From 12585145a3d5d8a532372a43b62ddbccb899a84a Mon Sep 17 00:00:00 2001
From: rohan-tessl <rohan-tessl@users.noreply.github.com>
Date: Wed, 6 May 2026 10:38:43 +0530
Subject: [PATCH] feat: improve 5 lowest-scoring skill definitions

---
 .agents/skills/building-components/SKILL.md   |  56 ++-
 .agents/skills/databricks-core/SKILL.md       |   2 +-
 .agents/skills/seo-audit/SKILL.md             | 464 ++----------------
 .agents/skills/vercel-cli/SKILL.md            |   6 +-
 .../vercel-composition-patterns/SKILL.md      | 115 ++---
 5 files changed, 154 insertions(+), 489 deletions(-)

diff --git a/.agents/skills/building-components/SKILL.md b/.agents/skills/building-components/SKILL.md
index b64fb6a..5a4dfe1 100644
--- a/.agents/skills/building-components/SKILL.md
+++ b/.agents/skills/building-components/SKILL.md
@@ -1,22 +1,56 @@
 ---
 name: building-components
-description: Guide for building modern, accessible, and composable UI components. Use when building new components, implementing accessibility, creating composable APIs, setting up design tokens, publishing to npm/registry, or writing component documentation.
+description: "Guide for building modern, accessible, and composable UI components. Use when building new components, implementing accessibility, creating composable APIs, setting up design tokens, publishing to npm/registry, or writing component documentation."
 ---
 
 # Building Components
 
-## When to use this skill
+## Workflow
 
-Use when the user is:
+Follow this sequence when building a new component:
 
-- Building new UI components (primitives, components, blocks, templates)
-- Implementing accessibility features (ARIA, keyboard navigation, focus management)
-- Creating composable component APIs (slots, render props, controlled/uncontrolled state)
-- Setting up design tokens and theming systems
-- Publishing components to npm or a registry
-- Writing component documentation
-- Implementing polymorphism or as-child patterns
-- Working with data attributes for styling/state
+1. **Define the API** -- Decide on props, slots, and controlled/uncontrolled state. See [composition.mdx](./references/composition.mdx) and [state.mdx](./references/state.mdx).
+2. **Implement the component** -- Use composition patterns (children over render props, explicit variants over boolean flags). See [principles.mdx](./references/principles.mdx).
+3. **Add accessibility** -- Add ARIA roles, keyboard navigation, and focus management. See [accessibility.mdx](./references/accessibility.mdx).
+4. **Style with data attributes** -- Use `data-*` attributes for state-driven styling rather than className toggling. See [data-attributes.mdx](./references/data-attributes.mdx) and [styling.mdx](./references/styling.mdx).
+5. **Export types** -- Co-locate TypeScript types with the component. See [types.mdx](./references/types.mdx).
+6. **Validate** -- Verify: ARIA roles present, keyboard navigation works, TypeScript types exported, design tokens used (no raw color values).
+7. **Publish** -- Publish to npm or a registry. See [npm.mdx](./references/npm.mdx) or [registry.mdx](./references/registry.mdx).
+
+## Quick Example
+
+```tsx
+import { forwardRef } from "react";
+
+interface ButtonProps extends React.ButtonHTMLAttributes<HTMLButtonElement> {
+  variant?: "primary" | "secondary" | "ghost";
+  size?: "sm" | "md" | "lg";
+}
+
+const Button = forwardRef<HTMLButtonElement, ButtonProps>(
+  ({ variant = "primary", size = "md", children, ...props }, ref) => (
+    <button
+      ref={ref}
+      data-variant={variant}
+      data-size={size}
+      role="button"
+      {...props}
+    >
+      {children}
+    </button>
+  )
+);
+Button.displayName = "Button";
+```
+
+## Decision Tree
+
+- **Building a primitive** -- See [definitions.mdx](./references/definitions.mdx) + [composition.mdx](./references/composition.mdx)
+- **Adding polymorphism** -- See [as-child.mdx](./references/as-child.mdx) + [polymorphism.mdx](./references/polymorphism.mdx)
+- **Setting up theming** -- See [design-tokens.mdx](./references/design-tokens.mdx)
+- **Publishing to a registry** -- See [registry.mdx](./references/registry.mdx) or [npm.mdx](./references/npm.mdx)
+- **Writing docs** -- See [docs.mdx](./references/docs.mdx)
+- **Marketplace distribution** -- See [marketplaces.mdx](./references/marketplaces.mdx)
 
