Iterate on a running web app until a fresh first-time-user tester rates its usability 9/10. Each round a new, blind subagent tries real tasks in the browser and scores them; the main agent fixes what it reports and repeats. Use when the user asks for…
MylesMCook/mcook-skills
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 35
- GitHub stars
- 0
- GitHub forks
- 1
Install with an AI assistant
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-skills.Loading the repository README…
Skills in this repository
Showing 35 of 35 collected skills.
Inspect and safely archive stale idle Codex tasks when the user asks to clean up old Codex tasks, threads, or processes. Use native Codex task operations; do not delete tasks or create scheduled cleanup.
Use only when the user explicitly invokes $fugu-second-opinion or asks for Sakana Fugu or Fugu Ultra by name to provide a second opinion, external model check, tie-breaker, or sanity check. Calls the Sakana API with prompt-only, user-authorized context by…
Use when creating, planning, prompting, generating, or editing quirky US English article illustrations: blog, newsletter, essay, Notion, document body art, editorial explainer, workflow/methodology visual, concept metaphor, shot list, or sparse…
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 a ready-to-use Goal without the `/goal` prefix. Do not use for normal…
Use this skill when you need a serious code review, diff review, or implementation-plan review from independent reviewers. In Codex hosts, run exactly three fresh Codex subagents with Skeptic, Architect, and Minimalist lenses. Return a PASS, CONTESTED, or…
Use this skill when developing, debugging, refactoring, or reviewing Microsoft Excel Office Scripts (`ExcelScript` TypeScript) for workbook automation, Power Automate Run script actions, ranges, tables, charts, PivotTables, JSON, fetch, performance, or…
Use this as the default skill for MCP work: MCP servers, MCP Apps, ChatGPT apps, widget-backed connectors, and major MCP refactors. Follow one opinionated path by default: a hosted TypeScript `mcp-use` MCP Apps project with Streamable HTTP at `/mcp`,…
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…
Use this skill for software architecture, system design, ADRs, migration plans, code review, refactors, APIs, data changes, reliability, performance, security, observability, or incident analysis when the answer should make tradeoffs explicit, prefer the…
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…
Exploratory browser QA for real web apps. Use when you want a smoke test, scoped verification, exploratory testing, or a balanced read on what works, what feels off, and what is blocked. Prefer this over `dogfood` when the user wants a lighter pass instead of…
Formal repro-first browser QA for real web apps. Use when the user wants to dogfood a site, run QA, bug hunt, find issues, or test an app with handoff-grade evidence such as repro steps, screenshots, videos, and a structured report. Do not use for lighter…
Use after an implementation plan is approved to execute mostly independent tasks through fresh subagents with scoped context, harness-aware model routing, proportional review gates, and mandatory controller verification.
Use when a user asks to inspect or debug a local MCP server or MCP App with Sunpeak's local inspector: start or connect to `sunpeak inspect` or a project dev inspector, keep simulation evidence separate from real server calls, and verify the rendered app with…
Initialize or update a repo-local `brain/`: create the `brain/` folder and managed `AGENTS.md` block, reflect durable repo learnings into principles or notes, or preview, apply, or discard one repo-scoped rumination pass.
Use AI Elements for React UIs that render AI-generated text, chat streams, tool calls, reasoning, or multimodal AI SDK messages with shadcn/ui.
Use when drafting, rewriting, editing, summarizing, or polishing prose for humans: docs, README/API docs, PRs, commit text, emails, Slack, reports, explanations, UI copy, comments, or final answers. Preserve meaning, choose a reader-appropriate tone, cut…
Integrate or troubleshoot QuiverAI's API at api.quiver.ai for listing models, generating SVGs from text, and vectorizing images into SVG. Use when Codex needs to wire QuiverAI into a Node.js or REST client, handle QUIVERAI_API_KEY safely, debug QuiverAI HTTP…
Create, audit, improve, rewrite, or package Agent Skills and Codex skills. Use when the task involves a SKILL.md-based skill, trigger descriptions, frontmatter, agents/openai.yaml, skills.sh listings, npx skills installation, or producing an updated skill…
Use this skill when the user explicitly wants final end-of-session closeout and no more branch or PR limbo: proper verification, proper commits, main/mainline landing, push, repo-native merge/release/deploy/publish steps, tracker updates, Entire/checkpoint…
Use when one AI agent needs to hand work to another agent with fresh context. Produce a self-contained handoff prompt with evidence, unknowns, and the next action. Create files only if explicitly asked.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include…
Use this skill when the user needs to design or audit one contained interaction moment such as button states, validation, loading, toggles, confirmations, undo, or other small state changes that need to feel clear, responsive, and trustworthy.
Use this skill when the user is starting, shaping, scoping, comparing, or planning something and needs help thinking it through in conversation. Trigger on vague starts like "I want to do X," "I'm thinking about...", "help me figure this out," "which…
Use this skill when the user wants a Nothing-inspired interface or a monochrome, industrial, typography-led UI: OLED-black or off-white surfaces, Swiss-style structure, dot-matrix hero moments, segmented progress bars, instrument-like controls, or an explicit…
Refine recently changed code for clarity, consistency, and maintainability without changing behavior. Use when the user explicitly asks to simplify, clean up, or lightly refactor touched code, reduce local complexity, remove redundancy, improve naming or…
Build TRMNL plugins with a strong bias toward Private Plugins and Recipes. Use when you need help choosing Private Plugin vs Recipe vs Third Party vs BYOS, generating TRMNL Form Fields YAML, picking polling vs webhook vs plugin_merge, writing Liquid and…
Author and debug raw Vega specifications when lower-level control over dataflow, scales, axes, legends, marks, signals, or event streams is required. Use for raw Vega authoring, advanced signal/event-stream interaction, or cases where Vega-Lite cannot express…
Author and debug Vega-Lite specifications for chart design, encoding choice, transforms, view composition, params, and invalid-data handling. Use for general Vega-Lite authoring and keep the solution in Vega-Lite unless the requirement clearly needs raw Vega.…
Practical Electron guidance for building and maintaining desktop apps with clear main process, renderer, preload, IPC, BrowserWindow, packaging, Electron Forge, debugging, and security defaults. Use when working on Electron app creation, Electron Forge setup,…
Find battle-tested open source projects on GitHub instead of writing fresh code for solved problems. Use when a task is generic enough that an existing tool or library likely exists, especially for CLI utilities, file conversion, scraping, automation, media…
Understand and build with the @mariozechner/pi-coding-agent SDK from pi-mono. Use when a request is about the pi SDK or pi-mono SDK, especially createAgentSession, DefaultResourceLoader, AuthStorage, ModelRegistry, SessionManager, SettingsManager, built-in or…
Create, refactor, and validate Pi packages. Use when an agent needs to scaffold a new Pi package, choose the correct Pi package surface, wire `package.json` `pi` manifests, or prove a Pi package works through the real `pi install` path.
Reduce incidental complexity in code and design. Use when shaping APIs, module boundaries, refactors, tests, naming, and architecture tradeoffs with a bias toward concrete, local, reversible solutions.