Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/MylesMCook/mcook-plugins.Loading the repository README…
Showing 40 of 54 collected skills.
Discover and use the current machine's nektos/act installation to validate or debug GitHub Actions locally. Use when act is requested, or when local execution of an existing CI test job would help authorized coding work. Check the installed CLI,…
Run a momentum-first three-lens Codex review of an explicit or readily inferable diff, commit, branch, plan, plugin, or small file set. Use when the user explicitly asks for adversarial, independent, three-reviewer, or Skeptic/Architect/Minimalist review.…
Create, plan, prompt, edit, and QA sparse 16:9 US English illustrations with Inkblot, a small solid-black deadpan worker. Use when the user asks for Inkblot or American Inkblot style, sparse white-background hand-drawn editorial/concept/article art, or a…
Build, integrate, debug, or update assistant-ui using current official upstream skills, documentation, and version-matched source. Use for assistant-ui questions, projects using @assistant-ui packages, or explicit assistant-ui evaluations. Generic chat UI…
Create, improve, format, or safely investigate evidence for fix-ready bug reports covering software, hardware, APIs, CLIs, SDKs, apps, services, integrations, data pipelines, infrastructure, build and test systems, and research tooling. Use when the requested…
Buzz CLI for relay operations: owner-reviewed agent drafts, messaging, channels, DMs, users, workflows, feed, reactions, canvas, social, repos, uploads, and agent memory.
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP…
Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.
Use when Codex should ask Claude Code CLI for investigation help or a fix plan while Codex keeps edit control.
Use when Codex should ask Claude Code CLI for a read-only review of a diff, branch, or working tree.
Use when Codex should call the local Claude Code CLI for setup checks, asks, or second opinions.
Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, scoped --help with examples, stdin and pipelines, stable output, actionable errors, idempotency, dry runs, and predictable structure. Use when building a CLI, adding…
Add, improve, or audit comments that help humans understand and review code, especially LLM-written code, in any language. Use when asked to explain generated code through comments, improve source comments or API docs, clean up stale comments, or propose a…
Author and debug Deneb visuals for Power BI, including dataset binding, PBIR persistence, report-theme integration, interactivity, and template metadata. Use this first for Deneb, Power BI, PBIR, report-theme, cross-filter, cross-highlight, or dataset-binding…
Turn "how does X work?" into an interactive, step-by-step explainer page. Use when a user asks how a system, protocol, process, workflow or incident works, wants it shown visually, or wants a walkthrough of what passes between parts (apps, servers, people,…
Operate and diagnose Microsoft Fabric, Power BI, and Power Automate through the bundled microsoft_fabric MCP server. Use for Fabric workspace and item inventory, notebook source inspection and guarded cell edits, pipeline definition edits and job failures,…
Trace one exact submission or correlation key across Power Automate runs, authoritative business records, and delivery artifacts. Use when someone asks whether a specific workflow submission completed, is still processing, failed before writing, or needs…
Build, review, or debug React components using Base UI and StyleX with live official documentation lookup and source citations. Lead Base UI + StyleX component selection, anatomy, state styling, render composition, forms, and themed overlays, including in…
Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.
Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph…
Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries,…
Set up, author, migrate, review, or debug StyleX styling in React and TypeScript applications. Use for @stylexjs/stylex compiler integration, stylex.create and stylex.props, tokens, themes, responsive styles, typed component style APIs, or Tailwind-to-StyleX…
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring…
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js…
Verify local web applications with Playwright CLI for live browser work and the repository's existing test runner for durable regressions. Use for UI flows, screenshots, console errors, accessibility checks, and browser debugging.
Complete final repository closeout when the user explicitly asks to git it out, get it out, ship completed work, or otherwise hand off a substantially finished session. Inspect repository state, run required gates, create proper commits, land and push…
Use when the user wants to turn a rough idea, dirty goal, messy long-run prompt, sidechat thought, or under-scoped Codex task into clean Goal objective text under 4000 characters. Produce ready-to-use Goal text without the `/goal` prefix. Do not use for…
Operate self-hosted Grist as a replay-safe application event log. Use for AppEvents schemas, REST logging, read-only SQL analysis, Grist API credentials, or deciding whether self-hosted Grist MCP is appropriate.
Evaluate, create, modify, test, debug, and verify Hono web applications. Use when Hono is named or imported, including routes, middleware, validation, RPC, JSX, adapters, CLI, testing, deployment boundaries, UI architecture, or an explicit Hono evaluation. Do…
Evaluate substantive software architecture tradeoffs, system boundaries, ADRs, migration strategies, and architectural incident lessons. Use when alternatives, ownership, compatibility, or recovery need an explicit design decision. Do not activate for…
Use this skill when the user wants to improve the visual quality of a human-facing surface such as UI, dashboards, landing pages, ecommerce, forms, decks, editorial pages, documents, print pieces, or other front-end work. Apply it to critique, redesign…
Laws of UX critique skill. Use when evaluating mockups, screenshots, design specs, prototypes, flows, onboarding, checkout, dashboards, forms, or design-review requests, even when the user does not say UX or name a law. Output the 2-4 most relevant laws with…
Keep meaningful repository development work aligned with Linear: map a repository, reuse or create outcome issues, resume tracked work, and record verification or blockers. Use for explicit Linear tracking or feature and bug work in a repository with an…
Builds, ports, updates, or reviews plugins for the Myles Codex Plugins marketplace, including portable Agent Plugins 1.0.0 packages, OpenAI-native plugin packages, dual-format compatibility, and MCP 2026-07-28 readiness. Use when creating a reusable…
Use when an MCP server needs optional inline UI, an interactive MCP App, a chart or dashboard, a picker, a review or confirmation surface, or a standards-first bridge between a Go MCP backend and a TypeScript component. Preserve a useful tool-only path and…
Build, refactor, review, or release an MCP server; choose Go, TypeScript, Python, or Rust; define tools and schemas; select remote HTTP or local stdio; design auth; add optional MCP Apps UI; or validate MCP 2026-07-28 and client portability.
Use when a local stdio MCP server must be distributed as a one-click MCP Bundle for desktop hosts. Default new Go servers to self-contained binary bundles, use the current stable MCPB manifest, and keep the ordinary executable usable outside MCPB.
Coordinate explicitly requested, decomposable work through native Codex subagents with deliberate model and reasoning selection, bounded parallelism, structured handoffs, verification, and parent-owned synthesis. Use only when the user invokes $orchestrate,…
Repository README source: README.md
Read the source README