tribunal-kit 4.0.0 → 4.2.0

package/.agent/skills/gsap-timeline/SKILL.md

@@ -0,0 +1,155 @@
+---
+name: gsap-timeline
+description: Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).
+license: MIT
+---
+
+# GSAP Timeline
+
+## When to Use This Skill
+
+Apply when building multi-step animations, coordinating several tweens in sequence or parallel, or when the user asks about timelines, sequencing, or keyframe-style animation in GSAP.
+
+**Related skills:** For single tweens and eases use **gsap-core**; for scroll-driven timelines use **gsap-scrolltrigger**; for React use **gsap-react**.
+
+## Creating a Timeline
+
+```javascript
+const tl = gsap.timeline();
+tl.to(".a", { x: 100, duration: 1 })
+  .to(".b", { y: 50, duration: 0.5 })
+  .to(".c", { opacity: 0, duration: 0.3 });
+```
+
+By default, tweens are **appended** one after another. Use the **position parameter** to place tweens at specific times or relative to other tweens.
+
+## Position Parameter
+
+Third argument (or position property in vars) controls placement:
+
+- **Absolute**: `1` — start at 1 second.
+- **Relative (default)**: `"+=0.5"` — 0.5s after end; `"-=0.2"` — 0.2s before end.
+- **Label**: `"labelName"` — at that label; `"labelName+=0.3"` — 0.3s after label.
+- **Placement**: `"<"` — start when recently-added animation starts; `">"` — start when recently-added animation ends (default); `"<0.2"` — 0.2s after recently-added animation start.
+
+Examples:
+
+```javascript
+tl.to(".a", { x: 100 }, 0);           // at 0
+tl.to(".b", { y: 50 }, "+=0.5");      // 0.5s after last end
+tl.to(".c", { opacity: 0 }, "<");     // same start as previous
+tl.to(".d", { scale: 2 }, "<0.2");    // 0.2s after previous start
+```
+
+## Timeline Defaults
+
+Pass defaults into the timeline so all child tweens inherit:
+
+```javascript
+const tl = gsap.timeline({ defaults: { duration: 0.5, ease: "power2.out" } });
+tl.to(".a", { x: 100 }).to(".b", { y: 50 }); // both use 0.5s and power2.out
+```
+
+## Timeline Options (constructor)
+
+- **paused: true** — create paused; call `.play()` to start.
+- **repeat**, **yoyo** — same as tweens; apply to whole timeline.
+- **onComplete**, **onStart**, **onUpdate** — timeline-level callbacks.
+- **defaults** — vars merged into every child tween.
+
+## Labels
+
+Add and use labels for readable, maintainable sequencing:
+
+```javascript
+tl.addLabel("intro", 0);
+tl.to(".a", { x: 100 }, "intro");
+tl.addLabel("outro", "+=0.5");
+tl.to(".b", { opacity: 0 }, "outro");
+tl.play("outro");  // start from "outro"
+tl.tweenFromTo("intro", "outro"); // pauses the timeline and returns a new Tween that animates the timeline's playhead from intro to outro with no ease.
+```
+
+## Nesting Timelines
+
+Timelines can contain other timelines.
+
+```javascript
+const master = gsap.timeline();
+const child = gsap.timeline();
+child.to(".a", { x: 100 }).to(".b", { y: 50 });
+master.add(child, 0);
+master.to(".c", { opacity: 0 }, "+=0.2");
+```
+
+## Controlling Playback
+
+- **tl.play()** / **tl.pause()**
+- **tl.reverse()** / **tl.progress(1)** then **tl.reverse()**
+- **tl.restart()** — from start.
+- **tl.time(2)** — seek to 2 seconds.
+- **tl.progress(0.5)** — seek to 50%.
+- **tl.kill()** — kill timeline and (by default) its children.
+
+## Official GSAP Best practices
+
+- ✅ Prefer timelines for sequencing
+- ✅ Use the **position parameter** (third argument) to place tweens at specific times or relative to labels.