 ## References
 
diff --git a/.agents/skills/databricks-core/SKILL.md b/.agents/skills/databricks-core/SKILL.md
index 79a2465..23ce752 100644
--- a/.agents/skills/databricks-core/SKILL.md
+++ b/.agents/skills/databricks-core/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: "databricks-core"
-description: "Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks."
+description: "Use when the user asks about Databricks CLI commands, authentication setup, workspace configuration, profile management, data exploration via Unity Catalog, or Databricks Asset Bundle (DAB) deployment. Configures Databricks auth and profiles, explores catalog/schema/table data, and deploys bundles."
 compatibility: Requires databricks CLI (>= v0.292.0)
 metadata:
   version: "0.1.0"
diff --git a/.agents/skills/seo-audit/SKILL.md b/.agents/skills/seo-audit/SKILL.md
index 06be685..6931cf3 100644
--- a/.agents/skills/seo-audit/SKILL.md
+++ b/.agents/skills/seo-audit/SKILL.md
@@ -1,450 +1,92 @@
 ---
 name: seo-audit
-description: When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
+description: "Use when the user wants to audit, review, or diagnose SEO issues on their site. Triggers on 'SEO audit', 'technical SEO', 'why am I not ranking', 'SEO issues', 'on-page SEO', 'meta tags review', 'SEO health check', 'my traffic dropped', 'lost rankings', 'not showing up in Google', 'core web vitals', 'crawl errors', or 'indexing issues'. For building pages at scale, see programmatic-seo. For structured data, see schema-markup. For AI search optimization, see ai-seo."
 metadata:
   version: 1.1.0
 ---
 
 # SEO Audit
 
-You are an expert in search engine optimization. Your goal is to identify SEO issues and provide actionable recommendations to improve organic search performance.
-
 ## Initial Assessment
 
