routing-policy-change

Modifies routing policy after signal extraction, including matched-decision logic, candidate-model selection, and downstream looper behavior. Use when changing decision predicates, thresholds, priorities, model ranking, cost or latency routing, or other post-signal routing policy.

Quality

85%

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

85%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 and actionable with a clear validation-gated workflow and well-labeled sections, fitting an instruction-only routing skill well. The main gap is an implicit rather than explicit error-recovery loop after the CI gate, and external-only references with no accompanying bundle.

Suggestions

Add an explicit error-recovery step after `make agent-ci-gate` (e.g., 'If the gate fails: review the report, fix the failing routing-policy surface, and re-run the gate until green') to complete the validate-fix-retry feedback loop.

Replace the `CHANGED_FILES="..."` placeholder in Standard Commands with a concrete example value so the commands are fully copy-paste ready.

If the referenced docs (change-surfaces.md, module-boundaries.md, testing-strategy.md) are essential, bundle them under a local `references/` directory so the skill is self-contained and the links resolve within the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: short Trigger, Workflow, Gotchas, Standard Commands, and Acceptance sections with no padding or explanation of concepts Claude already knows, so every token earns its place.	5 / 5
Actionability	Provides concrete executable commands (`make agent-report ENV=cpu CHANGED_FILES=...`, `make agent-ci-gate ...`, `make agent-feature-gate ...`) and a sequenced workflow, but the `CHANGED_FILES="..."` placeholders leave a minor gap versus fully copy-paste-ready examples.	4 / 5
Workflow Clarity	The five-step workflow has a clear sequence with a validation checkpoint at step 4 (`make agent-ci-gate`) gating step 5 verification, but the error-recovery feedback loop (what to do when the gate fails) is only implied rather than explicit.	4 / 5
Progressive Disclosure	Content is organized into clearly labeled sections with one-level-deep references to real docs (change-surfaces.md, module-boundaries.md, testing-strategy.md), but no bundled references/scripts/assets directory exists in the skill, so navigation is mostly external and the structure stops just short of the ideal overview-plus-bundle split.	4 / 5
	Total	17 / 20 Passed

Description

85%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 well-constructed: it states concrete actions, an explicit 'Use when' trigger clause, and a clearly bounded niche that separates it from sibling routing skills. Minor gains are possible only by adding a few more natural-language synonyms.

Dimension	Reasoning	Score
Specificity	Names the routing-policy domain and three concrete action areas ("matched-decision logic, candidate-model selection, and downstream looper behavior"), with only minor coverage gaps, fitting the 'several specific actions' anchor better than the single-pair anchor at 3.	4 / 5
Completeness	Explicitly answers what ("Modifies routing policy after signal extraction, including...") and when ("Use when changing decision predicates, thresholds, priorities, model ranking, cost or latency routing..."), matching the concrete-both anchor.	5 / 5
Trigger Term Quality	Covers a good range of natural trigger phrases ("decision predicates, thresholds, priorities, model ranking, cost or latency routing") users would cite, though the vocabulary is domain-specialized and a few lay synonyms are missing, placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clearly scoped niche (post-signal routing policy distinct from signal extraction and plugin hooks) with distinct triggers and minimal overlap risk, matching the clear-niche anchor.	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/routing-policy-change/SKILL.md
Commit: d8b03e3

Reviewed: ~1 hour 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.