tribunal-kit 1.0.0 → 2.4.2

package/.agent/skills/frontend-design/SKILL.md

@@ -2,6 +2,9 @@
 name: frontend-design
 description: Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.
 allowed-tools: Read, Write, Edit, Glob, Grep, Bash
+version: 1.0.0
+last-updated: 2026-03-12
+applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
 ---
 
 # Frontend Design System
@@ -128,6 +131,16 @@ REFLECTIVE (memory) → After: "I like what this says about me"
 
 ## 3. Layout Principles
 
+### Spatial & Asymmetric Composition (Pro Max Level)
+
+```
+Break out of basic CSS Grid/Flexbox row mentality. True premium design uses space intentionally:
+├── Overlapping: Let images break out of their containers
+├── Asymmetry: 60/40 or 70/30 splits, not just 50/50
+├── Negative Space as an Object: Whitespace isn't just "gap", it's a structural element
+└── Z-Axis Depth: Layering typography behind or partially over imagery
+```
+
 ### Golden Ratio (φ = 1.618)
 
 ```
@@ -339,6 +352,9 @@ For animation patterns: [animation-guide.md](animation-guide.md), for advanced:
 - **Mesh Gradients & Glow Effects**
 - **Same layout structure / Vercel clone**
 - **Not asking user preferences**
+- **Emojis for UI icons (BANNED: Use lucide-react/SVGs ✅)**
+- **Tailwind Defaults**: Using `rounded-md`, `shadow-md`, `text-blue-500` without custom configuration.
+- **Static Dead Zones**: Interfaces with zero micro-interactions. Inject "whimsy" (subtle scale, transform, or opacity shifts on interaction).
 
 ### ❌ Dark Patterns (Unethical)
 
@@ -416,3 +432,63 @@ After implementing your design, run the audit:
 ---
 
 > **Remember:** Design is THINKING, not copying. Every project deserves fresh consideration based on its unique context and users. **Avoid the Modern SaaS Safe Harbor!**
+
+---
+
+## Output Format
+
+When this skill produces a recommendation or design decision, structure your output as:
+
+```
+━━━ Frontend Design Recommendation ━━━━━━━━━━━━━━━━
+Decision:    [what was chosen / proposed]
+Rationale:   [why — one concise line]
+Trade-offs:  [what is consciously accepted]
+Next action: [concrete next step for the user]
+─────────────────────────────────────────────────
+Pre-Flight:  ✅ All checks passed
+             or ❌ [blocking item that must be resolved first]
+```
+
+
+
+---
+
+## 🤖 LLM-Specific Traps
+
+AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+
+1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
+2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
+3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
+4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
+
+---
+
+## 🏛️ Tribunal Integration (Anti-Hallucination)
+
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
+
+### ❌ Forbidden AI Tropes
+
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+
+### ✅ Pre-Flight Self-Audit
+
+Review these questions before confirming output:
+```
+✅ Did I rely ONLY on real, verified tools and methods?
+✅ Is this solution appropriately scoped to the user's constraints?
+✅ Did I handle potential failure modes and edge cases?
+✅ Have I avoided generic boilerplate that doesn't add value?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/frontend-design/color-system.md

@@ -146,6 +146,23 @@ Lightness (0-100%): Brightness
   100% = White
 ```
 
+### Advanced: OKLCH Color Space (Pro Max Level)
+
+Whenever possible in modern CSS, abandon HSL for **OKLCH**.
+```
+Perceptual Uniformity: OKLCH gradients don't pass through "muddy" zones like RGB/HSL
+Chroma over Saturation: `c` (chroma) allows for impossibly vibrant display P3 colors
+Syntax: `oklch(70% 0.1 250)` reads as Lightness, Chroma, Hue
+```
+
+### Tactile Textures (Grain & Noise)
+
+Flat hex fills feel cheap. Premium aesthetic uses texture:
+```
+SVG Noise: Overlay a 2-4% opacity SVG noise filter on dark backgrounds
+Vignettes: Combine subtle noise with a radial gradient to draw the eye centrally
+```
+
 ### Generating a Full Palette
 
 Given ANY base color, create a scale:
@@ -293,6 +310,7 @@ Before finalizing any color choice, verify:
 - Copy the same hex codes every project
 - Default to purple/violet (AI tendency)
 - Default to dark mode + neon (AI tendency)
+- Generic "Stripe Blur" or arbitrary Aurora blobs without spatial purpose
 - Use pure black (#000000) backgrounds
 - Use pure white (#FFFFFF) text on dark
 - Ignore user's industry context

package/.agent/skills/frontend-design/typography-system.md

@@ -94,6 +94,15 @@ When pairing, compare:
 | Neutral sans | Same sans | Minimal, tech |
 | Bold geometric | Light geometric | Contemporary |
 
