git:20260908.b45d86b to git:20260910.55adacd

6 added, 13 removed. Audit C to A.

-

---

- name: vllm-ascend-distributed-debug

- description: Diagnose vLLM Ascend multi-rank and multi-node startup, rank mapping, process-group, collective, HCCL, Ray, scheduler, connector, and distributed hang failures from structured topology and per-rank evidence. Use when a failure depends on rank count, parallel topology, nodes, collectives, or distributed endpoints. Do not use for graph-only divergence, isolated operator failures, performance benchmarking, or profiler analysis.

+ name: "vllm-ascend-distributed-debug"

+ description: "Diagnose vLLM Ascend multi-rank and multi-node startup, rank mapping, process-group, collective, HCCL, Ray, scheduler, connector, and distributed hang failures from structured topology and per-rank evidence. Use when a failure depends on rank count, parallel topology, nodes, collectives, or distributed endpoints. Do not use for graph-only divergence, isolated operator failures, performance benchmarking, or profiler analysis."

---

- # vLLM Ascend Distributed Debug

- Canonical skill source:

- `.agents/skills/vllm-ascend-distributed-debug/SKILL.md`

+

- Before using this skill:

+ # vLLM Ascend Distributed Debug

- 1. Read the canonical skill file above.

- 2. Follow its routing rules, entrypoints, guardrails, and acceptance criteria.

- 3. Use the remote-dev companion tools (`remote_*` MCP tools; CLI fallback `remote-dev <hyphen-tool> ...` or `uv run remote-dev <hyphen-tool> ...`) for ordinary remote endpoint read/edit/bash/search/patch work.

- 4. Use this Claude project skill only for the domain workflow described by the canonical source.

+ Read `.agents/skills/vllm-ascend-distributed-debug/SKILL.md` and only the references needed

+ for the current task. The canonical skill owns the workflow.