tribunal-kit 5.8.4 → 6.0.0

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

@@ -1,250 +1,112 @@
 ---
 name: frontend-design
-description: Design thinking for web UI. Micro-interactions, visual hierarchy, typography scaling, HSL color palettes, spacing systems, and CSS-first UI logic. Avoid generic AI aesthetics.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.1.0
-last-updated: 2026-04-06
-applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+description: Design engineering principles for React/Next.js. Relative color syntax (OKLCH), spatial grid math, fluid container queries, and contrast validation.
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - baseline-ui
+  - better-colors
+  - better-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
-# Frontend Design — Dense Reference
-
-## Hallucination Traps (Read First)
-
-- ❌ Purple gradient backgrounds (`from-purple-500 to-blue-500`) → ✅ The worst AI UI cliché. Use high-contrast solid colors, grain, or sophisticated HSL mono-palettes.
-- ❌ Hardcoded pixels (`font-size: 14px`) → ✅ Use `rem` for accessibility and scaling (`1rem = 16px`).
-- ❌ Gray text (`#888`) on white → ✅ Fails WCAG contrast. Text must be `4.5:1` ratio.
-- ❌ Generic sans-serif → ✅ Inter, Geist, Roboto Mono, or system-ui. Typography is 80% of design.
-- ❌ "Bento Box" grids for everything → ✅ Overused pattern. Use directional flow or asymmetric layouts.
-- ❌ Symmetrical layouts out of laziness → ✅ Tension and blank space (negative space) drive premium feel.
-- ❌ Infinite scrolling without context → ✅ Provide clear footers or logical pagination markers.
-- ❌ Over-animating everything (`all elements fade in`) → ✅ Animate state changes (hover, focus, submit), not static entry layout unless scrollytelling.
+# Frontend Design — Technical Spacing & Color Science
 
 ---
 
-## 1. Color Theory (HSL over HEX)
-
-Never use raw flat HEX colors. Use HSL to build cohesive scales.
+## Mandatory Pre-Flight Context Inspection
 
-```css
-:root {
-  /* HSL allows programmatic adjustment of lightness/saturation */
-  --hue: 220;
-  --sat: 80%;
+Before implementing front-end designs or CSS layout systems, you MUST inspect:
+1. Relative Color Syntax (Section 16) → Derive hover/active states dynamically with `oklch(from var(--color-primary) calc(l - 0.08) c h)`
+2. Nested Radius Math (Section 54) → Enforce `outer_radius = inner_radius + padding_inner` for nested card containers
+3. APCA Contrast Thresholds (Section 81) → Ensure Lc > 75 for body text, Lc > 60 for headings, and Lc > 45 for borders and labels
 
-  --bg-base: hsl(var(--hue), 15%, 98%);
-  --bg-surface: hsl(var(--hue), 20%, 100%);
+This skill guides the implementation of responsive layout systems, color science, and spatial tokens.
 
-  --text-main: hsl(var(--hue), 40%, 10%);
-  --text-muted: hsl(var(--hue), 20%, 40%);
-
-  --primary: hsl(var(--hue), var(--sat), 50%);
-  --primary-hover: hsl(var(--hue), var(--sat), 40%); /* Darken via L */
-}
-
-/* OLED Dark Mode */
-@media (prefers-color-scheme: dark) {
-  :root {
-    --bg-base: hsl(var(--hue), 10%, 2%);
-    --bg-surface: hsl(var(--hue), 10%, 6%);
-    --text-main: hsl(var(--hue), 20%, 95%);
-    --text-muted: hsl(var(--hue), 10%, 60%);
-  }
-}
-```
-
-## 2. Spatial Systems & Grid Mathematics
-
-Design relies on structural rhythm. Use an **8px base system**.
+---
 
-- **Micro padding**: `4px`, `8px` (Tags, List items)
-- **Component padding**: `16px`, `24px` (Cards, Inputs, Modals)
-- **Section spacing**: `48px`, `64px`, `96px` (Page sections)
-- **Line height**: Body `1.5`, Headings `1.1` or `1.2`.
+## 1. Relative Color Syntax & OKLCH Theme Tokens
 
