tribunal-kit 5.8.5 → 6.0.0

package/.agent/skills/improve-ui/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: improve-ui
 description: Audit an existing product surface against its own design evidence, identify verified UI problems, and write self-contained implementation plans for another agent. Strictly read-only on product source. Use when asked to review, refine, improve, or clean up an interface without replacing its identity.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: UI Craft & Design Audit
-  tier: master
-  co-requires: [better-ui, baseline-ui]
-  trigger-signals:
-    strong: [improve-ui, audit interface, refine UI, UI review, design-system drift, UI cleanup plan]
-    weak: [review layout, UI feedback]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - better-ui
+  - baseline-ui
+  - create-design-md
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Improve UI — Evidence-Based UI Audit & Implementation Planning
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before auditing UI surfaces or writing remediation plans, you MUST inspect:
+1. Read-Only Constraint (Section 24) → Strictly NEVER modify product source code (`src/`, `components/`, `app/`) during an `improve-ui` audit session
+2. 3-Proof Requirement (Section 40) → Every reported defect MUST present Observation (code line/element), Basis (token/grid violation), and Consequence
+3. Plan Artifact Output (Section 25) → Write implementation plans to `design-plans/` or output structured markdown for execution
+
 Audit a specific product surface against its governing design tokens and guidelines, identify verified UI defects, and generate self-contained implementation plans for remediation.
 
 ---

package/.agent/skills/intelligent-routing/SKILL.md

@@ -1,15 +1,27 @@
 ---
 name: intelligent-routing
 description: LLM Intent Processing and Gateway Routing mastery. Request classification hierarchies, function routing, confidence scoring, fallback cascades, zero-shot vs few-shot classification patterns, and identifying specialized skills for delegation. Use when parsing raw user input to determine the architectural path of execution.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 4.0.0
-last-updated: 2026-06-21
-applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
-routing:
-  domain: meta
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - fabel-protocol
+  - agentic-patterns
+  - behavioral-modes
+scripts-binding:
+  - .agent/scripts/compile_router.py
+  - .agent/scripts/verify_all.js
 ---
 
+# Intelligent Routing v4 — Self-Describing Skill Graph
+
+## Mandatory Pre-Flight Context Inspection
+
+Before routing user prompts to specialized skills or agents, you MUST inspect:
+1. `.agent/routing_index.json` → Read pre-compiled skill index instead of loading full skill markdown files into context
+2. Semantic Intent Schema (Section 1) → Classify request type (QUESTION, SURVEY, SIMPLE_EDIT, COMPLEX_BUILD, SECURITY_AUDIT, UNCLEAR_GIBBERISH)
+3. Confidence Threshold (Section 3 Socratic Yield Rule) → Yield back to user with clarifying question if confidence score is < 85s
+
 ## Hallucination Traps (Read First)
 
 - ❌ Routing based on exact keyword matching -> ✅ Use intent classification with confidence scores; keywords miss synonyms and context

package/.agent/skills/knowledge-graph/SKILL.md

@@ -1,14 +1,30 @@
 ---
-name: Knowledge Graph Analyzer
+name: knowledge-graph
 description: Understands the architecture, risk blast radius, and dependencies of the codebase without token bloat. Now includes Context Snapshots for 27x token reduction.
 version: 3.0.0
-routing:
-  domain: general
-  tier: basic
+last-updated: 2026-07-30
+skills:
+  - codebase-design
+  - architecture
+  - fabel-protocol
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/graph_builder.js
+  - .agent/scripts/graph_zoom.js
+  - .agent/scripts/verify_all.js
 ---
 
 # /graph — Knowledge Graph Skill v3.0
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before inspecting codebase architecture, you MUST inspect:
+1. Context Snapshots (`.agent/history/snapshots/`) → Read pre-computed JSON snapshots to reduce token overhead by 27x
+2. `graph_builder.js` output → Check downstream dependencies, risk scores, and blast radius before modifying any file
+3. Module boundaries → Identify top imported symbols and high-risk core modules
+
 Use this skill when the user types `/graph` or when you need to deeply understand the architecture of an unfamiliar codebase without suffering from context-window bloat.
 
