config-platform-change

Synchronizes config representations across router config, Python CLI schema, and dashboard config UI. Use when adding or changing a config concept that spans those surfaces or addressing config representation debt before Kubernetes-facing translation.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./tools/agent/skills/config-platform-change/SKILL.md

Quality

Content

78%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, actionable, well-structured skill body with concrete commands and clear validation gates. Its main weakness is progressive disclosure: the Must Read references point to files that are not present in the bundle.

Suggestions

Add the referenced docs (change-surfaces.md, module-boundaries.md) to a references/ directory, or remove/fix the links so navigation is not dangling.

Add an explicit 'if a gate fails, fix the mismatch and re-run the gate' feedback step to close the workflow loop.

Tighten the abstract workflow steps (e.g., 'Modify the config concept across all touched surfaces') into concrete sub-steps keyed to each surface.

Dimension	Reasoning	Score
Conciseness	Lean, well-organized body with no padding and no over-explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Concrete executable `make` commands with exact arguments, specific Must Read paths, and explicit gotchas; a couple of workflow steps ('Modify the config concept across all touched surfaces') stay abstract, keeping it below 5.	4 / 5
Workflow Clarity	Five-step sequenced workflow with explicit validation gates (`make agent-report`, `make agent-ci-gate`) and a debt-recording step; lacks a spelled-out 'if validation fails, fix and re-run' feedback loop, so below 5.	4 / 5
Progressive Disclosure	Sections are well-organized and references are one level deep and clearly signaled, but the referenced files (change-surfaces.md, module-boundaries.md) do not exist in the bundle, so the actual navigation target is dangling.	3 / 5
	Total	16 / 20 Passed

Description

67%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 clear, mostly specific description that explicitly covers both what and when, with a well-scoped niche. It is held back by jargon-heavy trigger phrasing that blunts naturalness and synonym coverage.

Suggestions

Add plain-language trigger terms and synonyms (e.g., 'config option', 'config field', 'CLI flag', 'dashboard setting') alongside the internal jargon so users would naturally say them.

Spell out one or two more concrete actions (e.g., 'add, rename, or remove a config field') to lift specificity toward 5.

Soften 'Kubernetes-facing translation' and 'indexed debt' in the trigger clause or move them to the body, keeping the description's 'when' crisp.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Synchronizes config representations across router config, Python CLI schema, and dashboard config UI') with the three specific surfaces; not a list of multiple discrete actions, so below 5.	4 / 5
Completeness	Explicitly states both what ('Synchronizes config representations across...') and when ('Use when adding or changing a config concept...'); the 'when' is present and concrete but jargon-laden rather than crisp, so below 5.	4 / 5
Trigger Term Quality	Has a natural-ish trigger ('Use when adding or changing a config concept') but leans heavily on internal jargon ('router config', 'Kubernetes-facing translation', 'indexed debt') and misses common synonyms; below 4.	3 / 5
Distinctiveness Conflict Risk	Targets a distinct multi-surface config-sync niche unlikely to fire for unrelated skills, with only minor overlap risk against closely related config skills.	4 / 5
	Total	15 / 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: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: vllm-project/semantic-router
Path: tools/agent/skills/config-platform-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.