+- ✅ Add **labels** with `addLabel()` for readable, maintainable sequencing.
+- ✅ Pass **defaults** into the timeline constructor so child tweens inherit duration, ease, etc.
+- ✅ Put ScrollTrigger on the timeline (or top-level tween), not on tweens inside a timeline.
+
+## Do Not
+
+- ❌ Chain animations with **delay** when a **timeline** can sequence them; prefer `gsap.timeline()` and the position parameter for multi-step animation.
+- ❌ Forget to pass **defaults** (e.g. `defaults: { duration: 0.5, ease: "power2.out" }`) when many child tweens share the same duration or ease.
+- ❌ Forget that **duration** on the timeline constructor is not the same as tween duration; timeline “duration” is determined by its children.
+- ❌ Nest animations that contain a ScrollTrigger; ScrollTriggers should only be on top-level Tweens/Timelines.
+
+---
+
+## 🏛️ 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.
+
+---
+
+## 🚨 LLM Trap Table
+
+|Pattern|What AI Does Wrong|What Is Actually Correct|
+|:---|:---|:---|
+|gsap-timeline|Position parameter as 2nd arg|Position parameter is the 3rd arg: tl.to(el, {x: 100}, "<")|
+|gsap-timeline|tl.add(gsap.to(...))|tl.to(...) (just chain the tween directly)|
+|gsap-timeline|Hardcoded delays (delay: 1)|Use position parameter (<, >, +=1) for relative timing|
+
+---
+
+## ✅ Pre-Flight Self-Audit
+
+Before producing any output, verify:
+```
+✅ Did I read the actual files before making claims about them?
+✅ Did I verify all method names against official GSAP documentation?
+✅ Did I add // VERIFY: on any uncertain API calls?
+✅ Are all imports from packages that actually exist in package.json?
+✅ Did I test my logic with edge cases (null, empty, 0, max)?
+✅ Did I avoid generating code for more than one module at a time?
+✅ Am I working from evidence, not assumption?
+```
+
+---
+
+## 🔁 VBC Protocol (Verify → Build → Confirm)
+
+```
+VERIFY:  Read the actual codebase before writing anything
+BUILD:   Generate the smallest meaningful unit of code
+CONFIRM: Verify the output is correct before presenting
+```

package/.agent/skills/gsap-utils/SKILL.md

@@ -0,0 +1,332 @@
+---
+name: gsap-utils
+description: Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.
+license: MIT
+---
+
+# gsap.utils
+
+## When to Use This Skill
+
+Apply when writing or reviewing code that uses **gsap.utils** for math, array/collection handling, unit parsing, or value mapping in animations (e.g. mapping scroll to a value, randomizing, snapping to a grid, or normalizing inputs).
+
+**Related skills:** Use with **gsap-core**, **gsap-timeline**, and **gsap-scrolltrigger** when building animations; CustomEase and other easing utilities are in **gsap-plugins**.
+
+## Overview
+
+**gsap.utils** provides pure helpers; no need to register. Use in tween vars (e.g. function-based values), in ScrollTrigger or Observer callbacks, or in any JS that drives GSAP. All are on **gsap.utils** (e.g. `gsap.utils.clamp()`).
+
+**Omitting the value: function form.** Many utils accept the value to transform as the **last** argument. If you omit that argument, the util returns a **function** that accepts the value later. Use the function form when you need to clamp, map, normalize, or snap many values with the same config (e.g. in a mousemove handler or tween callback). **Exception: random()** — pass **true** as the last argument to get a reusable function (do not omit the value); see [random()](https://gsap.com/docs/v3/GSAP/UtilityMethods/random()).
+
+```javascript
+// With value: returns the result
+gsap.utils.clamp(0, 100, 150); // 100
+
+// Without value: returns a function you call with the value later
+let c = gsap.utils.clamp(0, 100);
+c(150);  // 100
+c(-10);  // 0
+```
+
+## Clamping and Ranges
+
+### clamp(min, max, value?)
