codex-claude-plugins

Use when the user wants coordinated multi-agent planning, delegation, or role-based engineering guidance.

Spawn and coordinate team-agents and orchestration patterns for parallel execution. Use for complex multi-component work.

Add and verify lightweight macOS runtime telemetry. Use when wiring Logger events or inspecting logs for windows, sidebars, menus, and actions.

Triage macOS tests across Xcode and SwiftPM. Use when narrowing failures, explaining assertions or crashes, or separating setup from regressions.

Bridge macOS SwiftUI into AppKit narrowly. Use when implementing representables, reaching NSWindow or panels, handling menus, or using the responder chain.

Knowledge base about Duyet Le (@duyet) and duyetbot behavioral patterns. Owner profile, knowledge sources, and execution transparency.

Use when the user wants Duyetbot-style pragmatic engineering help, orchestration, learning, writing, or transparent task execution.

Core engineering principles for sustainable, maintainable code. No shortcuts, no hacks. Quality gates before completion.

Use when the user asks to fix issues, tests, CI failures, or create/update/push a fix branch.

Show your thinking and execution chain with phase/thinking markers and debug traces. Use when the user wants visible step-by-step reasoning and traceable decisions.

Autonomous code review and fix skill for the agent-loop plugin. Reviews PRs, applies fixes from AI review bots (CodeRabbit, Sourcery, Gemini), validates changes, and lands them. Designed for unattended overnight operation.

Browser automation and computer-use skill for the agent-loop plugin. Takes screenshots, validates UI behavior, fills forms, clicks elements, and performs live web proof. Uses existing Chrome session via DevTools MCP.

Core orchestrator for the agent-loop plugin. Runs a continuous maintenance loop that wakes every N minutes, scans repo queues, dispatches work to parallel agent threads, tracks progress, and reports results. Designed for overnight and day-long autonomous repo upkeep.

GitHub project triage for the agent-loop plugin. Scans open issues, PRs, CI queues, and blockers. Classifies items by fit, risk, proof, and autonomy. Adapted from github-project-triage for autonomous loop integration.

Wire AnyRouter into a project, migrate from Anthropic / OpenAI / OpenRouter, and call its MCP server. Use when the user mentions AnyRouter, asks to add a unified LLM gateway, wants to swap providers without code churn, migrates an existing OpenAI/Anthropic/OpenRouter integration, sets up Claude Code / Codex / Cursor against a custom base URL, or needs help with model ids like `provider/model`, app attribution headers (`X-AnyRouter-*`), provider preferences, streaming, BYOK, or the AnyRouter MCP server at `https://anyrouter.dev/api/v1/mcp`.

Apple Intelligence participation layer. Wire an app's actions and content into Siri, Spotlight, Writing Tools, Image Playground, and summaries via App Intents, entities, and schemas. Use before adding App Intents/schemas, Spotlight indexing, Writing Tools, or Image Playground; defer custom generative features and on-device model files to the sibling skills.

Backend and API implementation patterns for scalability, security, and maintainability. Use when building APIs, services, and backend infrastructure.

Build, run, and debug macOS apps with shell-first Xcode and Swift workflows. Use when launching apps or diagnosing build, startup, or runtime failures.

MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.

Specialized knowledge for the ClickHouse Monitor dashboard. Use this skill when: working with ClickHouse monitoring dashboards, analyzing query performance, writing ClickHouse system table queries, developing dashboard features, or integrating with the ClickHouse Monitor API. Covers query monitoring, table management, merge operations, system metrics, and ClickHouse version compatibility.

Drive the Command Code CLI (`cmd`) — a terminal coding agent that learns your taste — and orchestrate it as a headless sub-agent. Use this skill whenever the user mentions "cmd", "Command Code", "commandcode", asks to "spawn cmd", "dispatch cmd", "use cmd as a subagent", run coding work headlessly/unattended, fan out implementation across GitHub issues or tasks with cmd, learn/manage taste, or set up `cmd` MCP/skills/auth. Also use it whenever you are about to launch `cmd` in print/headless mode and need the correct flags (always `--yolo --max-turns 100000 --skip-onboarding`).

Use when the user asks to create a semantic commit, commit and push, or create a pull request from local changes.

Run on-device AI models in iOS, iPadOS, macOS, and visionOS apps with Core AI. Use when bundling .aimodel files, loading an AIModel, running inference over NDArray tensors, or compiling models ahead of time with coreai-build.

Use when regenerating or maintaining this plugin marketplace documentation from plugin manifests and component folders.

Consolidate a markdown knowledge base — merge near-duplicates, flag contradictions, prune stale notes, ingest inbox, refresh from sources, split, and rebuild the index. Use when a KB is noisy or stale, on a schedule, or to forget notes. Diff-for-approval; supports --auto.

Build on-device generative AI with Apple's Foundation Models framework. Use the system language model (Apple Intelligence) for text generation, structured output via @Generable and GenerationSchema, tool calling, and multimodal prompts through a LanguageModelSession.

Create distinctive, production-grade frontend interfaces with React and Next.js. Design quality, component architecture, performance patterns, and state management. Use when building web components, pages, or applications.

Use when managing GitHub pull requests, issues, workflows, releases, or review-bot feedback with the gh CLI.

Generate or review high-density, interactive, self-contained HTML artifacts based on Thariq Shihipar's "Unreasonable Effectiveness of HTML" patterns. Use this skill when asked to "create HTML," "build a dashboard," "format a PR review," "make an interactive explainer," or when you need to "review and update" existing HTML using the "good-html" style.