-**Check for product marketing context first:**
-If `.agents/product-marketing-context.md` exists (or `.claude/product-marketing-context.md` in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
-
-Before auditing, understand:
-
-1. **Site Context**
-   - What type of site? (SaaS, e-commerce, blog, etc.)
-   - What's the primary business goal for SEO?
-   - What keywords/topics are priorities?
-
-2. **Current State**
-   - Any known issues or concerns?
-   - Current organic traffic level?
-   - Recent changes or migrations?
-
-3. **Scope**
-   - Full site audit or specific pages?
-   - Technical + on-page, or one focus area?
-   - Access to Search Console / analytics?
-
----
-
-## Audit Framework
-
-### Schema Markup Detection Limitation
-
-**`web_fetch` and `curl` cannot reliably detect structured data / schema markup.**
-
-Many CMS plugins (AIOSEO, Yoast, RankMath) inject JSON-LD via client-side JavaScript — it won't appear in static HTML or `web_fetch` output (which strips `<script>` tags during conversion).
-
-**To accurately check for schema markup, use one of these methods:**
-
-1. **Browser tool** — render the page and run: `document.querySelectorAll('script[type="application/ld+json"]')`
-2. **Google Rich Results Test** — https://search.google.com/test/rich-results
-3. **Screaming Frog export** — if the client provides one, use it (SF renders JavaScript)
-
-Reporting "no schema found" based solely on `web_fetch` or `curl` leads to false audit findings — these tools can't see JS-injected schema.
-
-### Priority Order
-
-1. **Crawlability & Indexation** (can Google find and index it?)
-2. **Technical Foundations** (is the site fast and functional?)
-3. **On-Page Optimization** (is content optimized?)
-4. **Content Quality** (does it deserve to rank?)
-5. **Authority & Links** (does it have credibility?)
-
----
-
-## Technical SEO Audit
-
-### Crawlability
-
-**Robots.txt**
-
-- Check for unintentional blocks
-- Verify important pages allowed
-- Check sitemap reference
-
-**XML Sitemap**
-
-- Exists and accessible
-- Submitted to Search Console
-- Contains only canonical, indexable URLs
-- Updated regularly
-- Proper formatting
-
-**Site Architecture**
-
-- Important pages within 3 clicks of homepage
-- Logical hierarchy
-- Internal linking structure
-- No orphan pages
-
-**Crawl Budget Issues** (for large sites)
-
-- Parameterized URLs under control
-- Faceted navigation handled properly
-- Infinite scroll with pagination fallback
-- Session IDs not in URLs
-
-### Indexation
-
-**Index Status**
-
-- site:domain.com check
-- Search Console coverage report
-- Compare indexed vs. expected
-
-**Indexation Issues**
-
-- Noindex tags on important pages
-- Canonicals pointing wrong direction
-- Redirect chains/loops
-- Soft 404s
-- Duplicate content without canonicals
-
-**Canonicalization**
-
-- All pages have canonical tags
-- Self-referencing canonicals on unique pages
-- HTTP → HTTPS canonicals
-- www vs. non-www consistency
-- Trailing slash consistency
-
-### Site Speed & Core Web Vitals
-
-**Core Web Vitals**
-
-- LCP (Largest Contentful Paint): < 2.5s
-- INP (Interaction to Next Paint): < 200ms
-- CLS (Cumulative Layout Shift): < 0.1
-
-**Speed Factors**
-
-- Server response time (TTFB)
-- Image optimization
-- JavaScript execution
-- CSS delivery
-- Caching headers
-- CDN usage
-- Font loading
-
-**Tools**
-
-- PageSpeed Insights
-- WebPageTest
-- Chrome DevTools
-- Search Console Core Web Vitals report
-
-### Mobile-Friendliness
-
-- Responsive design (not separate m. site)
-- Tap target sizes
-- Viewport configured
-- No horizontal scroll
-- Same content as desktop
-- Mobile-first indexing readiness
-
-### Security & HTTPS
-
-- HTTPS across entire site
-- Valid SSL certificate
-- No mixed content
-- HTTP → HTTPS redirects
-- HSTS header (bonus)
-
-### URL Structure
-
-- Readable, descriptive URLs
-- Keywords in URLs where natural
-- Consistent structure
-- No unnecessary parameters
-- Lowercase and hyphen-separated
-
----
-
-## On-Page SEO Audit
-
-### Title Tags
-
-**Check for:**
-
-- Unique titles for each page
-- Primary keyword near beginning
-- 50-60 characters (visible in SERP)
-- Compelling and click-worthy
-- Brand name placement (end, usually)
-
-**Common issues:**
-
-- Duplicate titles
-- Too long (truncated)
-- Too short (wasted opportunity)
-- Keyword stuffing
-- Missing entirely
-
-### Meta Descriptions
-
-**Check for:**
-
-- Unique descriptions per page
-- 150-160 characters
-- Includes primary keyword
-- Clear value proposition
-- Call to action
-
-**Common issues:**
+**Check for product marketing context first:** If `.agents/product-marketing-context.md` exists, read it before asking questions.
 
-- Duplicate descriptions
-- Auto-generated garbage
-- Too long/short
-- No compelling reason to click
+Gather before auditing:
 
-### Heading Structure
+1. **Site type** (SaaS, e-commerce, blog, local) and primary business goal
+2. **Known issues**, recent changes/migrations, current traffic level
+3. **Scope** -- full site or specific pages; technical + on-page or one focus area; Search Console access available?
 