+
+Constrains a value between min and max. Omit **value** to get a function: `clamp(min, max)(value)`.
+
+```javascript
+gsap.utils.clamp(0, 100, 150); // 100
+gsap.utils.clamp(0, 100, -10); // 0
+
+let clampFn = gsap.utils.clamp(0, 100);
+clampFn(150); // 100
+```
+
+### mapRange(inMin, inMax, outMin, outMax, value?)
+
+Maps a value from one range to another. Use when converting scroll position, progress (0–1), or input range to an animation range. Omit **value** to get a function: `mapRange(inMin, inMax, outMin, outMax)(value)`.
+
+```javascript
+gsap.utils.mapRange(0, 100, 0, 500, 50);  // 250
+gsap.utils.mapRange(0, 1, 0, 360, 0.5);   // 180 (progress to degrees)
+
+let mapFn = gsap.utils.mapRange(0, 100, 0, 500);
+mapFn(50);  // 250
+```
+
+### normalize(min, max, value?)
+
+Returns a value normalized to 0–1 for the given range. Inverse of mapping when the target range is 0–1. Omit **value** to get a function: `normalize(min, max)(value)`.
+
+```javascript
+gsap.utils.normalize(0, 100, 50);   // 0.5
+gsap.utils.normalize(100, 300, 200); // 0.5
+
+let normFn = gsap.utils.normalize(0, 100);
+normFn(50); // 0.5
+```
+
+### interpolate(start, end, progress?)
+
+Interpolates between two values at a given progress (0–1). Handles numbers, colors, and objects with matching keys. Omit **progress** to get a function: `interpolate(start, end)(progress)`.
+
+```javascript
+gsap.utils.interpolate(0, 100, 0.5);       // 50
+gsap.utils.interpolate("#ff0000", "#0000ff", 0.5); // mid color
+gsap.utils.interpolate({ x: 0, y: 0 }, { x: 100, y: 50 }, 0.5); // { x: 50, y: 25 }
+
+let lerp = gsap.utils.interpolate(0, 100);
+lerp(0.5); // 50
+```
+
+## Random and Snap
+
+### random(minimum, maximum[, snapIncrement, returnFunction]) / random(array[, returnFunction])
+
+Returns a random number in the range **minimum**–**maximum**, or a random element from an **array**. Optional **snapIncrement** snaps the result to the nearest multiple (e.g. `5` → multiples of 5). **To get a reusable function**, pass **true** as the last argument (**returnFunction**); the returned function takes no args and returns a new random value each time. This is the only util that uses `true` for the function form instead of omitting the value.
+
+```javascript
+// immediate value: number in range
+gsap.utils.random(-100, 100);        // e.g. 42.7
+gsap.utils.random(0, 500, 5);        // 0–500, snapped to nearest 5
+
+// reusable function: pass true as last argument
+let randomFn = gsap.utils.random(-200, 500, 10, true);
+randomFn();  // random value in range, snapped to 10
+randomFn();  // another random value
+
+// array: pick one value at random
+gsap.utils.random(["red", "blue", "green"]);  // "red", "blue", or "green"
+let randomFromArray = gsap.utils.random([0, 100, 200], true);
+randomFromArray();  // 0, 100, or 200
+```
+
+**String form in tween vars:** use `"random(-100, 100)"`, `"random(-100, 100, 5)"`, or `"random([0, 100, 200])"`; GSAP evaluates it per target.
+
+```javascript
+gsap.to(".box", { x: "random(-100, 100, 5)", duration: 1 });
+gsap.to(".item", { backgroundColor: "random([red, blue, green])" });
+```
+
+### snap(snapTo, value?)
+
+Snaps a value to the nearest multiple of **snapTo**, or to the nearest value in an array of allowed values. Omit **value** to get a function: `snap(snapTo)(value)` (or `snap(snapArray)(value)`).