 ## The Token Reduction Protocol (Option C)

package/.agent/skills/landing-page/SKILL.md

@@ -1,20 +1,30 @@
 ---
 name: landing-page
 description: High-converting landing page structure, hero section layout variance, CTA hierarchy, visual pacing, feature grid storytelling, and social proof placement.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Landing Page Architecture & Conversion
-  tier: pro
-  co-requires: [compact-landing, company-logos, pricing-page, frontend-design]
-  trigger-signals:
-    strong: [landing-page, hero section, CTA hierarchy, conversion landing page, SaaS landing page, feature grid storytelling]
-    weak: [homepage design, marketing page]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - compact-landing
+  - company-logos
+  - pricing-page
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Landing Page — Conversion Architecture & Visual Pacing
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering full landing pages, you MUST inspect:
+1. Hero Layout Model (Section 50) → Choose appropriate layout variance model (Model A Centered Stacked, Model B Asymmetric Split, Model C Full-Bleed Canvas)
+2. CTA Hierarchy (Section 32) → Ensure exactly ONE primary solid accent button above the fold; pair only with a secondary ghost button
+3. Blueprint Rhythm (Section 22) → Follow the 6-section blueprint (Nav, Hero, Social Proof, Features, Testimonials, Final CTA)
+
 Build high-converting, visually stunning landing pages that guide visitors from curiosity to conversion.
 
 ---

package/.agent/skills/lint-and-validate/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: lint-and-validate
 description: Linting and validation principles for code quality enforcement.
-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
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - clean-code
+  - config-validator
+  - code-review-checklist
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Linting & Validation
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before running linting tools or modifying linter rules, you MUST inspect:
+1. Zero-Warning CI Blocking (Section 34) → Enforce zero-warning policy in CI pipelines; ban treating lint warnings as non-blocking
+2. Mandatory Strict Type Checks (Section 121) → Run static type checking (`tsc --noEmit` or `mypy`) alongside linters to catch non-linter type bugs
+3. Diff Review Before Auto-Fixing (Section 15) → Review diffs explicitly after auto-fixing (`eslint --fix`) to prevent accidental removal of side-effect code
+
 ## Hallucination Traps (Read First)
 
 - ❌ Auto-fixing lint errors without reviewing the diff -> ✅ Some auto-fixes change logic (e.g., removing 'unused' variables that are side-effects)

package/.agent/skills/llm-engineering/SKILL.md

@@ -1,19 +1,33 @@
 ---
 name: llm-engineering
 description: LLM engineering mastery for production AI systems. Prompt engineering, RAG pipeline design, vector store selection, embedding strategies, chunking, reranking, structured output, function calling, streaming, evals, guard-rails, cost optimization, and LLMOps. Use when building AI features, chat interfaces, semantic search, or any system calling an LLM API.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.2.0
-last-updated: 2026-04-07
-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:
+  - ai-prompt-injection-defense
+  - advanced-rag-pipelines
+  - data-validation-schemas
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # LLM Engineering — Production AI Systems Mastery
 
