

The English summary is being prepared. Showing the original description.

Reviews URLSession networking code for iOS/macOS. Covers async/await patterns, request building, error handling, caching, and background sessions. Use when reviewing code that uses URLSession, URLRequest, URLCache, or URLError, or any iOS networking path.

The English summary is being prepared. Showing the original description.

Reviews watchOS code for app lifecycle, complications (ClockKit/WidgetKit), WatchConnectivity, and performance constraints. Use when reviewing code with import WatchKit, WKExtension, WKApplicationDelegate, WCSession, or watchOS-specific patterns.

The English summary is being prepared. Showing the original description.

Reviews FastAPI code for routing patterns, dependency injection, validation, and async handlers. Use when reviewing FastAPI apps, checking APIRouter setup, Depends() usage, or response models.

The English summary is being prepared. Showing the original description.

Reviews iOS animation code for correctness, performance, accessibility, and Apple API best practices. Use when reviewing .swift files containing animation code — withAnimation, .animation(), PhaseAnimator, KeyframeAnimator, matchedGeometryEffect, navigationTransition, CABasicAnimation, CASpringAnimation, UIViewPropertyAnimator, UIDynamicAnimator, symbolEffect, scrollTransition, contentTransition, or custom Transition conformances.

The English summary is being prepared. Showing the original description.

Schema for tracking code review outcomes to enable feedback-driven skill improvement. Use when logging review results or analyzing review quality.

The English summary is being prepared. Showing the original description.

Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.

The English summary is being prepared. Showing the original description.

Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in state management, graph structure, and async patterns.

The English summary is being prepared. Showing the original description.

Mandatory verification steps for all code reviews to reduce false positives. Load this skill before reporting ANY code review findings.

The English summary is being prepared. Showing the original description.

Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.

The English summary is being prepared. Showing the original description.

Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.

The English summary is being prepared. Showing the original description.

Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.

The English summary is being prepared. Showing the original description.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

The English summary is being prepared. Showing the original description.

Cut a kolu release — tag master, promote the Unreleased changelog entry, publish a GitHub release. ONLY invoke when the user explicitly types `/release` or `$release`; never auto-select from a natural-language request.

The English summary is being prepared. Showing the original description.

Launch the kolu dev server on two RANDOM free ports so it never collides with the running production `kolu.service`, remember the ports for the rest of the session, and tear down only the dev instance. Load before running the app locally — for evidence capture, driving a live kolu with the chrome-devtools MCP, or any `just dev` you'd otherwise run by hand. Triggers on "run kolu locally", "launch the dev server", "boot kolu", "drive a live kolu", "start the app to screenshot it", or before pointing chrome-devtools at a local kolu.

The English summary is being prepared. Showing the original description.

Diagnose Kolu client-side performance issues (memory leaks, high GPU, slow interactions) using chrome-devtools MCP + the Debug → Diagnostic info dialog + heap-snapshot analyzers. Triggers on "memory leak", "GPU memory", "tab bloat", "why is kolu slow", "debug performance", "zombie canvas", "WebGL leak", or any

The English summary is being prepared. Showing the original description.

Use Pierre Computer Company's `@pierre/trees` (path-first file tree) and `@pierre/diffs` (shiki-based code/diff renderer) in Kolu. Pierre ships Preact/vanilla cores with optional React wrappers — Kolu consumes the vanilla classes and wraps them in thin SolidJS components. Trigger when: wiring up a file tree, rendering unified diffs or syntax-highlighted files, replacing `@git-diff-view`, or any mention of `@pierre/trees` / `@pierre/diffs` / "pierre library".

The English summary is being prepared. Showing the original description.

How a downstream app consumes the shared @kolu/surface stack (@kolu/surface · surface-app · surface-remote · surface-mcp) — declaring a typed reactive surface, serving it, consuming it (SolidJS hooks or a CLI), and mirroring a remote surface over ssh. Grounded in the real consumers: kolu, drishti, odu, and the TUIs. Load when wiring a surface server/client/mirror, or reaching for makeSession / a link / the `.use()` hooks. CHANGING the framework is gated separately — see "Changing the framework" below (a paired, CI-green drishti PR pinned to final kolu HEAD).

The English summary is being prepared. Showing the original description.

Turn a feature request into a minimal, file-level implementation plan before any code.

The English summary is being prepared. Showing the original description.

Maintain the slopus/happy open source project. Triage issues, manage the GitHub project board, draft closing comments, find duplicates, check if bugs are fixed on main, and engage with community contributors. NEVER posts comments or closes issues without showing exact text and getting approval first.

The English summary is being prepared. Showing the original description.

ADB-based RIPDPI device/emulator debugging: build/install/launch, logcat filtering, fixture port-forwarding, instrumented tests, crash/ANR triage. Use when debugging on a real device or emulator.

The English summary is being prepared. Showing the original description.

Playbook for capturing SOCKS5/VPN-tunnel traffic on Android devices and emulators with mitmproxy, tcpdump, or PCAPdroid. Use when debugging on-device network traffic or correlating Kotlin/Rust logs.

The English summary is being prepared. Showing the original description.

MTProto-over-WebSocket tunnel for Telegram: DC classification, obfuscated2 detection, TLS backend choice, and the relay loop. Use when touching Telegram DC routing, MTProto classification, or ripdpi-ws-tunnel.

The English summary is being prepared. Showing the original description.

Reference for Android VPN/proxy service lifecycle: runtime coordinators, status/telemetry flow, where to make changes. Use when touching service start/stop, handover, or coordinator code.

The English summary is being prepared. Showing the original description.