+### Pro Max Pairing: Extreme Contrast
+
+The highest tier of design deliberately creates aesthetic tension:
+```
+Hyper-Traditional + Brutalist: e.g., Garamond (Display) + Inter (Tiny, uppercase tracking)
+Ultra-Condensed + Ultra-Wide: Mixing opposite widths for structural brutalism
+Variable Font Axis Tuning: Don't just use `font-weight`. Adjust `font-stretch`, `slnt`, or custom axes dynamically based on viewport.
+```
+
 ### Avoid
 
 - ❌ Two decorative fonts together
@@ -317,6 +326,15 @@ Users scan in F-pattern:
 - High contrast = less strain
 - Consistent patterns = predictable
 
+### Kinetic Typography (Motion)
+
+Static type is baseline. Pro Max interfaces animate type:
+```
+Split-Text Staggering: Animating words or characters individually on scroll entry
+Weight Shifting: Variable fonts shifting smoothly from `wght` 300 to 800 on hover
+Masking: Text revealing itself from behind invisible overflow masks
+```
+
 ---
 
 ## 10. Typography Selection Checklist

package/.agent/skills/game-development/SKILL.md

@@ -2,6 +2,9 @@
 name: game-development
 description: Game development orchestrator. Routes to platform-specific skills based on project needs.
 allowed-tools: Read, Write, Edit, Glob, Grep, Bash
+version: 1.0.0
+last-updated: 2026-03-12
+applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
 ---
 
 # Game Development
@@ -165,3 +168,69 @@ Abstract input into ACTIONS, not raw keys:
 ---
 
 > **Remember:** Great games come from iteration, not perfection. Prototype fast, then polish.
+
+---
+
+## Output Format
+
+When this skill produces or reviews code, structure your output as follows:
+
+```
+━━━ Game Development Report ━━━━━━━━━━━━━━━━━━━━━━━━
+Skill:       Game Development
+Language:    [detected language / framework]
+Scope:       [N files · N functions]
+─────────────────────────────────────────────────
+✅ Passed:   [checks that passed, or "All clean"]
+⚠️  Warnings: [non-blocking issues, or "None"]
+❌ Blocked:  [blocking issues requiring fix, or "None"]
+─────────────────────────────────────────────────
+VBC status:  PENDING → VERIFIED
+Evidence:    [test output / lint pass / compile success]
+```
+
+**VBC (Verification-Before-Completion) is mandatory.**
+Do not mark status as VERIFIED until concrete terminal evidence is provided.
+
+
+
+---
+
+## 🤖 LLM-Specific Traps
+
+AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+
+1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
+2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
+3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
+4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
+
+---
+
+## 🏛️ Tribunal Integration (Anti-Hallucination)
+
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
+
+### ❌ Forbidden AI Tropes
+
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+
+### ✅ Pre-Flight Self-Audit
+
+Review these questions before confirming output:
+```
+✅ Did I rely ONLY on real, verified tools and methods?
+✅ Is this solution appropriately scoped to the user's constraints?
+✅ Did I handle potential failure modes and edge cases?
+✅ Have I avoided generic boilerplate that doesn't add value?
+```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.

package/.agent/skills/geo-fundamentals/SKILL.md

@@ -1,156 +1,215 @@
 ---
 name: geo-fundamentals
 description: Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
-allowed-tools: Read, Glob, Grep
+allowed-tools: Read, Write, Edit, Glob, Grep
+version: 1.0.0
+last-updated: 2026-03-12
+applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
 ---
 
-# GEO Fundamentals
+# Generative Engine Optimization (GEO)
 
-> Optimization for AI-powered search engines.
+> Traditional SEO optimizes for keyword ranking in blue links.
+> GEO optimizes for citation and inclusion in AI-generated answers.
 
 ---
 
-## 1. What is GEO?
+## What GEO Is
 
-**GEO** = Generative Engine Optimization
+When users ask ChatGPT, Claude, Perplexity, or Google SGE a question, an AI synthesizes an answer from sources it considers authoritative. GEO is the practice of making your content the kind that AI systems cite, quote, and summarize.
 