 ---
 
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering LLM integrations or tool calling loops, you MUST inspect:
+1. Zod Schema Validation on JSON Outputs (Section 115) → Always run Zod validation (`Schema.parse(...)`) on LLM JSON responses, even in strict mode
+2. Hybrid Vector + Keyword Search (Section 290) → Use hybrid vector + BM25 keyword search in RAG applications to prevent missing exact identifiers
+3. System Prompt Secret Isolation (Section 69) → Never put private API keys, database credentials, or secret internal URLs into system prompts
+
+# LLM Engineering — Production AI Systems Mastery
+
+---
+
 ## Model Selection
 
 ```

package/.agent/skills/local-first/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: local-first
 description: Local-first software architecture mastery. CRDTs (Conflict-free Replicated Data Types), IndexedDB synchronization, sync engines (ElectricSQL, Replicache, PowerSync), offline-capable data fetching, optimistic UI, and SQLite in the browser (WASM). Use when building PWA offline capabilities, rapid UIs, or multiplayer collaborative tools.
-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:
+  - local-first-architecture
+  - react-specialist
+  - baseline-ui
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Local-First Architecture — Offline-capable Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing local-first storage or CRDT synchronization, you MUST inspect:
+1. Conflict Resolution Strategy (Section 15) → Define explicit conflict resolution (LWW timestamps or Yjs CRDTs) before writing local sync logic
+2. Persistent Storage (Section 16) → Use IndexedDB (via Dexie/idb) or SQLite WASM for local persistence; ban localStorage for >5MB data
+3. Incremental Watermark Sync (Section 17) → Perform delta syncs using timestamps/watermarks rather than re-fetching full datasets
+
 ## Hallucination Traps (Read First)
 
 - ❌ Assuming server data is always newer than local data -> ✅ Conflicts are inevitable; design merge strategy (LWW, CRDTs) before writing code

package/.agent/skills/local-first-architecture/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: local-first-architecture
 description: Local-first architecture guidance for instant-feeling web & desktop apps, optimistic updates, IndexedDB sync engines, offline operation, and Conflict-free Replicated Data Types (CRDTs).
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Local-First Architecture & Sync Engines
-  tier: pro
-  co-requires: [local-first, realtime-patterns, architecture]
-  trigger-signals:
-    strong: [local-first-architecture, Linear architecture, optimistic updates, IndexedDB sync, CRDT, offline-first app, zero-latency UI]
-    weak: [offline sync, optimistic state]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - react-specialist
+  - nextjs-react-expert
+  - baseline-ui
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Local-First Architecture — Instant UI & Sync Engines
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing local-first architecture or offline sync engines, you MUST inspect:
+1. Zero Network Latency Rule (Section 24) → Execute reads and writes against local storage (IndexedDB/SQLite) first before queueing outbound sync
+2. Outbound Mutation Queue (Section 28) → Persist mutation logs in IndexedDB with client-generated UUID `idempotencyKey` fields
+3. Conflict Resolution Strategy (Section 33) → Use Last-Write-Wins (LWW) for simple fields or CRDTs (Yjs/Automerge) for collaborative state
+
 Architect software that reads and writes to local storage (SQLite/IndexedDB) first, ensuring instant zero-latency UI mutations with background server synchronization.
 
 ---

package/.agent/skills/lottie-animation/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: lottie-animation
 description: Lottie and dotLottie integration, playback control, hover/click triggers, runtime theming, and performance optimization for React/Vue/Web.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Vector Animation & Lottie Integration
-  tier: pro
-  co-requires: [60fps-animation, text-to-lottie]
-  trigger-signals:
-    strong: [lottie-animation, dotLottie, Lottie React, Lottie playback, vector animation JSON]
-    weak: [lottie, json animation]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - 60fps-animation
+  - motion-engineering
+  - micro-interaction
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Lottie Animation — dotLottie & Runtime Control
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before integrating Lottie animations, you MUST inspect:
+1. Asset Format (.lottie vs .json) → Prefer compressed `.lottie` (dotLottie) assets for 80% smaller bundle file sizes
+2. Playback Triggers (Section 34) → Bind playback to user hover/click or viewport intersection instead of aggressive continuous looping
+3. Package Manifest (`package.json`) → Verify `@dotlottie/react-player` or `lottie-web` library dependencies
+
 Integrate lightweight, vector-based Lottie animations with interactive trigger controls and runtime color theming.
 
