docs: add cookbook-migrate-model skill from the Qwen3.5 pilot (#27845)

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

.claude/skills/cookbook-add-model/templates/config.jsx.tmpl

@@ -48,6 +48,12 @@ export const config = {
     { id: "fp8",  label: "FP8"  },
     { id: "fp4",  label: "FP4"  },
   ],
+  // 4th dim. The count follows the model's operating points: 1 recipe → a
+  // single "balanced"; 2 → low-latency + high-throughput; 3 → the full trio
+  // (the ideal). Per-combination: a single-recipe combination (e.g. a CPU
+  // platform) parks under its semantically honest tier — no slant → balanced;
+  // the page's list is the union and the engine greys unused chips. Never
+  // invent a recipe just to fill chips.
   strategies: [
     { id: "low-latency",     label: "Low-Latency"     },
     { id: "balanced",        label: "Balanced"        },
@@ -158,7 +164,10 @@ sgl-eval run gsm8k \\
     cookbookModel: "__HF_ORG__/__MODEL_SLUG__",
   },
 
-  // Opt-in per axis. DELETE any axis your model doesn't expose (don't leave a stub).
+  // Opt-OUT per axis: general axes (attention / moe-for-MoE / parsers /
+  // speculative / pdDisagg / hicache) ship on every cookbook — DELETE only the
+  // axes this model genuinely cannot use (e.g. hisparse on non-DSA models, moe
+  // on pure-dense models); prefer disable+disableReason for variant/hw subsets.
   playgroundFeatures: {
 
     // ----- Card: "Attention Parallelism" -----  KEEP if the model exposes TP/CP/DP
@@ -312,6 +321,9 @@ sgl-eval run gsm8k \\
   // EXAMPLE cells — one per hardware family to show the shape. REPLACE each with
   // your model's verified recipe, or DELETE families you don't support. `match`
   // MUST have exactly the 5 keys; env/flags are flat literals.
+  // Accuracy-degrading flags (W4A4-style runtime quant, lossy --kv-cache-dtype)
+  // default to Playground/tips — putting one in a cell needs explicit user
+  // confirmation (authoring-reference §2.2).
   cells: [
     // ==== NVIDIA Blackwell + FP4 (single node) ====
     {

.claude/skills/cookbook-add-model/templates/page.mdx.tmpl

@@ -103,8 +103,9 @@ import { Playground } from "/src/snippets/_playground.jsx";
 
 ## 3. Advanced Usage
 
-{/* Keep only the subsections that apply. Each runnable block is followed by an
-    **Output Example:** + a ```text Output block with REAL server output. */}
+{/* Keep only the subsections that apply. Commands and outputs in this section are
+    COLLAPSIBLE (required — match DeepSeek-V4 §3): each runnable example lives in an
+    <Accordion>, its REAL server output in a following <Accordion title="Example Output">. */}
 
 ### 3.1 Reasoning
 
@@ -114,6 +115,8 @@ Enable the `__REASONING_PARSER__` reasoning parser (toggle **Reasoning Parser**
     answer → `content`). If your parser emits inline `<think>...</think>` tags inside
     `content`, parse the tags from `content` instead. */}
 
+<Accordion title="Reasoning Example (Python)">
+
 ```python Example
 from openai import OpenAI
 
@@ -128,18 +131,23 @@ print("Reasoning:", getattr(msg, "reasoning_content", None))
 print("Answer:", msg.content)
 ```
 
-**Output Example:**
+</Accordion>
+
+<Accordion title="Example Output">
 
 ```text Output
 TODO: paste real server output here.
 ```
 
+</Accordion>
+
 ### 3.2 Tool Calling
 
 Enable the `__TOOLCALL_PARSER__` tool-call parser (toggle **Tool Call Parser** in the **Parsers** card of the [Playground above](#playground)) to surface structured tool calls via `message.tool_calls`.
 
-{/* TODO: tool-calling example + **Output Example:**. On thinking-mode models the
-    follow-up may put text in `reasoning_content`; print both that and `content`. */}
+{/* TODO: tool-calling example in an <Accordion> + an <Accordion title="Example Output">.
+    On thinking-mode models the follow-up may put text in `reasoning_content`;
+    print both that and `content`. */}
 
 ### 3.3 HiCache (Hierarchical KV Caching)