Fix SKILL.md: correct constraints (1.44MB per onnx file, Script not If, all static shapes required)

SKILL.md

@@ -45,10 +45,11 @@ Research → Design → Experiment → Analyze → Research → ...
 |------|-------|
 | Input/Output | `"input"`/`"output"` float32 `[1,10,30,30]` one-hot |
 | Opset | 17 (IR 8). Opset 10 also accepted on Kaggle |
-| Max file size | 1.44 MB per model |
-| Banned ops | Loop, Scan, NonZero, Unique, Script, Function |
+| **Max .onnx file size** | **1.44 MB per ONNX file** (not submission zip) |
+| Static shapes | **All tensors and parameters must have statically-defined shapes** |
+| Banned ops | **Loop, Scan, NonZero, Unique, Script, Function** |
 | Scoring | `max(1.0, 25.0 - ln(MACs + memory + params))` per task |
-| Tasks | **All 400 count. There are NO excluded tasks.** |
+| Tasks | **All 400 count. There are NO excluded tasks. Unsolved = 1.0 pt.** |
 | Validation | Models checked against **train + test + arc-gen** (ALL splits) |
 | Submission | `submission.zip` with `task001.onnx`–`task400.onnx` + optional `submission.csv` |
 
@@ -106,6 +107,8 @@ Run with: `python -m neurogolf_solver.main [args]`
 ```
 
 ### ONNX Building Rules (opset 17)
+- **All shapes must be static** — no dynamic dimensions
+- **Max 1.44 MB per .onnx file** — checked by Kaggle validator
 - **Slice(step=-1)** for flip/rotate — zero MACs, replaces Gather for these transforms
 - **Gather** (opset 1) for spatial remapping — used by concat, spatial_gather, mirrors, etc.
 - **NEVER** use GatherElements (opset 11)
@@ -187,9 +190,9 @@ Before submitting to Kaggle:
 - [ ] All models validated against train + test + arc-gen (locally)
 - [ ] **All 400 tasks attempted** (no exclusions)
 - [ ] No GatherElements in any model
-- [ ] No banned ops
-- [ ] Each .onnx < 1.44 MB
-- [ ] submission.zip generated and < 1.44 MB
+- [ ] No banned ops (Loop, Scan, NonZero, Unique, Script, Function)
+- [ ] All tensor shapes are static
+- [ ] **Each .onnx file < 1.44 MB**
 - [ ] Local estimated score calculated and compared to expected LB
 - [ ] **A/B test**: ran both old and new solver on same tasks, new solver scores higher