CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vllm-sr

Install, configure, verify, maintain, troubleshoot and optimize vLLM Semantic Router v0.5 on a Docker host (CPU, AMD or NVIDIA GPU) or a Kubernetes cluster (Helm or the operator), through its CLI and Router API. Use for a first install, configuration and routing changes, checks of routed requests, upgrades and the v0.5 config migration, secrets, logs, health, backup and restore, removal, failure diagnosis, and tuning of the decision model, recipes, caches, latency and cost with sr-bench.

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

The canonical home for this skill is vllm-sr-agent-operations in vllm-project/semantic-router

SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly engineered operational skill: dense, imperative, with exact commands, exact success criteria, explicit failure loops and conservative stop-and-ask boundaries on every task. Its only structural weakness is navigation plumbing — absolute-URL links instead of relative paths into the local bundle, and one example file nested two levels deep — which keeps progressive disclosure a notch below the rest.

Suggestions

Use relative links to the bundled files (e.g. [Deployment](references/deployment-loop.md)) instead of absolute https://vllm-sr.ai/... URLs, so navigation works wherever the skill bundle is installed and cannot break if the site moves.

Surface http-configuration-plan.md directly (e.g. from the Configure task section or the task table) or fold it into configuration-loop.md, so no content sits two reference levels deep from SKILL.md.

Clarify the compressed Envoy note in the Maintain section ("takes `--gateway extproc` in all three commands") by naming the three commands explicitly, since the antecedent is currently implicit.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout: no general concept explanations, just product-specific facts Claude could not know ("the Router (inference on port 8899, management API on 8080)", "the default decision model holds about 7 GB on the CPU") compressed into rules, tables and commands. The v0.5 version references are the product's current version and a migration target, not stale time-sensitive guidance, so they do not trigger the version-number penalty. It does not fit anchor 4 because there is no passage of over-explanation to trim — every token carries operational weight.

5 / 5

Actionability

Preflight and port checks are copy-paste-ready command blocks with a pass/fail decision table, and every task section names exact commands and exact success evidence: "`serve` exits 0 after `✓ vLLM Semantic Router is running (standalone gateway)`", "`config apply` exits 0 and prints `\"applied\": true`", "an sr-bench run returns `\"status\": \"completed\"` with every target `\"complete\": true`". The one literal ellipsis (`vllm-sr route probe … --expect-decision code-route`) reflects deployment-specific route names and is explicitly justified by context, keeping it at the top anchor rather than 4.

5 / 5

Workflow Clarity

Each task has an explicit five-part loop — Preconditions, Run, Success, On failure, Stop and ask — with validation defined as observable output ("Success is what the output contains: an exit code, a JSON field, a header value. An HTTP 200 alone is not success") and explicit feedback loops ("Change one thing at a time, then rerun the step that failed", "run its check, apply its fix, rerun the failed step"). Destructive and batch operations (removal, upgrade, rollback, config apply) all carry validation checkpoints and stop-and-ask gates, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The overview-to-reference split is genuinely good — a task table routes to eight real bundle files, each named with when-to-use conditions, and ~2,260 lines of detail live outside the 220-line SKILL.md. But scored against the actual bundle structure it falls just short of the top anchor: all reference links are absolute URLs (https://vllm-sr.ai/install/agent/vllm-sr/references/…) rather than relative paths to the bundled ./references/ files, and http-configuration-plan.md is only reachable via a second-level link from configuration-loop.md, so navigation has minor gaps — the signature of anchor 4 rather than 5.

4 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: third-person, densely packed with concrete capabilities, explicit platforms and interfaces, and a full "Use for" trigger clause enumerating the scenarios it covers. Its only cost is length — it is a long single sentence — but every clause is signal rather than padding, so the verbosity guideline is not triggered.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions — "Install, configure, verify, maintain, troubleshoot and optimize" plus "upgrades and the v0.5 config migration, secrets, logs, health, backup and restore, removal, failure diagnosis, and tuning of the decision model, recipes, caches, latency and cost with sr-bench" — and pins the surfaces involved ("Docker host (CPU, AMD or NVIDIA GPU) or a Kubernetes cluster (Helm or the operator), through its CLI and Router API"). This matches the anchor for multiple specific concrete actions with comprehensive coverage; there is no vague filler to drop it to 4.

5 / 5

Completeness

The "what" is explicit and concrete ("Install, configure, verify, maintain, troubleshoot and optimize vLLM Semantic Router v0.5…through its CLI and Router API") and the "when" is an explicit trigger clause: "Use for a first install, configuration and routing changes, checks of routed requests, upgrades and the v0.5 config migration…". Both are present with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

It covers the natural phrases a user would say when needing this skill — "first install", "routing changes", "checks of routed requests", "upgrades", "migration", "secrets", "logs", "health", "backup and restore", "failure diagnosis", "tuning" — alongside product-specific terms ("vLLM Semantic Router", "sr-bench"). Coverage is comprehensive with synonyms and variants (e.g. both "troubleshoot" and "failure diagnosis", both "removal" and per-task verbs); it does not sit at 4 because no common variation a user would plausibly say is missing.

5 / 5

Distinctiveness Conflict Risk

The description is scoped to a named product and version ("vLLM Semantic Router v0.5") with its own distinctive triggers (sr-bench, decision model, config migration), giving it a clear niche with minimal overlap risk against generic vLLM-serving or container-ops skills. It is not a 4 because the product naming and task list are specific enough that mis-triggering for a different skill is unlikely.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

vllm-project/semantic-router

Path

website/static/install/agent/vllm-sr/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.