+
+```javascript
+gsap.utils.snap(10, 23);     // 20
+gsap.utils.snap(0.25, 0.7);  // 0.75
+gsap.utils.snap([0, 100, 200], 150); // 100 or 200 (nearest in array)
+
+let snapFn = gsap.utils.snap(10);
+snapFn(23); // 20
+```
+
+Use in tweens for grid or step-based animation:
+
+```javascript
+gsap.to(".x", { x: 200, snap: { x: 20 } });
+```
+
+### shuffle(array)
+
+Returns a new array with the same elements in random order. Use for randomizing order (e.g. stagger from "random" with a copy).
+
+```javascript
+gsap.utils.shuffle([1, 2, 3, 4]); // e.g. [3, 1, 4, 2]
+```
+
+### distribute(config)
+
+**Returns a function** that assigns a value to each target based on its position in the array (or in a grid). Used internally for advanced staggers; use it whenever you need values spread across many elements (e.g. scale, opacity, x, delay). The returned function receives `(index, target, targets)` — either call it manually or pass the result directly into a tween; GSAP will call it per target with index, element, and array.
+
+**Config (all optional):**
+
+| Property | Type | Description |
+|----------|------|-------------|
+| `base` | Number | Starting value. Default `0`. |
+| `amount` | Number | Total to distribute across all targets (added to base). E.g. `amount: 1` with 100 targets → 0.01 between each. Use **each** instead to set a fixed step per target. |
+| `each` | Number | Amount to add between each target (added to base). E.g. `each: 1` with 4 targets → 0, 1, 2, 3. Use **amount** instead to split a total. |
+| `from` | Number \| String \| Array | Where distribution starts: index, or `"start"`, `"center"`, `"edges"`, `"random"`, `"end"`, or ratios like `[0.25, 0.75]`. Default `0`. |
+| `grid` | String \| Array | Use grid position instead of flat index: `[rows, columns]` (e.g. `[5, 10]`) or `"auto"` to detect. Omit for flat array. |
+| `axis` | String | For grid: limit to one axis (`"x"` or `"y"`). |
+| `ease` | Ease | Distribute values along an ease curve (e.g. `"power1.inOut"`). Default `"none"`. |
+
+**In a tween:** pass the result of `distribute(config)` as the property value; GSAP calls the function for each target with `(index, target, targets)`.
+
+```javascript
+// Scale: middle elements 0.5, outer edges 3 (amount 2.5 distributed from center)
+gsap.to(".class", {
+  scale: gsap.utils.distribute({
+    base: 0.5,
+    amount: 2.5,
+    from: "center"
+  })
+});
+```
+
+**Manual use:** call the returned function with `(index, target, targets)` to get the value for that index.
+
+```javascript
+const distributor = gsap.utils.distribute({
+  base: 50,
+  amount: 100,
+  from: "center",
+  ease: "power1.inOut"
+});
+const targets = gsap.utils.toArray(".box");
+const valueForIndex2 = distributor(2, targets[2], targets);
+```
+
+See [distribute()](https://gsap.com/docs/v3/GSAP/UtilityMethods/distribute/) for more.
+
+## Units and Parsing
+
+### getUnit(value)
+
+Returns the unit string of a value (e.g. `"px"`, `"%"`, `"deg"`). Use when normalizing or converting values.
+
+```javascript
+gsap.utils.getUnit("100px");   // "px"
+gsap.utils.getUnit("50%");     // "%"
+gsap.utils.getUnit(42);        // "" (unitless)
+```
+
+### unitize(value, unit)
+
+Appends a unit to a number, or returns the value as-is if it already has a unit. Use when building CSS values or tween end values.
+
+```javascript
+gsap.utils.unitize(100, "px");  // "100px"
+gsap.utils.unitize("2rem", "px"); // "2rem" (unchanged)
+```
+
+### splitColor(color, returnHSL?)
