Delete end-to-end-workflow.md per review feedback

Reviewers on PR #1239 (kaix-nv, mxinO) flagged the e2e workflow doc as
unnecessary: the skill descriptions already route Claude to chain PTQ,
deployment, and evaluation skills, and the content duplicated
workspace-management.md or lived better inside the evaluation skill's
nel-ci-guide.md references.

Removes the file and its three cross-references (evaluation/SKILL.md,
ptq/SKILL.md, workspace-management.md). The "carry PTQ patches forward
to deploy/eval" insight is preserved as a one-liner in evaluation/SKILL.md.

Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>

Author: Edwardf0t1

.claude/skills/common/end-to-end-workflow.md

@@ -105,8 +105,6 @@ workspaces/model-name-format/
   logs/                ← All: SLURM job logs
 ```
 
-See `skills/common/end-to-end-workflow.md` for the full pipeline.
-
 ## Example Flow
 
 ```text

.claude/skills/common/workspace-management.md

@@ -16,7 +16,7 @@ You're an expert in NeMo Evaluator Launcher! Guide the user through creating pro
 
 If `MODELOPT_WORKSPACE_ROOT` is set, read `skills/common/workspace-management.md`. Check for existing workspaces — especially if evaluating a model from a prior PTQ or deployment step. Reuse the existing workspace so you have access to the quantized checkpoint and any code modifications.
 
-This skill is often the final stage of the PTQ → Deploy → Eval pipeline. If the model required runtime patches during deployment (transformers upgrade, framework source fixes), carry those patches into the NEL config via `deployment.command`. See `skills/common/end-to-end-workflow.md` for the full pipeline.
+This skill is often the final stage of the PTQ → Deploy → Eval pipeline. If the model required runtime patches during deployment (transformers upgrade, framework source fixes), carry those patches into the NEL config via `deployment.command`.
 
 ### Workflow
 

.claude/skills/evaluation/SKILL.md

@@ -135,7 +135,7 @@ Report the path and size to the user.
 
 Validate the exported checkpoint's quantization pattern matches the recipe. Quantization config patterns can silently miss layers if the model uses non-standard naming (e.g., Gemma4 `experts.*` missed by `*mlp*` patterns) — this only surfaces later as deployment failures. Read `references/checkpoint-validation.md` for the validation script, expected patterns per recipe, and common pattern gaps.
 
-**Next steps**: If the user wants to deploy or evaluate the quantized checkpoint, use the **deployment** or **evaluation** skill. The checkpoint workspace carries over — see `skills/common/end-to-end-workflow.md` for the full PTQ → Deploy → Eval pipeline. If the model required patches during PTQ (e.g., transformers upgrade), the same fixes will likely be needed at deployment and evaluation time.
+**Next steps**: If the user wants to deploy or evaluate the quantized checkpoint, use the **deployment** or **evaluation** skill. The checkpoint workspace carries over. If the model required patches during PTQ (e.g., transformers upgrade), the same fixes will likely be needed at deployment and evaluation time.
 
 ## Key API Rules