Closes #938. cc @marta-sd

Summary

The "Key Facts" section of launching-evals/SKILL.md had two NVIDIA-internal references that bias the skill toward NVIDIA infra and confuse external users:

1. "PPP" terminology with coreai_dlalgo_* example account names. "PPP" is internal NVIDIA jargon; the example values are NVIDIA-specific.

   • Renamed the bullet to "SLURM account" (the universally-correct term).
   • Kept "PPP" as a parenthetical alias so internal users still recognize it.
   • Genericized the example values to <account_name> / <new_account_name>.

2. HF cache download example hardcoded an NVIDIA-internal lustre path (/lustre/fsw/portfolios/coreai/users/<username>/cache/...).

   • Replaced with <your_hf_cache_dir> placeholder.
   • Added a hint that it should be a shared filesystem accessible from compute nodes — /lustre/... for multi-node clusters or ~/.cache/huggingface for single-node setups.

Diff

- - **PPP** = Slurm account (the `account` field in cluster_config.yaml). When the user says "change PPP to X", update the account value (e.g., `coreai_dlalgo_compeval` → `coreai_dlalgo_llm`).
+ - **SLURM account**: the `account` field in `cluster_config.yaml`. When the user asks to change it (some teams call this a "PPP"), update the value (e.g., `<account_name>` → `<new_account_name>`).

- - **HF cache requirement**: ... then `HF_HOME=/lustre/fsw/portfolios/coreai/users/<username>/cache/huggingface hf download <model>`. Without this, vLLM will fail with `LocalEntryNotFoundError`.
+ - **HF cache requirement**: ... then `HF_HOME=<your_hf_cache_dir> hf download <model>` (typically a shared filesystem accessible from compute nodes — e.g., a `/lustre/...` mount on multi-node clusters or `~/.cache/huggingface` for single-node setups). Without this, vLLM will fail with `LocalEntryNotFoundError`.

Context

This came up while vendoring launching-evals into NVIDIA/Model-Optimizer (PR #1239). Reviewers flagged the internal references. Issue #938 has the full discussion.

Thanks for the earlier gitlab-master URL fix in #920 — this PR addresses the two leftovers.