+
+Converts a color string into an array: **[red, green, blue]** (0–255), or **[red, green, blue, alpha]** (4 elements for RGBA when alpha is present or required). Pass **true** as the second argument (**returnHSL**) to get **[hue, saturation, lightness]** or **[hue, saturation, lightness, alpha]** (HSL/HSLA) instead. Works with `"rgb()"`, `"rgba()"`, `"hsl()"`, `"hsla()"`, hex, and named colors (e.g. `"red"`). Use when animating color components or building gradients. See [splitColor()](https://gsap.com/docs/v3/GSAP/UtilityMethods/splitColor/).
+
+```javascript
+gsap.utils.splitColor("red");                    // [255, 0, 0]
+gsap.utils.splitColor("#6fb936");                // [111, 185, 54]
+gsap.utils.splitColor("rgba(204, 153, 51, 0.5)"); // [204, 153, 51, 0.5] (4 elements)
+gsap.utils.splitColor("#6fb936", true);          // [94, 55, 47] (HSL: hue, saturation, lightness)
+```
+
+## Arrays and Collections
+
+### selector(scope)
+
+Returns a scoped selector function that finds elements only within the given element (or ref). Use in components so selectors like `".box"` match only descendants of that component, not the whole document. Accepts a DOM element or a ref (e.g. React ref; handles `.current`).
+
+```javascript
+const q = gsap.utils.selector(containerRef);
+q(".box");        // array of .box elements inside container
+gsap.to(q(".circle"), { x: 100 });
+```
+
+### toArray(value, scope?)
+
+Converts a value to an array: selector string (scoped to element), NodeList, HTMLCollection, single element, or array. Use when passing mixed inputs to GSAP (e.g. targets) and a true array is needed.
+
+```javascript
+gsap.utils.toArray(".item");           // array of elements
+gsap.utils.toArray(".item", container); // scoped to container
+gsap.utils.toArray(nodeList);          // [ ... ] from NodeList
+```
+
+### pipe(...functions)
+
+Composes functions: **pipe(f1, f2, f3)(value)** returns f3(f2(f1(value))). Use when applying a chain of transforms (e.g. normalize → mapRange → snap) in a tween or callback.
+
+```javascript
+const fn = gsap.utils.pipe(
+  (v) => gsap.utils.normalize(0, 100, v),
+  (v) => gsap.utils.snap(0.1, v)
+);
+fn(50); // normalized then snapped
+```
+
+### wrap(min, max, value?)
+
+Wraps a value into the range min–max (inclusive min, exclusive max). Use for infinite scroll or cyclic values. Omit **value** to get a function: `wrap(min, max)(value)`.
+
+```javascript
+gsap.utils.wrap(0, 360, 370);  // 10
+gsap.utils.wrap(0, 360, -10);   // 350
+
+let wrapFn = gsap.utils.wrap(0, 360);
+wrapFn(370); // 10
+```
+
+### wrapYoyo(min, max, value?)
+
+Wraps value in range with a yoyo (bounces at ends). Use for back-and-forth within a range. Omit **value** to get a function: `wrapYoyo(min, max)(value)`.
+
+```javascript
+gsap.utils.wrapYoyo(0, 100, 150); // 50 (bounces back)
+
+let wrapY = gsap.utils.wrapYoyo(0, 100);
+wrapY(150); // 50
+```
+
+## Best practices
+
+- ✅ Omit the value argument to get a reusable function when the same range/config is used many times (e.g. scroll handler, tween callback): `let mapFn = gsap.utils.mapRange(0, 1, 0, 360); mapFn(progress)`.
+- ✅ Use **snap** for grid-aligned or step-based values; use **toArray** when GSAP or your code needs a real array from a selector or NodeList.
+- ✅ Use **gsap.utils.selector(scope)** in components so selectors are scoped to a container or ref.
