Address feedbacks

Signed-off-by: Kai Xu <kaix@nvidia.com>

Author: kaix-nv

.claude/skills/evaluation/SKILL.md

@@ -256,7 +256,7 @@ After the dry-run, check the output from `nel` for any problems with the config.
 
 **Monitoring Progress**
 
-After job submission, register the job and set up monitoring per the **monitor skill**.
+After job submission, register the job per the **monitor skill** for durable cross-session tracking. For one-off queries (live status, debugging a failed run, analyzing results) use the **launching-evals skill**; for querying past runs in MLflow use **accessing-mlflow**.
 
 **NEL-specific diagnostics** (for debugging failures):
 

.claude/skills/monitor/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: monitor
-description: Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation", "what's the status of the PTQ", "check on job 12345", or after any skill submits a long-running job. Also triggers on "nel status", "squeue", or any request to check progress of a previously submitted job.
+description: Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation", "what's the status of the PTQ", "check on job <slurm_job_id>", or after any skill submits a long-running job. Also triggers on "nel status", "squeue", or any request to check progress of a previously submitted job.
 ---
 
 # Job Monitor