agent-skills

Use this skill when the user wants to test a business idea, strategy, or initiative against real-world risk. Triggers include: 'test my idea', 'what are the riskiest assumptions', 'help me validate this', 'run EMT on this', 'extract assumptions', 'assumption mapping', 'what could go wrong with this plan', 'pressure test this', 'validate this plan', 'what could go wrong with this strategy', 'identify hidden risk in this idea', or any request to pressure-test a business decision before committing resources. Runs a guided Extract → Map → Test system based on David J. Bland's Precoil methodology.

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

This skill should be used when shaping a software change and needing to breadboard the solution at the right level of abstraction (places, affordances, connections), including mapping an existing system via UI + code affordances, producing a wiring diagram, a parts/BOM plan, a fit check, and (when relevant) an extract-vs-duplicate analysis.

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

This skill should be used when a user needs a demo package that starts with a live demo (not slides) and produces both a demo script and a navigable single-file HTML runbook, including caveats, respectful competitive comparison, and LLM architecture details (RAG, evals, observability).

Generate a Product Requirements Document (PRD) as JSON for Ralph by converting an existing PRD markdown file. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Run a Ralph-style, one-story-per-iteration loop using the Ralph CLI (dev, research, e2e, review), Codex-by-default, and dossier-local PRD JSON discovery.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

This skill should be used when users want to scrape multiple websites (Firecrawl, Parallel, or hybrid), extract brand guideline signals (including CSS variables + computed styles via browser probing), generate per-site prompt packs, and blend sources into a composite brand direction with exactly three outputs: brand_guidelines.md, prompt_library.json, design_tokens.json.

Web search/scrape/crawl via Firecrawl CLI (prefer for live internet lookups).

This skill should only be used when the user uses the word workflow and asks to develop or implement changes with a verification-first loop and clean handoff/pickup boundaries.

Draft PRD with scope, stories, acceptance criteria, verification. Use when shaping a new feature or spec.

Transforms Brand DNA artefacts (docs/02-guidelines/inspiration/brand_guidelines.md, design_tokens.json, prompt_library.json) into Tailwind-ready design system config (CSS variables + Tailwind preset) for a web app and a marketing site. Use when wiring tokens into Tailwind, setting up light/dark mode, or generating reusable presets and component recipes.

Fast, persistent browser automation via `browser-use` CLI (sessions persist across commands). Use for multi-step web workflows (open -> state -> click/input -> verify -> repeat). Supports chromium/headed, real Chrome (logged-in), and remote browser.

This skill should only be used when the user uses the word workflow and asks to shape a project from messy inputs into a de-risked, de-scoped shaped packet (brief, breadboard, risks, spikes) ready for wf-plan, with handoff/pickup boundaries to avoid context rot.

This skill should be used when preparing a handoff checklist for agents and persisting it as a handoff note that can be picked up in a fresh thread.

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

This skill should be used when preparing a pickup checklist when starting a task, rehydrating context from the latest handoff note if available.

Teach engineering concepts for real understanding using the Feynman technique, strong metaphors, and diagrams (render via beautiful-mermaid). Use when users ask to explain/teach/break down engineering concepts, build intuition/mental models, understand trade-offs/failure modes/design choices, or want a visual diagram.

This skill should be used when users want a Firecrawl-like capability for web discovery and clean markdown extraction using Parallel Search and Parallel Extract (including objective-led excerpts and full content).

Use this agent when you have a specification, plan, feature description, or technical document that needs user flow analysis and gap identification. This agent should be used proactively when:\n\n.

Map and refactor an agent context ecosystem: skills, commands/workflows, hooks, agent files, AGENTS.md templates, and docs. Output system map, module/dependency design, Register updates, and a concrete split/consolidate/rename/delete plan. Use when routing or ownership is messy.

Use this agent when you need to perform security audits, vulnerability assessments, or security reviews of code. This includes checking for common security vulnerabilities, validating input handling, reviewing authentication/authorization implementations, scanning for hardcoded secrets, and ensuring OWASP compliance.

React composition patterns that scale. Use when refactoring boolean prop proliferation, designing reusable component APIs, or reviewing component architecture.

Design feedback via the rams skill. Use for UI critique or design suggestions; backup to ui-skills.

React/Next.js performance best practices from Vercel. Use when writing, reviewing, or refactoring React/Next.js code for performance, data fetching, or bundle size.

Apply Disney's 12 animation principles to web interfaces. Use when implementing motion, reviewing animation quality, designing micro-interactions, or making UI feel alive. Triggers on tasks involving CSS animations, transitions, motion libraries, easing curves, springs, or UX feedback.

Baseline UI rules to prevent design slop. Use for UI design or review.

Conduct design interviews, generate five distinct UI variations in a temporary design lab, collect feedback, and produce implementation plans. Use when the user wants to explore UI design options, redesign existing components, or create new UI with multiple approaches to compare.

Fix accessibility issues. Use for a11y audits or fixes.

Fix metadata issues. Use for SEO/social metadata audits or fixes.

Fix animation performance issues. Use for motion audits or refactors.

Design and implement microinteractions, motion design, transitions, and user feedback patterns. Use when adding polish to UI interactions, implementing loading states, or creating delightful user experiences.

This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).

Best practices and example-driven guidance for building SwiftUI views and components. Use when creating or refactoring SwiftUI UI, designing tab architecture with TabView, composing screens, or needing component-specific patterns and examples.

Comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Use when styling React/Vue/Svelte components, building responsive layouts, implementing design systems, or optimizing CSS workflow.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.

Verification ladder. Pick smallest scope, run scripts in order, smoke UI, report PASS/NO-GO.