+
+## Do Not
+
+- ❌ Assume **mapRange** / **normalize** handle units; they work on numbers. Use **getUnit** / **unitize** when units matter.
+- ❌ Override or rely on undocumented behavior; stick to the documented API.
+
+### Learn More
+
+https://gsap.com/docs/v3/HelperFunctions
+
+---
+
+## 🏛️ 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.
+
+---
+
+## 🚨 LLM Trap Table
+
+|Pattern|What AI Does Wrong|What Is Actually Correct|
+|:---|:---|:---|
+|gsap-utils|Using mapRange on units like "100px"|mapRange works only on pure numbers. Use getUnit/unitize|
+|gsap-utils|Re-creating random per frame|Pass true as 4th param: random(-10, 10, 1, true) for a reusable fn|
+|gsap-utils|Scoping global .box|Use gsap.utils.selector(container) inside components|
+
+---
+
+## ✅ Pre-Flight Self-Audit
+
+Before producing any output, verify:
+```
+✅ Did I read the actual files before making claims about them?
+✅ Did I verify all method names against official GSAP documentation?
+✅ Did I add // VERIFY: on any uncertain API calls?
+✅ Are all imports from packages that actually exist in package.json?
+✅ Did I test my logic with edge cases (null, empty, 0, max)?
+✅ Did I avoid generating code for more than one module at a time?
+✅ Am I working from evidence, not assumption?
+```
+
+---
+
+## 🔁 VBC Protocol (Verify → Build → Confirm)
+
+```
+VERIFY:  Read the actual codebase before writing anything
+BUILD:   Generate the smallest meaningful unit of code
+CONFIRM: Verify the output is correct before presenting
+```

package/.agent/skills/i18n-localization/SKILL.md

@@ -111,3 +111,45 @@ In Next.js Middleware:
 3. Rewrite URL to the detected locale (e.g., `/ja/dashboard`).
 
 ---
+
+
+---
+
+## 🤖 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/intelligent-routing/SKILL.md

@@ -164,4 +164,75 @@ This file contains all available skills and workflows as a condensed index for t
 |`web-design-guidelines`|Review UI code for Next-Generation Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".|
 |`webapp-testing`|Web application testing principles. E2E, Playwright, deep audit strategies.|
 |`whimsy-injector`|Micro-delight generator for frontend interfaces. Suggests and implements subtle animations, playful transitions, and interaction polish across any frontend stack.|
-|`workflow-optimizer`|Analyzes agent tool-calling patterns and task execution efficiency to suggest process improvements.|
+|`workflow-optimizer`|Analyzes agent tool-calling patterns and task execution efficiency to suggest process improvements.|
+|`api-architect`|API contract design agent. Builds robust REST/GraphQL/tRPC endpoints with RFC 9457 error formats, idempotency, pagination, and versioning. Use when designing new API routes or reviewing API contracts.|
+|`resilience-reviewer`|Fault tolerance reviewer. Audits for swallowed errors, naked Promises, missing retries/timeouts, absent circuit breakers, and missing React error boundaries. Use when reviewing backend or full-stack code for reliability.|
+|`schema-reviewer`|Input validation reviewer. Enforces strict Zod/Pydantic validation at all trust boundaries (API, env, query params). Catches `z.any()`, missing `.parse()`, and unvalidated external data. Use when reviewing data ingestion or API input handling.|
+|`gsap-core`|GSAP core animation API — gsap.to(), from(), fromTo(), easing, stagger, defaults, matchMedia(). Use for JavaScript animation with GSAP.|
+|`gsap-scrolltrigger`|GSAP ScrollTrigger plugin — scroll-driven animations, pinning, snapping. Use when building scroll-linked animation.|
+|`gsap-timeline`|GSAP timeline sequencing — Timeline API, position parameters, labels, nesting. Use for multi-step animation choreography.|
+|`gsap-react`|GSAP in React — useGSAP hook, ref-based targeting, cleanup, context scoping. Use when animating React components with GSAP.|
+|`gsap-plugins`|GSAP plugins — Flip, Draggable, MorphSVG, SplitText, MotionPath, DrawSVG. Use for advanced GSAP effects.|
