Move nel-ci-guide.md to Model-Optimizer-Internal per review feedback

Reviewer @shengliangxu flagged that the NEL CI evaluation guide contains
NVIDIA-internal infrastructure (JET clusters, svc-jet service account,
gitlab-master NEL CI triggers, COMPEVAL_HF_TOKEN, internal lustre paths)
and should not ship in the public repo.

The file has been moved to Model-Optimizer-Internal:agent/nel-ci-guide.md
(see internal MR: zhiyu/add-nel-ci-guide-to-agent). This commit removes
the public copy and the "NEL CI and Cluster-Specific Notes" section from
evaluation/SKILL.md that referenced it.

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

Author: Edwardf0t1

.claude/skills/evaluation/SKILL.md

@@ -319,19 +319,6 @@ After job submission, you can monitor progress using:
 
 ---
 
-### NEL CI and Cluster-Specific Notes
-
-For running evaluations on NVIDIA JET clusters (oci-hsg, cw, oci-nrt) or SLURM clusters like dlcluster, read `references/nel-ci-guide.md`. It covers:
-- NEL CI GitLab trigger pattern vs NEL SLURM executor
-- Cluster-specific GPU counts and storage paths
-- Checkpoint availability (compute nodes may not share login node filesystems)
-- Environment variable prefixes (`host:`, `lit:`) for SLURM executor
-- SGLang must bind `--host 0.0.0.0` for health checks
-- Directory setup and `chmod 777` for JET service account access
-- Common issues (NGC auth, gated datasets, walltime, `NEL_OTHER_OVERRIDES` space-splitting)
-
----
-
 Direct users with issues to:
 
 - **GitHub Issues:** <https://github.com/NVIDIA-NeMo/Evaluator/issues>