+Perceptually uniform color science ensures stable contrast. Use CSS **Relative Color Syntax** to derive state colors dynamically:
 ```css
-/* Fluid Typography (Clamp) */
-h1 {
-  /* Min 2rem, fluidly scale between 480px-1200px, Max 4rem */
-  font-size: clamp(2rem, 5vw, 4rem);
-  letter-spacing: -0.02em; /* Tighten large text */
+:root {
+  /* base color values */
+  --color-primary: oklch(62% 0.21 250);       /* Brand electric blue */
+  
+  /* Deriving hover states dynamically: reduce lightness, preserve chroma and hue */
+  --color-primary-hover: oklch(from var(--color-primary) calc(l - 0.08) c h);
+  --color-primary-active: oklch(from var(--color-primary) calc(l - 0.12) c h);
+  
+  /* Backgrounds */
+  --bg-surface: oklch(100% 0 0);
+  --text-main: oklch(20% 0.02 250);
 }
 
-p {
-  font-size: 1rem;
-  max-width: 65ch; /* Optimal reading length */
+[data-theme="dark"] {
+  --bg-surface: oklch(14% 0.008 250);
+  --text-main: oklch(93% 0.003 250);
 }
 ```
 
 ---
 
-## 3. Interaction & "Juice" (Micro-interactions)
-
-A premium UI reacts to the user instantly and smoothly. Focus on state transitions.
+## 2. Spatial Grid Math & Radius Tokens
 
+Enforce an 8px spatial grid calculated mathematically to ensure alignment precision:
 ```css
-/* Smooth generic transition */
-.btn {
-  transition: all 0.2s cubic-bezier(0.25, 0.46, 0.45, 0.94);
-}
-
-/* Active Depth - The physical button push */
-.btn:active {
-  transform: scale(0.97);
-}
-
-/* Hardware-Accelerated Shadows */
-.card {
-  box-shadow:
-    0 4px 6px -1px rgba(0, 0, 0, 0.1),
-    0 2px 4px -1px rgba(0, 0, 0, 0.06);
-  transition:
-    transform 0.3s ease,
-    box-shadow 0.3s ease;
-}
-.card:hover {
-  transform: translateY(-4px); /* Float effect */
-  box-shadow:
-    0 20px 25px -5px rgba(0, 0, 0, 0.1),
-    0 10px 10px -5px rgba(0, 0, 0, 0.04);
+:root {
+  --base-grid: 8px;
+  
+  --space-xs:  calc(var(--base-grid) * 0.5);  /* 4px  - icon gaps */
+  --space-sm:  calc(var(--base-grid) * 1);    /* 8px  - tag paddings */
+  --space-md:  calc(var(--base-grid) * 2);    /* 16px - inputs */
+  --space-lg:  calc(var(--base-grid) * 3);    /* 24px - card padding */
+  --space-xl:  calc(var(--base-grid) * 4);    /* 32px - section gaps */
 }
 ```
 
----
+### Nested Radius Formula
+Ensure component inner borders track correctly:
+`outer_radius = inner_radius + padding_inner`
+If container padding is `16px` and inner content radius is `8px`, then container outer radius must be exactly `24px` (`8px + 16px`).
 
-## 4. Modern Glassmorphism & Depth
+---
 
-Flat design is dead. Modern UI uses depth, layering, and blur.
+## 3. Responsive Layouts & Container Queries
 