+|`gsap-performance`|GSAP performance — will-change, GPU compositing, lazy MediaQuery, reduced motion. Use when optimizing GSAP animations.|
+|`gsap-utils`|GSAP utility methods — toArray, clamp, mapRange, interpolate, distribute. Use for GSAP helper functions.|
+|`gsap-frameworks`|GSAP framework integration — Vue, Svelte, Astro, Angular, Webflow. Use when integrating GSAP outside React.|
+|`error-resilience`|Error resilience patterns. Retry strategies, circuit breakers, graceful degradation, timeout policies.|
+|`data-validation-schemas`|Data validation with Zod, Pydantic, and JSON Schema. Use when building validation layers.|
+|`monorepo-management`|Monorepo tooling and workspace management. Turborepo, Nx, pnpm workspaces.|
+|`typescript-advanced`|Advanced TypeScript patterns. Generics, conditional types, template literals, discriminated unions.|
+|`game-developer`|Game development orchestrator. Routes to platform-specific skills (Unity/C#, Godot/GDScript, WebGL). Use when building games or game engines.|
+|`documentation-writer`|Technical documentation specialist. README files, API docs, code comments, architecture docs, and AI-friendly documentation. Use when writing or reviewing documentation.|
+|`test-engineer`|Test generation and strategy specialist. Creates tests using the Testing Trophy (unit → integration → E2E). Use when generating tests or designing test architecture.|
+|`qa-automation-engineer`|QA automation specialist. End-to-end testing pipelines, Playwright/Cypress configuration, CI test integration, visual regression. Use when building automated QA systems.|
+|`code-archaeologist`|Legacy code exploration specialist. Navigates unfamiliar codebases, identifies patterns, maps dependencies, documents tribal knowledge. Use when exploring or understanding legacy code.|
+|`project-planner`|Project planning specialist. 4-phase methodology (Analyze → Plan → Solution → Implement). Use when planning features, roadmaps, or multi-step implementations.|
+|`product-manager`|Product strategy specialist. Feature prioritization, roadmap planning, stakeholder alignment, competitive analysis. Use when making product decisions or prioritizing features.|
+|`product-owner`|User story and backlog management specialist. Writing acceptance criteria, sprint planning, backlog grooming. Use when defining user stories or managing backlogs.|
+|`seo-specialist`|SEO optimization specialist. Technical SEO, meta tags, structured data (JSON-LD), Core Web Vitals impact on search ranking, sitemap/robots configuration. Use when optimizing search visibility.|
+|`throughput-optimizer`|Throughput and latency optimization specialist. Load testing, connection pooling, queue management, batch processing, caching strategies. Use when optimizing system throughput or reducing latency.|
+|`vitals-reviewer`|Core Web Vitals specialist. LCP, CLS, INP measurement and optimization, Lighthouse auditing, real user monitoring. Use when auditing or improving web performance metrics.|
+|`penetration-tester`|Penetration testing and red team specialist. MITRE ATT&CK mapping, attack surface analysis, exploitation paths, vulnerability chaining. Use when pen testing applications or assessing attack surfaces.|
+|`db-latency-auditor`|Database performance specialist. Slow query analysis, EXPLAIN ANALYZE, index optimization, N+1 detection, connection pool tuning. Use when debugging database performance issues.|
+|`ai-code-reviewer`|AI/LLM integration code reviewer. Hallucinated model names, invented API parameters, prompt injection vulnerabilities, missing rate limits, streaming error handling. Use when reviewing code that calls LLM APIs.|
+
+
+---
+
+## 🤖 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/lint-and-validate/SKILL.md

@@ -209,3 +209,45 @@ Evidence:    [test output / lint pass / compile success]
 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.