-**Check for:**
+## Schema Markup Detection Limitation
 
-- One H1 per page
-- H1 contains primary keyword
-- Logical hierarchy (H1 → H2 → H3)
-- Headings describe content
-- Not just for styling
+`web_fetch` and `curl` cannot detect JS-injected JSON-LD. Use one of:
 
-**Common issues:**
+1. **Browser tool**: `document.querySelectorAll('script[type="application/ld+json"]')`
+2. **Google Rich Results Test**: https://search.google.com/test/rich-results
+3. **Screaming Frog export** (if available)
 
-- Multiple H1s
-- Skip levels (H1 → H3)
-- Headings used for styling only
-- No H1 on page
+Never report "no schema found" based solely on `web_fetch`.
 
-### Content Optimization
+## Audit Checklist
 
-**Primary Page Content**
+Audit in priority order. For each issue found, record: Issue, Impact (High/Medium/Low), Evidence, Fix, Priority.
 
-- Keyword in first 100 words
-- Related keywords naturally used
-- Sufficient depth/length for topic
-- Answers search intent
-- Better than competitors
+### 1. Crawlability and Indexation
 
-**Thin Content Issues**
+- `robots.txt`: no unintentional blocks, sitemap referenced
+- XML sitemap: accessible, canonical/indexable URLs only, regularly updated
+- Important pages reachable within 3 clicks
+- No orphan pages; logical internal linking
+- Large sites: parameterized URLs controlled, faceted navigation handled
+- Index status: `site:domain.com` count matches expected; check Search Console coverage
+- No noindex on important pages, no misdirected canonicals, no redirect chains
+- Canonical consistency: self-referencing, HTTPS, www/non-www, trailing slash
 
-- Pages with little unique content
-- Tag/category pages with no value
-- Doorway pages
-- Duplicate or near-duplicate content
+### 2. Technical Foundations
 
-### Image Optimization
+- **Core Web Vitals**: LCP < 2.5s, INP < 200ms, CLS < 0.1
+- TTFB, image compression, JS/CSS delivery, caching headers, CDN, font loading
+- HTTPS everywhere, valid SSL, no mixed content, HTTP-to-HTTPS redirects
+- Mobile: responsive, proper viewport, adequate tap targets, no horizontal scroll
+- URLs: readable, lowercase, hyphenated, no unnecessary parameters
 
-**Check for:**
+### 3. On-Page Optimization
 
-- Descriptive file names
-- Alt text on all images
-- Alt text describes image
-- Compressed file sizes
-- Modern formats (WebP)
-- Lazy loading implemented
-- Responsive images
+- **Titles**: unique per page, primary keyword near start, 50-60 chars, brand at end
+- **Meta descriptions**: unique per page, 150-160 chars, includes keyword, has CTA
+- **Headings**: one H1 per page with keyword, logical H1-H2-H3 hierarchy
+- **Content**: keyword in first 100 words, sufficient depth, answers search intent
+- **Images**: descriptive filenames, alt text, compressed, WebP, lazy loaded
+- **Internal links**: important pages well-linked, descriptive anchor text, no broken links
+- **Keyword mapping**: clear target per page, no cannibalization, topical clusters
 
-### Internal Linking
+### 4. Content Quality (E-E-A-T)
 