+Avoid viewport-level media queries for self-contained components. Use container queries to make components portable:
 ```css
-/* Frosted Glass */
-.glass {
-  background: rgba(255, 255, 255, 0.7);
-  backdrop-filter: blur(16px);
-  -webkit-backdrop-filter: blur(16px);
-  border: 1px solid rgba(255, 255, 255, 0.2);
-  border-radius: 16px;
+.component-wrapper {
+  container-type: inline-size;
+  container-name: component;
 }
-```
 
----
-
-## 5. Forms and High-Friction UI
-
-Forms are where users drop off. They must be flawless.
-
-- **Auto-focus** the first input on modal open.
-- **Labels** must be visible outside the input (not just placeholders).
-- **Validation** happens `onBlur` (when leaving), NOT `onChange` (typing).
-- **Submit buttons** show loading spinners, disable inputs, and prevent double-clicks.
-
-```css
-/* Focus-visible: Only show ring for keyboard nav, not mouse clicks */
-button:focus-visible {
-  outline: 2px solid var(--primary);
-  outline-offset: 2px;
+@container component (min-width: 450px) {
+  .inner-layout {
+    display: grid;
+    grid-template-columns: repeat(2, 1fr);
+    gap: var(--space-md);
+  }
 }
 ```
 
 ---
 
-## 6. Accessibility (WCAG 2.2 AA)
-
-Design is fundamentally broken if it excludes users.
-
-- ✅ Interactive elements need `aria-label` if not visually labeled.
-- ✅ Custom dropdowns/selects must support Arrow Keys and Escape.
-- ✅ Color alone cannot convey state (Error text must have an icon too `❌ Password invalid`).
-- ✅ Hide decorative SVG/icons from screen readers `aria-hidden="true"`.
-
----
-
-AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
+## 4. APCA Contrast Guidelines
 
-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.
+Ensure that typography meets the APCA Lc guidelines:
+*   Lc > 75 for body text elements.
+*   Lc > 60 for large titles and headings.
+*   Lc > 45 for secondary input labels and border guides.
 
 ---
 
-**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.
-
-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.
-
 ## Pre-Flight Checklist
-
 - [ ] Have I reviewed the user's specific constraints and requests?
 - [ ] Have I checked the environment for relevant existing implementations?
 
 ## VBC Protocol (Verification-Before-Completion)
-
 You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
-
----
-
-## 🤖 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-security-expert/SKILL.md

@@ -1,17 +1,31 @@
 ---
 name: frontend-security-expert
 description: Frontend security auditing for modern meta-frameworks. Focuses on React/Next.js UI paradigms, hydration poisoning, third-party script supply chain, local storage security, and XSS prevention in modern environments.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-05-22
-applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - backend-security-expert
+  - api-security-auditor
+  - vulnerability-scanner
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Frontend Security Expert — Modern Meta-Frameworks
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before auditing or writing client-side code, you MUST inspect:
+1. XSS Sanitize Rules (Section 28) → Require DOMPurify for any `dangerouslySetInnerHTML` and audit dynamic `javascript:` URIs
+2. HttpOnly Auth Token Storage (Section 34) → Ban storing JWTs or auth tokens in `localStorage` or `sessionStorage`; use `HttpOnly`, `Secure`, `SameSite` cookies
+3. PostMessage Origin Verification (Section 46) → Never use `targetOrigin: '*'` and always validate `event.origin` on receiving handlers
+
+# Frontend Security Expert — Modern Meta-Frameworks
+
 ## Hallucination Traps (Read First)
 
 - ❌ Focusing on generic OWASP top 10 (SQLi, IDOR) → ✅ This is the _frontend_ skill. Focus strictly on client-side boundaries, SSR hydration, and DOM.

package/.agent/skills/game-design-expert/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: game-design-expert
 description: Game Design, UX, and Flow State mastery. Replaces fragmented legacy skills. Core gameplay loop design, 3Cs (Character, Camera, Controls), input buffering, coyote time, juice (game feel), telemetry tracking, narrative alignment, and audio spatialization integration. Use when crafting player experience, progression arcs, or systemic balance.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-02
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - game-engineering-expert
+  - 12-principles-of-animation
+  - sounds-on-the-web
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Game Design Expert — Player Experience & Flow Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before designing gameplay systems or controller feel, you MUST inspect:
+1. 3Cs Foundation (Character, Camera, Controls) (Section 25) → Implement input buffering (~150ms) and coyote time (~100ms) before designing enemy AI or progression
+2. Macro Gameplay Loop Validation (Section 42) → Ensure upgrading systems directly alter action and combat feel to prevent player churn
+3. Juicing & Hitstop Feel (Section 58) → Incorporate screen shake, hitstop (3 freeze frames), particle explosions, and squash-and-stretch for impact feedback
+
 ## Hallucination Traps (Read First)
 
