openclaw-vsr-bridge

Install vLLM Semantic Router in agent-safe mode, import supported OpenClaw model providers into canonical VSR config, and rewrite OpenClaw to target VSR.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%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 tight, command-driven skill body that respects token budget, gives copy-paste-ready commands with sensible safety boundaries, and sequences the workflow with validation suggestions. The only notable gap is the absence of an explicit validate-fail-retry feedback loop around the config import/rewrite steps.

Suggestions

Add an error-recovery loop after the import step: 'If import or validation fails, inspect the reported errors, fix the openclaw.json or flags, and re-run before any OpenClaw rewrite.'

State how to detect import success explicitly (e.g., the command's exit status or expected output) before proceeding to the OpenClaw rewrite.

Include what to do when no openclaw.json is found at any of the three candidate paths, so the workflow does not dead-end.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive — commands, an ordered workflow, and boundaries with no explanation of concepts Claude already knows and no padding; every line earns its place. It is not a 4 because there is no over-explanation anywhere to trim.	5 / 5
Actionability	Commands are fully executable and copy-paste ready: "curl -fsSL https://vllm-sr.ai/install.sh \| bash -s -- --mode cli --runtime skip --no-launch", "vllm-sr config import --from openclaw --source <openclaw.json> --target config.yaml", plus validate, router, serve, and a curl smoke check. It is not a 4 because the concrete commands cover the common cases with no gaps.	5 / 5
Workflow Clarity	The 8-step sequence is clear with ordered checkpoints (check existing install, locate config in priority order, import before rewriting OpenClaw) and suggested validation commands, matching the most-checkpoints anchor. It is not a 5 because there is no explicit error-recovery feedback loop (e.g., 'if validate fails, fix the config and re-run') and no guidance on handling import failure; it is not a 3 because validation steps are explicitly present rather than missing.	4 / 5
Progressive Disclosure	This is a short, single-purpose skill with no bundle files and no need for external references; its sections (When To Use, Requirements, Workflow, Boundaries) are well-organized, which per the simple-skill guideline earns a 5. It is not a 4 because nothing is inlined that belongs in a separate file and navigation is trivial.	5 / 5
	Total	19 / 20 Passed

Description

75%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.

A highly specific, third-person description of a niche integration task with concrete named actions and tools, but it omits any "Use when..." trigger guidance, capping its completeness. Adding a trigger clause would lift the two dimensions currently held back.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user wants to install or configure VSR for an OpenClaw agent, migrate an openclaw.json under VSR management, or route OpenClaw requests through a semantic router.'

Include a few natural synonyms or phrasings users might say, such as 'migrate', 'route', or 'semantic routing', to broaden trigger-term coverage.

Consider mentioning the openclaw.json file name explicitly so a user referencing that file triggers the skill.

Dimension	Reasoning	Score
Specificity	"Install vLLM Semantic Router in agent-safe mode, import supported OpenClaw model providers into canonical VSR config, and rewrite OpenClaw to target VSR" lists multiple specific concrete actions (install, import, rewrite) each tied to concrete artifacts, matching the comprehensive-coverage anchor. It is not a 4 because coverage of the skill's actions is complete rather than having minor gaps.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guideline. It is not a 2 because the "what" is fully explicit, and not a 4 because the "when" is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	Natural terms a user would say are present ("vLLM Semantic Router", "VSR", "OpenClaw", "install", "rewrite"), giving good keyword coverage, but a few natural variations are missing (e.g., "route", "migrate", "semantic router"). It is not a 5 because there is no synonym or phrasing breadth comparable to the "PDF files, PDFs, forms, .pdf" anchor.	4 / 5
Distinctiveness Conflict Risk	The description names a very specific niche (OpenClaw-to-VSR bridging) with distinct tool names, so it is unlikely to trigger for the wrong skill. It is not lower because no generic phrasing like "helps with configs" appears that would overlap other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: dashboard/backend/skillpacks/openclaw-vsr-bridge/SKILL.md
Commit: c89d5d4

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.