routing-calibration-loop

Calibrates routing changes against a live router endpoint with executable probes, local DSL validation, versioned deploys, and structured failure review. Use when tuning signals, projections, decisions, or maintained route examples against a real apiserver.

Quality

90%

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

88%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 highly actionable, well-sequenced calibration loop with concrete commands and strong validation/feedback checkpoints throughout. Conciseness and progressive disclosure are slightly below full marks due to minor cross-section redundancy and the absence of bundle files for content splitting.

Suggestions

Reduce redundancy between the Trigger, Stop Conditions, and Gotchas sections — several cautions (e.g., not declaring success on a single passing probe, capturing deploy versions) are restated across sections.

Consider extracting the per-step detail of the Workflow into a reference file, keeping SKILL.md as a tighter overview with one-level-deep links, to improve progressive disclosure.

Tighten Gotchas entries that restate Workflow cautions (e.g., the PUT /config/router complete-document point overlaps with step 6) to recover token budget.

Dimension	Reasoning	Score
Conciseness	Mostly lean and imperative, assuming Claude's competence without explaining basic concepts, but there is minor redundancy between the Trigger, Gotchas, and Workflow sections that could be tightened.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands ('python3 tools/agent/scripts/router_calibration_loop.py eval ...', 'make agent-report ...') plus concrete endpoints and file paths covering the common cases.	5 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit validation checkpoints — local 'sr-dsl validate', 'wait for GET /ready to return ready=true', before/after probe comparison — plus a three-bucket failure-classification feedback loop and version-capture/rollback guardrails.	5 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep 'Must Read' references to repo assets, but all operational detail lives inline in SKILL.md with no bundle files to split content further.	4 / 5
	Total	18 / 20 Passed

Description

92%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 that answers both what and when with concrete actions and trigger phrases in proper third-person voice. Trigger terms are domain-appropriate but slightly jargon-heavy, keeping trigger_term_quality just below full marks.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'executable probes, local DSL validation, versioned deploys, and structured failure review' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly states both what ('Calibrates routing changes against a live router endpoint...') and when ('Use when tuning signals, projections, decisions...') with concrete trigger phrases, in third-person voice.	5 / 5
Trigger Term Quality	'Use when tuning signals, projections, decisions, or maintained route examples against a real apiserver' provides good domain-natural trigger terms, though they are somewhat jargon-heavy and lack synonyms or file extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — live router apiserver calibration — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: 6 suspicious	Warning

	Total	14 / 16 Passed

Repository: vllm-project/semantic-router
Path: tools/agent/skills/maintainer/routing-calibration/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.