-| Goal | Platform |
-|------|----------|
-| Be cited in AI responses | ChatGPT, Claude, Perplexity, Gemini |
+The mechanisms differ from traditional SEO:
+- AI doesn't rank URLs — it synthesizes information
+- Backlinks matter less than citation-worthiness
+- Content density and factual specificity matter more than keyword density
 
-### SEO vs GEO
+---
+
+## How AI Systems Select Content to Cite
 
-| Aspect | SEO | GEO |
-|--------|-----|-----|
-| Goal | #1 ranking | AI citations |
-| Platform | Google | AI engines |
-| Metrics | Rankings, CTR | Citation rate |
-| Focus | Keywords | Entities, data |
+Based on observable patterns in AI retrieval:
+
+| Signal | What It Means |
+|---|---|
+| Authoritative domain | .gov, .edu, established publications get higher base trust |
+| Factual specificity | Numbers, dates, named sources > vague descriptions |
+| Structured content | Lists, tables, step-by-step = easier to extract |
+| Complete answers | Content that fully addresses the question in one place |
+| Original research | Data, studies, surveys the AI can't find elsewhere |
+| Freshness | Recently updated content has advantage for time-sensitive topics |
 
 ---
 
-## 2. AI Engine Landscape
+## Writing for AI Consumption
 
-| Engine | Citation Style | Opportunity |
-|--------|----------------|-------------|
-| **Perplexity** | Numbered [1][2] | Highest citation rate |
-| **ChatGPT** | Inline/footnotes | Custom GPTs |
-| **Claude** | Contextual | Long-form content |
-| **Gemini** | Sources section | SEO crossover |
+### Answer First (Inverted Pyramid)
 
----
+AI models extract answers. Put the answer at the top of the content, not after a 300-word preamble.
+
+```
+❌ Old blog pattern:
+   [intro paragraph explaining what the article is about]
+   [background context]
+   [finally... the answer in paragraph 5]
+
+✅ GEO pattern:
+   [Direct answer in first 1–2 sentences]
+   [Supporting evidence, data, explanation]
+   [Deeper context for readers who want more]
+```
+
+### Use Citation-Ready Structures
+
+```markdown
+# Format that AI can easily extract:
 
-## 3. RAG Retrieval Factors
+## Definition
+[Term] is [concise definition]. [Supporting context].
 
-How AI engines select content to cite:
+## Key Facts
+- [Specific, numbered fact with source]
+- [Specific statistic — "X% of Y according to Z study"]
+- [Named, verifiable claim]
 
-| Factor | Weight |
-|--------|--------|
-| Semantic relevance | ~40% |
-| Keyword match | ~20% |
-| Authority signals | ~15% |
-| Freshness | ~10% |
-| Source diversity | ~15% |
+## Step-by-Step Process
+1. [Precise step]
+2. [Precise step]
+3. [Precise step]
+```
+
+### Be Specific with Data
+
+```
+❌ "Many developers prefer TypeScript"
+✅ "In the 2024 Stack Overflow Developer Survey, 64% of respondents said they used TypeScript"
+
+❌ "Deployment takes some time"  
+✅ "Vercel cold-start latency for serverless functions averages 200–400ms for Node.js 20 runtimes"
+```
 
 ---
 
-## 4. Content That Gets Cited
+## Content Formats AI Favors
 
-| Element | Why It Works |
-|---------|--------------|
-| **Original statistics** | Unique, citable data |
-| **Expert quotes** | Authority transfer |
-| **Clear definitions** | Easy to extract |
-| **Step-by-step guides** | Actionable value |
-| **Comparison tables** | Structured info |
-| **FAQ sections** | Direct answers |
+| Format | GEO Value | Why |
+|---|---|---|
+| FAQ pages | High | Matches question-answer format of AI responses |
+| Comparison tables | High | Easily extracted for comparison queries |
+| How-to guides with numbered steps | High | Directly answerable procedural questions |
+| Definition/explanation articles | High | Definitional queries are common AI use cases |
+| Long-form opinion pieces | Low | Hard to extract a clear answer from |
+| News articles | Medium | Good for recency, lower for evergreen queries |
 
 ---
 
-## 5. GEO Content Checklist
+## Technical Requirements for AI Indexing
+
+```html
+<!-- Ensure Perplexity and other AI crawlers can access your content -->
+<!-- Check robots.txt — don't accidentally block AI crawlers -->
+
+# robots.txt — allow AI crawlers
+User-agent: PerplexityBot
+Allow: /
+
+User-agent: ChatGPT-User
+Allow: /
+
+User-agent: ClaudeBot
+Allow: /
+
+<!-- Structured data helps AI understand content context -->
+<script type="application/ld+json">
+{
+  "@context": "https://schema.org",
+  "@type": "FAQPage",
+  "mainEntity": [{
+    "@type": "Question",
+    "name": "What is tribunal-kit?",
+    "acceptedAnswer": {
+      "@type": "Answer",
+      "text": "tribunal-kit is an npm package that installs an anti-hallucination agent kit..."
+    }
+  }]
+}
+</script>
+```
 
