Skill Grader / report card

xiaopu-ai/web-design

Graded A on context cost and craft. 70 tokens of this skill ride in the system prompt of every message, whether or not it fires (light footprint). Last graded Sep 14, 2026; re-graded weekly from HEAD.

View on GitHub ↗Share the grade Grade another skill

A overall · 3.80/4

github.com/xiaopu-ai/web-design@HEAD · 1 skill · 70t resident (light) · 2,874t per activation · 252,813t bundle

Resident footprint

70t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).

Description honesty

Reads as a statement of purpose, not defensive trigger padding.

Body size

Largest body is 1,673 words (~2,874t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Body routes to 9 reference file(s); 70 auxiliary .md files are fetched at point of use instead of riding in the body.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`const`, 1 invocations + 3 shell blocks) — verification and state live in code, not prompt.

A overall (3.80/4). 1 skill(s), 70t resident on every message (light), 2,874t loaded per activation. Weakest axis: body size (B).

Put the grade in your README

The badge shows the current letter grade and links back to this page. It re-renders from the latest grade, so it never goes stale when you improve the skill.

Markdown

[![Skill Grader: A](https://seoagent.com/skill-grader/badge/xiaopu-ai/web-design.svg)](https://seoagent.com/skill-grader/xiaopu-ai/web-design)

HTML

<a href="https://seoagent.com/skill-grader/xiaopu-ai/web-design"><img src="https://seoagent.com/skill-grader/badge/xiaopu-ai/web-design.svg" alt="Skill Grader: A" height="20"></a>

How this was graded

Six deterministic axes from “@skills: Attention Is All You Have” (Yin et al., 2026) and the open seo-skill-bench footprint scorer: resident footprint, description honesty, body size, progressive disclosure, factoring, and CLI leverage. Tokens are approximated as chars/4. No LLM, no signup, same result every run. Read the full methodology.