Skill Grader / report card

PyModel/css-pro-tips

Graded A on context cost and craft. 73 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Not on the leaderboard — it lists public repos with 25+ stars.

Score: 3.75 / 4
Resident: 73 tokens
Footprint: light
Per activation: 3,091 tokens

Re-grade now →View on GitHub ↗Share the grade Grade another skillLast graded Sep 26, 2026 from HEAD

Add the badge to your README

It shows the current letter grade and links back to this page. Improve the skill, hit Re-grade now, and the badge follows — GitHub may keep the old image for up to an hour.

Markdown

[![Skill Grader: A](https://seoagent.com/skill-grader/badge/PyModel/css-pro-tips.svg)](https://seoagent.com/skill-grader/PyModel/css-pro-tips)

HTML

<a href="https://seoagent.com/skill-grader/PyModel/css-pro-tips"><img src="https://seoagent.com/skill-grader/badge/PyModel/css-pro-tips.svg" alt="Skill Grader: A" height="20"></a>

Report card

A overall · 3.75/4

github.com/PyModel/css-pro-tips@HEAD · 1 skill · 73t resident (light) · 3,091t per activation · 51,991t bundle

Resident footprint

73t 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 1,552 words (~3,091t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Body routes to 13 reference file(s); 30 auxiliary .md files are fetched at point of use instead of riding in the body.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Some CLI usage; more verification could move from prose into commands.

A overall (3.75/4). 1 skill(s), 73t resident on every message (light), 3,091t loaded per activation. Weakest axis: body size (B).

Six deterministic axes, no LLM, same result every run. Tokens are approximated as chars/4. Read the methodology, or see how SEO skills score on task outcomes in the open SEO skill benchmark.