git:20260909.d4dffb8 to git:20260910.55adacd

6 added, 13 removed. Audit C to A.

- <!-- Generated Claude Code shim from .agents/skills/vllm-ascend-serving/SKILL.md. Do not edit. -->
---
- name: vllm-ascend-serving
- description: Start, check, or stop a single-node vLLM Ascend service through coordinator TaskClient. Use for 拉服务 / 看服务状态 / 停掉服务. Do not use for machine bootstrap or generic remote I/O.
+ name: "vllm-ascend-serving"
+ description: "Start, check, or stop a single-node vLLM Ascend service through coordinator TaskClient. Use for 拉服务 / 看服务状态 / 停掉服务. Do not use for machine bootstrap or generic remote I/O."
---
- # vLLM Ascend Serving
-
- Canonical skill source:
-
- `.agents/skills/vllm-ascend-serving/SKILL.md`
+ <!-- Generated from .agents/skills/vllm-ascend-serving/SKILL.md. Do not edit. -->
- Before using this skill:
+ # vLLM Ascend Serving
- 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-serving/SKILL.md` and only the references needed
+ for the current task. The canonical skill owns the workflow.