router-service-platform-change

Modifies router-side API, authz, memory, provider, storage, or runtime service modules outside config, decision, selection, and extproc plugin chains. Use when changing apiserver endpoints, authz or rate-limit policy code, memory or response storage flows, provider adapters, or other router service-platform modules.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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.

The body is concise, well-structured, and actionable with concrete make commands and validation checkpoints. Its main gaps are abstract early workflow steps and the absence of an explicit failure-recovery loop.

Suggestions

Make workflow steps 1 and 2 more concrete — name the specific files or commands used to 'Read change surfaces and module boundaries' instead of leaving them as high-level directives.

Add an explicit feedback loop after the agent-ci-gate step (e.g., 'If the gate fails, fix the flagged constraint and re-run agent-ci-gate before proceeding').

Confirm the Must Read reference paths resolve within the skill bundle, or note explicitly that they are repo-level docs, so navigation does not appear broken when the skill is packaged standalone.

Dimension	Reasoning	Score
Conciseness	Mostly lean bullet points and short workflow steps with no padding of concepts Claude already knows; the Gotchas prose ('not generic fallback territory anymore...') could be trimmed slightly but earns its place.	4 / 5
Actionability	Provides concrete executable commands (`make agent-report ENV=cpu CHANGED_FILES=...`, `make agent-ci-gate ...`) in both the workflow and Standard Commands, but early steps ('Read change surfaces...', 'Modify the router-side service...') remain high-level.	4 / 5
Workflow Clarity	A clear five-step sequence with verification checkpoints (agent-report in step 3, agent-ci-gate in step 4); however, no explicit error-recovery feedback loop ('if gate fails, fix and re-run') is documented.	4 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled 'Must Read' block of one-level-deep references; the links point to external repo paths (../../../../tools/agent/docs/) rather than bundle files, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is specific, well-bounded, and answers both what and when with concrete trigger phrases. Its main limitation is relying on a single action verb across many module types rather than enumerating distinct actions.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates several concrete module types (API, authz, memory, provider, storage, runtime service modules), but the single verb 'Modifies' limits the breadth of distinct actions, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	Explicitly states both what ('Modifies router-side API, authz, memory, provider, storage, or runtime service modules...') and when ('Use when changing apiserver endpoints, authz or rate-limit policy code...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain terms a router developer would say ('apiserver endpoints', 'authz or rate-limit policy code', 'memory or response storage flows', 'provider adapters'); good keyword coverage with a few common variations absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (router service-platform modules) sharpened by an explicit exclusion boundary ('outside config, decision, selection, and extproc plugin chains'), minimizing conflict with sibling skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: vllm-project/semantic-router
Path: tools/agent/skills/router-service-platform-change/SKILL.md
Commit: e73c772

Reviewed: 9 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.