Scaffold a new shared-brain knowledge base folder (default ~/kb) — a plain-markdown, OKF v0.1-conformant memory store that any coding agent can read/write across sessions. Use when the user asks to set up, init, or bootstrap a kb / shared brain / persistent agent memory folder, or wants an OKF bundle with a graph viewer ready out of the box.

Use before implementing when requirements are ambiguous: run a Socratic interview to clarify a vague feature request or to find gaps in a plan/spec file, and turn it into a decision-complete plan with scope, edge cases, and tests.

Design App Intents, app entities, and App Shortcuts for iOS system surfaces. Use when exposing app actions or content to Shortcuts, Siri, Spotlight, widgets, or controls.

Build, run, and debug iOS apps on Simulator with XcodeBuildMCP. Use when launching an app, inspecting simulator UI or logs, or diagnosing runtime behavior.

Capture and interpret iOS Simulator ETTrace profiles. Use when profiling launch or runtime latency, comparing traces, or finding CPU-heavy stacks.

Capture and inspect iOS leaks and memgraphs. Use when debugging leaked objects, retain cycles, memory growth, or before/after leak evidence.

Mirror an iOS Simulator into an in-app browser and hot-reload SwiftUI previews from importable Swift packages. Use when previewing SwiftUI in the simulator, mirroring a running simulator in the browser, or live-reloading package-backed previews.

Implement and review macOS SwiftUI Liquid Glass UI. Use when adopting system glass, removing conflicting custom chrome, or building glass surfaces.

Best practices for building macOS apps with SwiftUI, AppKit, and Mac Catalyst. Use when architecting a Mac app, choosing scene and window types, wiring menus and commands, or deciding between native SwiftUI, AppKit, and Mac Catalyst.

Author, initialize, validate, and render Open Knowledge Format (OKF) bundles — vendor-neutral knowledge as markdown files with YAML frontmatter. Use when creating an OKF bundle, scaffolding a knowledge catalog, writing OKF concept docs, building index.md/log.md files, checking a bundle for OKF v0.1 conformance, or rendering a bundle as an interactive graph viewer.

Build and refactor SwiftUI UI with component patterns and examples. Use when shaping navigation, state, layouts, controls, or screen composition.

Refactor SwiftUI view files into stable, testable structure. Use when splitting large views, tightening data flow, or cleaning Observation ownership.

Break down complex tasks into parallel workstreams for efficient execution. Use when planning multi-component features, large refactors, or any work that benefits from parallelization.

Iterative execution loop — break work into small steps and verify each before the next, adapting from results. Use when executing multi-step tasks that need verification between steps.

Refactor existing knowledge into an Open Knowledge Format (OKF) bundle — convert loose notes, docs, READMEs, wikis, or a catalog/metadata export into markdown concept files with YAML frontmatter, index.md, and a knowledge graph. Use when migrating existing knowledge to OKF, normalizing a notes folder, or exporting a catalog to OKF.

Orchestrate complex work through parallel agent coordination. Decompose tasks into parallel lanes, iterate with verify loops, spawn background workers, and synthesize results. Use for multi-component features, large investigations, or any work benefiting from parallelization.

Prepare macOS packaging and notarization workflows. Use when archiving apps, validating bundles, or explaining distribution-only failures.

Comprehensive prompt engineering guidance for Claude (Anthropic), Gemini (Google), and Grok (xAI). Use when crafting prompts to leverage each model's unique capabilities—XML-style tags for Claude, system instructions for Gemini, conversational style for Grok.

Engineering discipline and systematic quality verification. Core principles, anti-patterns, decision rules, and gate procedures for code review and delivery.

React and Next.js implementation patterns for performance and maintainability. Use when building frontend components, pages, and applications with React ecosystem.

Use the `sag` CLI (ElevenLabs text-to-speech) to speak text aloud, and drive sag-notify voice notifications. Use when the user asks to speak/say something out loud, install or set up sag, set up or change voice notifications, pick a TTS voice or language, announce that work is done or that you need their input by voice, or troubleshoot why sag produces no sound (e.g. 402 paid-voice errors). Triggers on "sag", "speak this", "say out loud", "voice notification", "text to speech", "ElevenLabs", "notify me when done".

Inspect macOS signing, entitlements, and Gatekeeper issues. Use when diagnosing code signing, sandbox, hardened runtime, or trust failures.

Use when reviewing changed code for reuse, quality, and efficiency, then directly simplifying or cleaning up issues found.

Use when configuring, previewing, troubleshooting, or disabling the Claude Code statusline plugin.

Build, run, and test SwiftPM macOS packages and executables. Use when the repo is package-first or has no Xcode project.

Implement and review iOS 26+ SwiftUI Liquid Glass UI. Use when adopting Liquid Glass or checking its correctness, performance, and design fit.

Build macOS SwiftUI scenes and components with desktop patterns. Use when shaping windows, commands, toolbars, settings, split views, or inspectors.

Audit SwiftUI runtime performance from code first. Use when diagnosing slow rendering, janky scrolling, expensive updates, or profiling needs.

TypeScript best practices, strict typing patterns, and type safety strategies. Use when implementing TypeScript code with focus on type correctness and maintainability.

Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export, dataset preparation, synthetic data, MLX (Apple Silicon). Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF, prepare dataset, synthetic data, install unsloth, environment flags, MLX training.

Refactor macOS SwiftUI views and scenes into stable structure. Use when splitting large views, tightening scene state, or narrowing AppKit escapes.

Customize macOS SwiftUI windows and scene behavior. Use when tuning window chrome, drag regions, placement, restoration, launch behavior, or borderless windows.