-**Check for:**
-
-- Important pages well-linked
-- Descriptive anchor text
-- Logical link relationships
-- No broken internal links
-- Reasonable link count per page
-
-**Common issues:**
-
-- Orphan pages (no internal links)
-- Over-optimized anchor text
-- Important pages buried
-- Excessive footer/sidebar links
-
-### Keyword Targeting
-
-**Per Page**
-
-- Clear primary keyword target
-- Title, H1, URL aligned
-- Content satisfies search intent
-- Not competing with other pages (cannibalization)
-
-**Site-Wide**
-
-- Keyword mapping document
-- No major gaps in coverage
-- No keyword cannibalization
-- Logical topical clusters
-
----
-
-## Content Quality Assessment
-
-### E-E-A-T Signals
-
-**Experience**
-
-- First-hand experience demonstrated
-- Original insights/data
-- Real examples and case studies
-
-**Expertise**
-
-- Author credentials visible
-- Accurate, detailed information
-- Properly sourced claims
-
-**Authoritativeness**
-
-- Recognized in the space
-- Cited by others
-- Industry credentials
-
-**Trustworthiness**
-
-- Accurate information
-- Transparent about business
-- Contact information available
-- Privacy policy, terms
-- Secure site (HTTPS)
-
-### Content Depth
-
-- Comprehensive coverage of topic
-- Answers follow-up questions
-- Better than top-ranking competitors
-- Updated and current
-
-### User Engagement Signals
-
-- Time on page
-- Bounce rate in context
-- Pages per session
-- Return visits
-
----
-
-## Common Issues by Site Type
-
-### SaaS/Product Sites
-
-- Product pages lack content depth
-- Blog not integrated with product pages
-- Missing comparison/alternative pages
-- Feature pages thin on content
-- No glossary/educational content
-
-### E-commerce
-
-- Thin category pages
-- Duplicate product descriptions
-- Missing product schema
-- Faceted navigation creating duplicates
-- Out-of-stock pages mishandled
-
-### Content/Blog Sites
-
-- Outdated content not refreshed
-- Keyword cannibalization
-- No topical clustering
-- Poor internal linking
-- Missing author pages
-
-### Local Business
-
-- Inconsistent NAP
-- Missing local schema
-- No Google Business Profile optimization
-- Missing location pages
-- No local content
-
----
+- First-hand experience demonstrated, original insights/data
+- Author credentials visible, properly sourced claims
+- Comprehensive topic coverage, answers follow-up questions, current/updated
+- Contact info, privacy policy, terms available
 
 ## Output Format
 
-### Audit Report Structure
-
-**Executive Summary**
+**Executive Summary**: Overall health, top 3-5 priorities, quick wins.
 
-- Overall health assessment
-- Top 3-5 priority issues
-- Quick wins identified
+**Findings** (per section): Issue, Impact, Evidence, Fix, Priority.
 
-**Technical SEO Findings**
-For each issue:
-
-- **Issue**: What's wrong
-- **Impact**: SEO impact (High/Medium/Low)
-- **Evidence**: How you found it
-- **Fix**: Specific recommendation
-- **Priority**: 1-5 or High/Medium/Low
-
-**On-Page SEO Findings**
-Same format as above
-
-**Content Findings**
-Same format as above
-
-**Prioritized Action Plan**
-
-1. Critical fixes (blocking indexation/ranking)
+**Prioritized Action Plan**:
+1. Critical (blocking indexation/ranking)
 2. High-impact improvements
 3. Quick wins (easy, immediate benefit)
 4. Long-term recommendations
 
----
-
 ## References
 
-- [AI Writing Detection](references/ai-writing-detection.md): Common AI writing patterns to avoid (em dashes, overused phrases, filler words)
-- For AI search optimization (AEO, GEO, LLMO, AI Overviews), see the **ai-seo** skill
-
----
-
-## Tools Referenced
-
-**Free Tools**
-
-- Google Search Console (essential)
-- Google PageSpeed Insights
-- Bing Webmaster Tools
-- Rich Results Test (**use this for schema validation — it renders JavaScript**)
-- Mobile-Friendly Test
-- Schema Validator
-
-> **Note on schema detection:** `web_fetch` strips `<script>` tags (including JSON-LD) and cannot detect JS-injected schema. Use the browser tool, Rich Results Test, or Screaming Frog instead — they render JavaScript and capture dynamically-injected markup. See the Schema Markup Detection Limitation section above.
-
-**Paid Tools** (if available)
-
-- Screaming Frog
-- Ahrefs / Semrush
-- Sitebulb
-- ContentKing
-
----
-
-## Task-Specific Questions
-
-1. What pages/keywords matter most?
-2. Do you have Search Console access?
-3. Any recent changes or migrations?
-4. Who are your top organic competitors?
-5. What's your current organic traffic baseline?
-
----
+- [AI Writing Detection](references/ai-writing-detection.md): Common AI writing patterns to avoid
+- For AI search optimization, see **ai-seo**
+- For structured data, see **schema-markup**
+- For building SEO pages at scale, see **programmatic-seo**
 