 - ❌ Designing reward systems without testing for compulsion loops -> ✅ Playtesting must verify engagement without addiction patterns

package/.agent/skills/game-engineering-expert/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: game-engineering-expert
 description: Game Engineering and Systems Architecture mastery. Replaces fragmented legacy skills. Entity Component Systems (ECS), Unity (C#) / Godot (GDScript) integration, physics calculations, deterministic engine state, WebGL memory management, multiplayer sync architectures (deterministic lockstep vs traditional authoritative), spatial partitioning, and rendering pipelines.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-02
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - game-design-expert
+  - csharp-developer
+  - 60fps-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Game Engineering Expert — Performance & State Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering game state loops or physics engines, you MUST inspect:
+1. Clamped DeltaTime Rule (Section 25) → Clamp `deltaTime` (max 0.05s) to prevent physics explosions on frame rate drops
+2. Garbage Collection & Object Pooling (Section 50) → Pre-allocate and pool game objects; ban `Instantiate()` or dynamic memory allocations in frame update loops
+3. FixedUpdate vs Update Separation (Section 43) → Put all physics logic in `FixedUpdate()`; use `Update()` strictly for visual interpolation and input collection
+
 ## Hallucination Traps (Read First)
 
 - ❌ Using deltaTime without clamping -> ✅ Unclamped deltaTime causes physics explosions on frame spikes; clamp to max 0.05s

package/.agent/skills/generative-ui-expert/SKILL.md

@@ -1,13 +1,29 @@
 ---
 name: generative-ui-expert
 description: Generative UI mastery. Vercel AI SDK 3.0+, React Server Components (RSC) + LLMs, streaming UI elements, structured tool calling (Zod schemas), and managing client-side AI state via useChat/useObject.
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - nextjs-react-expert
+  - react-specialist
+  - browser-native-ai
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Generative UI Expert (Vercel AI SDK)
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing Generative UI streaming pipelines, you MUST inspect:
+1. Tool Parameter Schemas (Section 87) → Validate all LLM tool parameters with Zod schemas
+2. RSC Server Action Boundaries (Section 33) → Annotate server actions with `"use server"` and yield Server Components directly from `streamUI`
+3. Intermediate Skeleton Yielding (Section 80) → Always `yield <SkeletonLoader />` before awaiting async APIs or external LLM tool calls
+
 You are the definitive expert in Generative UI using the Vercel AI SDK and React Server Components (RSC). Your goal is to move AI from spitting out "markdown walls of text" into rendering interactive, stateful, and dynamic UI components natively inside the chat or application stream.
 
 ## 1. Core Principles

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

@@ -1,15 +1,29 @@
 ---
 name: geo-fundamentals
 description: Generative Engine Optimization (GEO) mastery. Structuring content for LLM ingestion. Adapting SEO for AI interfaces (ChatGPT, Claude, Perplexity), optimizing markdown semantic hierarchies, citation structuring, minimizing boilerplate, reducing HTML DOM depth, and API-first content delivery. Use when making information discoverable not just to Google, but directly to AI indexing agents.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-02
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - seo-fundamentals
+  - browser-native-ai
+  - readme-builder
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Generative Engine Optimization (GEO)
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before optimizing content for AI engine ingestion, you MUST inspect:
+1. High Information Density Rule (Section 25) → Maximize factual density; eliminate marketing boilerplate so LLM context windows aren't truncated
+2. Explicit Claim-to-Source Mapping (Section 51) → Map stats and claims directly to explicit `<cite>` sources/links; ban vague unanchored assertions
+3. Text-Based Architecture Diagrams (Section 94) → Represent architecture via text/Mermaid.js code blocks; ban image-only architecture diagrams
+
 ## Hallucination Traps (Read First)
 
