| name | vllm-semantic-router-harness |
| description | Bridges native skill discovery into the vLLM Semantic Router repository harness, routing tasks through the canonical agent-report flow, repo-local skill registry, and validation commands. Use when starting any task inside the vLLM Semantic Router repository to resolve the correct primary skill, read canonical docs, and run harness validation. |
vLLM Semantic Router Harness
This is a native-discovery bridge. The canonical source of truth remains:
When To Use
Use this skill whenever the current workspace is this repository or the task touches files under src/, tools/agent/, docs/agent/, dashboard/, or .github/.
Required Flow
- Read
AGENTS.md first.
- Read
docs/agent/README.md and the nearest local AGENTS.md for hotspot directories.
- Run
make agent-report ENV=cpu|amd CHANGED_FILES="..." before non-trivial edits.
- Start from the resolved primary skill under
tools/agent/skills/.
- Validate with the canonical harness commands from
tools/make/agent.mk.
Boundaries
- Do not treat this wrapper as canonical policy text.
- Do not copy or fork skill instructions out of
tools/agent/**.
- Use
make agent-report to expose the full routed context pack; this wrapper only improves native startup discovery.