-## Related Skills
+## Tools
 
-- **ai-seo**: For optimizing content for AI search engines (AEO, GEO, LLMO)
-- **programmatic-seo**: For building SEO pages at scale
-- **site-architecture**: For page hierarchy, navigation design, and URL structure
-- **schema-markup**: For implementing structured data
-- **page-cro**: For optimizing pages for conversion (not just ranking)
-- **analytics-tracking**: For measuring SEO performance
+- **Free**: Google Search Console, PageSpeed Insights, Rich Results Test (renders JS -- use for schema), Bing Webmaster Tools
+- **Paid** (if available): Screaming Frog, Ahrefs/Semrush, Sitebulb, ContentKing
diff --git a/.agents/skills/vercel-cli/SKILL.md b/.agents/skills/vercel-cli/SKILL.md
index 91b5799..a699b31 100644
--- a/.agents/skills/vercel-cli/SKILL.md
+++ b/.agents/skills/vercel-cli/SKILL.md
@@ -1,11 +1,11 @@
 ---
 name: vercel-cli
-description: Deploy, manage, and develop projects on Vercel from the command line
+description: "Deploy, manage, and develop projects on Vercel from the command line. Use when the user asks to deploy to Vercel, configure environment variables, manage domains, check deployment status, link projects, set up local dev with Vercel, or run Vercel CLI commands like 'vercel deploy', 'vercel dev', 'vercel env', or 'vercel domains'."
 ---
 
 # Vercel CLI Skill
 
-The Vercel CLI (`vercel` or `vc`) deploys, manages, and develops projects on the Vercel platform from the command line. Use `vercel <command> -h` for full flag details on any command.
+Use `vercel <command> -h` for full flag details on any command.
 