 - ❌ Assuming SEO and GEO are the same -> ✅ GEO optimizes for AI crawlers and LLM ingestion, not just search engine ranking

package/.agent/skills/git-pro/SKILL.md

@@ -1,18 +1,29 @@
 ---
 name: git-pro
 description: Industry-level Git & GitHub mastery. Advanced Git internals (bisect, worktrees, reflog), monorepo strategies (Turborepo/Nx), semantic-release, OIDC-based GitHub Actions auth (no static AWS secrets), CODEOWNERS, matrix builds, reusable workflows, and release engineering. Use when advanced Git operations, complex branching strategies, or production-grade CI/CD workflow authoring is required.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-06-21
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: devops
-  tier: pro
-  supersedes: github-operations
-  trigger-signals:
-    strong: [monorepo, bisect, reflog, OIDC, semantic-release, CODEOWNERS]
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - github-operations
+  - cicd-pro
+  - bash-linux
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Git Pro — Industry-Level Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before running complex Git operations or writing release workflows, you MUST inspect:
+1. Safe Force Push Rule (Section 18) → Use `--force-with-lease` exclusively; ban raw `git push --force` on shared/remote branches
+2. Reflog Recovery Strategy (Section 30) → Inspect `git reflog` to recover lost commits or bad resets before discarding uncommitted state
+3. OIDC Authentication Protocol (Section 208) → Configure OIDC AWS auth (`id-token: write`) in GitHub Actions workflows; ban static AWS access keys
+
 ## Hallucination Traps (Read First)
 
 - ❌ `git push --force` on shared branches → ✅ Always use `git push --force-with-lease` (fails if remote has new commits you haven't seen)

package/.agent/skills/github-operations/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: github-operations
 description: Git and GitHub workflow mastery. Branching strategies (Git Flow, trunk-based), commit message conventions, interactive rebase, merge conflict resolution, pull request best practices, GitHub Actions, branch protection rules, monorepo strategies, and git hooks. Use when working with Git, GitHub Actions, or any version control operations.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 2.0.0
-last-updated: 2026-04-01
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - git-pro
+  - cicd-pro
+  - bash-linux
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # GitHub Operations — Git & CI/CD Workflow Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before running Git commands or writing GitHub workflows, you MUST inspect:
+1. Local-Only Interactive Rebase (Section 172) → Perform interactive rebases (`git rebase -i`) ONLY on local unpushed commits; ban rebasing public/shared history
+2. Conventional Commit Standards (Section 55) → Format commit messages using Conventional Commits (`type(scope): description`) for automated changelogs
+3. Squash Merge Default (Section 146) → Enforce squash merge strategy for feature branches merging into main to keep history linear and clean
+
+# GitHub Operations — Git & CI/CD Workflow Mastery
+
+---
+
 ## Branching Strategy
 
 ### Trunk-Based Development (Recommended)

package/.agent/skills/gpt-taste/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: gpt-taste
 description: High-agency UX/UI skill with strict layout variance, typography, and GSAP motion engineering constraints for superior visual judgment.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: High-Agency Aesthetic Judgment
-  tier: pro
-  co-requires: [taste-skill, better-ui, frontend-design]
-  trigger-signals:
-    strong: [gpt-taste, high agency UI, visual refinement, layout variance, superior aesthetic judgment]
-    weak: [aesthetic UI, refined visual]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - taste-skill
+  - better-ui
+  - better-colors
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # GPT Taste — High-Agency Visual Refinement & Layout Variance
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before generating UI layouts or visual code, you MUST inspect:
+1. Structural Layout Variance (Section 24) → Vary structural layout across sections; ban uniform 3-card bento grids
+2. OKLCH Perceptual Palette (Section 30) → Declare all color tokens using OKLCH color space for perceptual uniformity
+3. Zero Truncation Rule (Section 39) → Strictly ban `// TODO: add remaining items` placeholder comments; generate complete production-ready code
+
 Inject high-agency visual judgment and layout variance into AI-generated interfaces.
 
 ---