-### Content Elements
+---
 
-- [ ] Question-based titles
-- [ ] Summary/TL;DR at top
-- [ ] Original data with sources
-- [ ] Expert quotes (name, title)
-- [ ] FAQ section (3-5 Q&A)
-- [ ] Clear definitions
-- [ ] "Last updated" timestamp
-- [ ] Author with credentials
+## Metrics for GEO
 
-### Technical Elements
+Traditional SEO metrics (keyword rank, backlinks) don't fully apply. Track:
 
-- [ ] Article schema with dates
-- [ ] Person schema for author
-- [ ] FAQPage schema
-- [ ] Fast loading (< 2.5s)
-- [ ] Clean HTML structure
+- **AI mention rate** — manually query AI systems for your topic and check if your brand/content appears
+- **Citation count** — if identifiable quotes from your content appear in AI outputs
+- **Perplexity source appearances** — Perplexity shows its sources; track mentions
+- **Direct traffic** — users who find AI mentions and navigate directly (not via search)
 
 ---
 
-## 6. Entity Building
+## Scripts
 
-| Action | Purpose |
-|--------|---------|
-| Google Knowledge Panel | Entity recognition |
-| Wikipedia (if notable) | Authority source |
-| Consistent info across web | Entity consolidation |
-| Industry mentions | Authority signals |
+| Script | Purpose | Run With |
+|---|---|---|
+| `scripts/geo_checker.py` | Audits content for GEO best practices | `python scripts/geo_checker.py <url>` |
 
 ---
 
-## 7. AI Crawler Access
+## Output Format
 
-### Key AI User-Agents
+When this skill produces a recommendation or design decision, structure your output as:
 
-| Crawler | Engine |
-|---------|--------|
-| GPTBot | ChatGPT/OpenAI |
-| Claude-Web | Claude |
-| PerplexityBot | Perplexity |
-| Googlebot | Gemini (shared) |
+```
+━━━ Geo Fundamentals Recommendation ━━━━━━━━━━━━━━━━
+Decision:    [what was chosen / proposed]
+Rationale:   [why — one concise line]
+Trade-offs:  [what is consciously accepted]
+Next action: [concrete next step for the user]
+─────────────────────────────────────────────────
+Pre-Flight:  ✅ All checks passed
+             or ❌ [blocking item that must be resolved first]
+```
 
-### Access Decision
 
-| Strategy | When |
-|----------|------|
-| Allow all | Want AI citations |
-| Block GPTBot | Don't want OpenAI training |
-| Selective | Allow some, block others |
 
 ---
 
-## 8. Measurement
+## 🤖 LLM-Specific Traps
 
-| Metric | How to Track |
-|--------|--------------|
-| AI citations | Manual monitoring |
-| "According to [Brand]" mentions | Search in AI |
-| Competitor citations | Compare share |
-| AI-referred traffic | UTM parameters |
+AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+
+1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
+2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
+3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
+4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
+5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
 
 ---
 
-## 9. Anti-Patterns
+## 🏛️ Tribunal Integration (Anti-Hallucination)
 
-| ❌ Don't | ✅ Do |
-|----------|-------|
-| Publish without dates | Add timestamps |
-| Vague attributions | Name sources |
-| Skip author info | Show credentials |
-| Thin content | Comprehensive coverage |
+**Slash command: `/review` or `/tribunal-full`**
+**Active reviewers: `logic-reviewer` · `security-auditor`**
 
----
+### ❌ Forbidden AI Tropes
 
-> **Remember:** AI cites content that's clear, authoritative, and easy to extract. Be the best answer.
+1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
+2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
+3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
 
----
+### ✅ Pre-Flight Self-Audit
 
-## Script
+Review these questions before confirming output:
+```
+✅ Did I rely ONLY on real, verified tools and methods?
+✅ Is this solution appropriately scoped to the user's constraints?
+✅ Did I handle potential failure modes and edge cases?
+✅ Have I avoided generic boilerplate that doesn't add value?
+```
 
-| Script | Purpose | Command |
-|--------|---------|---------|
-| `scripts/geo_checker.py` | GEO audit (AI citation readiness) | `python scripts/geo_checker.py <project_path>` |
+### 🛑 Verification-Before-Completion (VBC) Protocol
 
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.