 ## Critical: Project Linking
 
@@ -32,6 +32,8 @@ vercel deploy     # preview deployment
 vercel --prod     # production deployment
 ```
 
+**Verify setup**: After `vercel link`, confirm `.vercel/project.json` (or `repo.json`) exists. After `vercel deploy`, check the returned URL to confirm success.
+
 ## Decision Tree
 
 Use this to route to the correct reference file:
diff --git a/.agents/skills/vercel-composition-patterns/SKILL.md b/.agents/skills/vercel-composition-patterns/SKILL.md
index d8a4672..acca509 100644
--- a/.agents/skills/vercel-composition-patterns/SKILL.md
+++ b/.agents/skills/vercel-composition-patterns/SKILL.md
@@ -1,11 +1,6 @@
 ---
 name: vercel-composition-patterns
-description:
-  React composition patterns that scale. Use when refactoring components with
-  boolean prop proliferation, building flexible component libraries, or
-  designing reusable APIs. Triggers on tasks involving compound components,
-  render props, context providers, or component architecture. Includes React 19
-  API changes.
+description: "React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes."
 license: MIT
 metadata:
   author: vercel
@@ -14,76 +9,68 @@ metadata:
 
 # React Composition Patterns
 
-Composition patterns for building flexible, maintainable React components. Avoid
-boolean prop proliferation by using compound components, lifting state, and
-composing internals. These patterns make codebases easier for both humans and AI
-agents to work with as they scale.
+## Refactoring Workflow
 
-## When to Apply
+1. **Identify** -- Find components with 3+ boolean props or complex conditional rendering
+2. **Choose pattern** -- Use the priority table below to select the right approach
+3. **Refactor** -- Apply the pattern; prefer compound components for complex UI, explicit variants for mode switches
+4. **Validate** -- Confirm: no boolean prop proliferation, state lifted to providers, children used over render props
+5. **Review** -- Read the relevant rule file for edge cases before finalizing
 
-Reference these guidelines when:
+## Core Pattern: Boolean Props to Compound Components
 
-- Refactoring components with many boolean props
-- Building reusable component libraries
-- Designing flexible component APIs
-- Reviewing component architecture
-- Working with compound components or context providers
+```tsx
+// BEFORE: boolean prop proliferation
+<Card showHeader showFooter isCollapsible hasBorder />
 
-## Rule Categories by Priority
-
-| Priority | Category                | Impact | Prefix          |
-| -------- | ----------------------- | ------ | --------------- |
-| 1        | Component Architecture  | HIGH   | `architecture-` |
-| 2        | State Management        | MEDIUM | `state-`        |
-| 3        | Implementation Patterns | MEDIUM | `patterns-`     |
-| 4        | React 19 APIs           | MEDIUM | `react19-`      |
-
-## Quick Reference
-
-### 1. Component Architecture (HIGH)
-
-- `architecture-avoid-boolean-props` - Don't add boolean props to customize
-  behavior; use composition
-- `architecture-compound-components` - Structure complex components with shared
-  context
-
-### 2. State Management (MEDIUM)
-
-- `state-decouple-implementation` - Provider is the only place that knows how
-  state is managed
-- `state-context-interface` - Define generic interface with state, actions, meta
-  for dependency injection
-- `state-lift-state` - Move state into provider components for sibling access
-
-### 3. Implementation Patterns (MEDIUM)
-
-- `patterns-explicit-variants` - Create explicit variant components instead of
-  boolean modes
-- `patterns-children-over-render-props` - Use children for composition instead
-  of renderX props
+// AFTER: compound components via composition
+<Card>
+  <Card.Header />
+  <Card.Body collapsible>{content}</Card.Body>
+  <Card.Footer />
+</Card>
+```
 
-### 4. React 19 APIs (MEDIUM)
+## Core Pattern: Explicit Variants Over Boolean Modes
 
-> **⚠️ React 19+ only.** Skip this section if using React 18 or earlier.
+```tsx
+// BEFORE: boolean mode switching
+<Button primary />
+<Button secondary />
+<Button ghost />
 
-- `react19-no-forwardref` - Don't use `forwardRef`; use `use()` instead of `useContext()`
+// AFTER: explicit variant components or union prop
+<Button variant="primary" />
+<PrimaryButton />
+```
 
-## How to Use
+## Core Pattern: React 19 -- Drop forwardRef
 
-Read individual rule files for detailed explanations and code examples:
+```tsx
+// React 18 (old)
+const Input = forwardRef<HTMLInputElement, InputProps>((props, ref) => (
+  <input ref={ref} {...props} />
+));
 
-```
-rules/architecture-avoid-boolean-props.md
-rules/state-context-interface.md
+// React 19 (new) -- ref is a regular prop
+function Input({ ref, ...props }: InputProps & { ref?: React.Ref<HTMLInputElement> }) {
+  return <input ref={ref} {...props} />;
+}
 ```
 
-Each rule file contains:
+## Rules by Priority
 
-- Brief explanation of why it matters
-- Incorrect code example with explanation
-- Correct code example with explanation
-- Additional context and references
+| Priority | Rule | What to do |
+| -------- | ---- | ---------- |
+| 1 (HIGH) | `architecture-avoid-boolean-props` | Replace boolean props with composition |
+| 1 (HIGH) | `architecture-compound-components` | Structure complex components with shared context |
+| 2 | `state-decouple-implementation` | Provider is the only place that knows state impl |
+| 2 | `state-context-interface` | Generic interface: state, actions, meta |
+| 2 | `state-lift-state` | Move state into providers for sibling access |
+| 3 | `patterns-explicit-variants` | Variant components instead of boolean modes |
+| 3 | `patterns-children-over-render-props` | Use children, not renderX props |
+| 4 | `react19-no-forwardref` | Drop `forwardRef`; use `use()` instead of `useContext()` |
 
-## Full Compiled Document
+Read individual rule files in `rules/` for detailed explanations with incorrect/correct code examples.
 
-For the complete guide with all rules expanded: `AGENTS.md`
+For the complete compiled guide with all rules expanded: `AGENTS.md`