router-contract-change

Use when changing a request-visible router contract across configuration, signals, decisions, algorithms, or recipe-scoped plugins in vLLM Semantic Router.

Quality

86%

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

86%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, token-efficient instruction skill with concrete commands, file pointers, and a clear sequenced workflow. It would reach full marks on actionability and workflow clarity by giving concrete DOMAIN/PROFILE examples and an explicit verify->fix->retry loop.

Suggestions

Replace the templated `DOMAIN=<domain>` / `PROFILE=<profile>` placeholders with one or two concrete example invocations so the commands are copy-paste ready.

Add an explicit feedback loop: if `make check` or `make verify` fails, state that Claude should fix the issue and re-run before proceeding.

Optionally clarify what 'the affected contract' maps to in `tools/agent/docs/change-surfaces.md` so the reader knows which section to consult.

Dimension	Reasoning	Score
Conciseness	Lean and unpadded; assumes Claude's competence and explains no known concepts, with every line an actionable directive.	5 / 5
Actionability	Provides concrete executable commands (`make check`, `make verify DOMAIN=`, `make verify PROFILE=`) and file pointers, but the DOMAIN/PROFILE values are templated placeholders rather than copy-paste-ready concrete examples.	4 / 5
Workflow Clarity	Clear sequence (read docs, keep consistent, update artifacts, run check, verify) with verification checkpoints present, though an explicit verify->fix->retry feedback loop is not spelled out.	4 / 5
Progressive Disclosure	Short, well-organized body with a clear section header and one-level-deep, clearly signaled external references (`AGENTS.md`, `tools/agent/docs/change-surfaces.md`); no bundle files are present, so the simple-skill exception applies.	5 / 5
	Total	18 / 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.

A strong, specific description with an explicit 'Use when' trigger and a clearly bounded niche; it enumerates concrete contract surfaces and is highly distinguishable from generic skills. It could push specificity higher by naming concrete actions rather than change categories.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates several concrete contract surfaces (configuration, signals, decisions, algorithms, recipe-scoped plugins), but these are categories of change rather than concrete actions, leaving minor coverage gaps short of a 5.	4 / 5
Completeness	Explicitly answers both 'what' (changing a request-visible router contract across the listed surfaces) and 'when' (Use when changing...) with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Opens with the natural 'Use when changing' trigger and includes domain keywords a vLLM Semantic Router user would actually say, though some common variations or synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow niche (vLLM Semantic Router, request-visible router contract) with distinct triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	18 / 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: tools/agent/skills/router-contract-change/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.