 ---

package/.agent/skills/marquee-loop/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: marquee-loop
 description: Hardware-accelerated, seamless, continuous looping marquees for logo rows, testimonials, and announcements with pause-on-hover accessibility.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Ticker & Continuous Motion
-  tier: pro
-  co-requires: [60fps-animation, company-logos]
-  trigger-signals:
-    strong: [marquee-loop, marquee animation, continuous ticker, looping logo track, seamless marquee]
-    weak: [scrolling logos, ticker]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - 60fps-animation
+  - company-logos
+  - accessible-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Marquee Loop — Hardware-Accelerated Continuous Tickers
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing marquee loop tracks, you MUST inspect:
+1. DOM Structure (Section 24) → Duplicate item tracks MUST be rendered with `aria-hidden="true"` to prevent screen reader redundancy
+2. Hover Accessibility (Section 50) → Enforce `animation-play-state: paused` on `:hover` and `:focus-within`
+3. Reduced Motion Fallback (Section 61) → Collapse marquee into static wrapped flex grid when `prefers-reduced-motion: reduce` is active
+
 Build seamless 60fps infinite marquee tracks that pause on hover and respect accessibility settings.
 
 ---

package/.agent/skills/masked-reveal/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: masked-reveal
 description: CSS clip-path, SVG masking, and layered entrance reveals for images, hero banners, and text blocks.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Visual Masking & Entrance Motion
-  tier: pro
-  co-requires: [60fps-animation, framer-motion-expert]
-  trigger-signals:
-    strong: [masked-reveal, clip-path reveal, SVG mask animation, curtain reveal, text mask reveal]
-    weak: [mask effect, clip path animation]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - 60fps-animation
+  - framer-motion-expert
+  - motion-engineering
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Masked Reveal — Clip-Path & Layered Entrances
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing clip-path or SVG mask reveals, you MUST inspect:
+1. Target DOM elements → Enforce `overflow: hidden` on text line wrappers to prevent unmasked overflow artifacts
+2. `clip-path: inset()` syntax (Section 26) → Prefer CSS `clip-path` over heavy SVG masks for linear curtain wipes
+3. Transition Easing → Use custom ease-out curves (`cubic-bezier(0.16, 1, 0.3, 1)`) for smooth deceleration
+
 Create editorial, high-end visual reveals using CSS `clip-path` and SVG masks.
 
 ---

package/.agent/skills/mcp-builder/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: mcp-builder
 description: Model Context Protocol (MCP) server integration mastery. Building custom MCP servers, standardizing tool exposes, managing standardized communication between large language models and localized datasets, securing boundary contexts, and architecting resource schemas. Use when modifying, extending, or building custom toolsets for AI platforms relying on the MCP standard.
-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:
+  - backend-security-expert
+  - nodejs-best-practices
+  - agentic-patterns
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# MCP Builder — Context Protocol Mastery
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before architecting MCP tools or resource handlers, you MUST inspect:
+1. Strict Zod Input Validation (Section 45) → Enforce explicit JSON Schema parameter validation (Zod) for every tool exposed to the LLM
+2. Resource vs Tool Distinction (Section 68) → Use Resources for static read-only data (`file:///`, `db://schema`), Tools strictly for dynamic parameterized actions
+3. Output Payload Truncation Safeguard (Section 94) → Forcibly truncate large tool response outputs before returning payload to protect LLM context windows
+
 ## Hallucination Traps (Read First)
 
 - ❌ Exposing tools without input validation schemas -> ✅ Every MCP tool MUST have JSON Schema for parameters; the protocol requires it

package/.agent/skills/micro-interaction/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: micro-interaction
 description: Detailed UI motion guidance for hover and press feedback, toggles, checkboxes, toasts, drawers, modals, list transitions, and shared-element interactions.
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Micro-Interactions & Component Tactility
-  tier: pro
-  co-requires: [delight, emil-design-eng, better-ui]
-  trigger-signals:
-    strong: [micro-interaction, button press feedback, toggle motion, checkbox animation, toast entrance, drawer interaction]
-    weak: [interactive feedback, hover state animation]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - delight
+  - better-ui
+  - 60fps-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Micro-Interaction — Component Motion & Tactile Feedback
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before engineering component micro-interactions, you MUST inspect:
+1. Duration Caps → Keep interactive component feedback (press/hover/toggle) under 180ms
+2. Popover Origin Rules (Section 60) → Set `transform-origin` dynamically to match trigger button position
+3. SVG Path Draw-on (Section 48) → Use `stroke-dashoffset` transitions for checkboxes and toggle icons
+
 Craft responsive, physically grounded micro-interactions for everyday UI controls.
 
 ---

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

@@ -1,16 +1,31 @@
 ---
 name: mobile-design
 description: Mobile-first design for iOS, Android, Foldables, React Native, Flutter. Touch interaction, haptics, 120Hz performance, on-device AI, spatial UI, Reanimated 3. Use when building mobile UI, animations, or cross-platform apps.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.1.0
-last-updated: 2026-04-06
-routing:
-  domain: general
-  tier: basic
+tools: Read, Grep, Glob, Bash, Edit, Write
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - building-native-ui
+  - adapt
+  - 60fps-animation
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Mobile Design — Dense Reference
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before designing mobile interfaces or writing React Native code, you MUST inspect:
+1. Reanimated 3 & Worklet Rules (Section 47) → Execute animations on the UI thread using Reanimated 3 worklets; ban legacy `Animated.View`
+2. List Optimization (Section 32) → Use `@shopify/flash-list` with required `estimatedItemSize` instead of `ScrollView` or `FlatList`
+3. Safe Area Insets (Section 100) → Always wrap content with `useSafeAreaInsets()` to accommodate notch, dynamic island, and home indicators
+
+# Mobile Design — Dense Reference
+
 ## Hallucination Traps (Read First)
 
 - ❌ `Animated.View` for any animation → ✅ `Reanimated 3` worklets (Animated API is legacy, runs on JS thread)

package/.agent/skills/monorepo-management/SKILL.md

@@ -1,15 +1,29 @@
 ---
 name: monorepo-management
 description: Monorepo architecture and tooling mastery. Turborepo, Nx, pnpm workspaces, shared package design, task pipelines, dependency hoisting, change detection, versioning strategies (independent vs. fixed), shared TypeScript configs, internal packages, and CI optimization for monorepos. Use when setting up monorepos, managing shared code across apps, or optimizing build pipelines.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 1.0.0
-last-updated: 2026-04-17
-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:
+  - cicd-pro
+  - codebase-design
+  - lint-and-validate
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
+# Monorepo Management — Scaling Multi-Package Projects
+
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before organizing workspace packages or writing Turborepo/pnpm configs, you MUST inspect:
+1. Internal Package Protocol (Section 128) → Reference internal monorepo dependencies via `"workspace:*"` protocol and mark them `"private": true`
+2. Topological Task Dependencies (Section 146) → Define topological ordering (`"^build"`) in `turbo.json` to ensure dependencies build before consumers
+3. Domain-Focused Package Partitioning (Section 261) → Divide shared code into domain packages (`packages/ui`, `packages/db`, `packages/utils`); ban single monolithic `packages/shared` dumpsters
+
 ## Hallucination Traps (Read First)
 
 - ❌ Publishing internal packages to npm when they're meant to stay private -> ✅ Internal packages use `"private": true` and workspace protocol `"workspace:*"`

package/.agent/skills/morphing-icons/SKILL.md

@@ -1,20 +1,29 @@
 ---
 name: morphing-icons
 description: Build morphing SVG icon components that transition smoothly between states (Play <-> Pause, Hamburger Menu <-> Close X, Sun <-> Moon).
-version: 1.0.0
-last-updated: 2026-07-22
-applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
-routing:
-  domain: Interactive Vector Icons & State Morphing
-  tier: pro
-  co-requires: [svg-animation, micro-interaction]
-  trigger-signals:
-    strong: [morphing-icons, morphing SVG icon, menu to close icon, play to pause icon, animated icon morph]
-    weak: [icon transition, animated icon]
+version: 3.0.0
+last-updated: 2026-07-30
+skills:
+  - svg-animation
+  - micro-interaction
+  - 60fps-animation
+tools: Read, Grep, Glob, Bash, Edit, Write
+scripts-binding:
+  - .agent/scripts/lint_runner.js
+  - .agent/scripts/verify_all.js
 ---
 
 # Morphing Icons — Interactive State-Morphing Vector Icons
 
+---
+
+## Mandatory Pre-Flight Context Inspection
+
+Before implementing morphing icon components, you MUST inspect:
+1. Target states (e.g. Hamburger Menu <-> Close X, Play <-> Pause) → Verify matching SVG path point count and coordinate bounds
+2. Accessibility (Section 65) → Ensure `aria-label` updates dynamically alongside state changes
+3. Interpolation Curves → Use snappy ease-out curves (`cubic-bezier(0.16, 1, 0.3, 1)`) with duration $\le 200\text{ms}$
+
 Architect crisp, interactive SVG icon components that morph seamlessly between operational states.
 
 ---