Skill Grader / report card

A

maverickgao8848/mav-slide-craft-skill

  • Design & frontend
  • Documents & files

Graded A on context cost and craft. 58 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #5 of 57 on the leaderboard →

Score
3.80 / 4
Resident
58 tokens
Footprint
light
Per activation
3,539 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 3, 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.

Skill Grader: A
Markdown
[![Skill Grader: A](https://seoagent.com/skill-grader/badge/maverickgao8848/mav-slide-craft-skill.svg)](https://seoagent.com/skill-grader/maverickgao8848/mav-slide-craft-skill)
HTML
<a href="https://seoagent.com/skill-grader/maverickgao8848/mav-slide-craft-skill"><img src="https://seoagent.com/skill-grader/badge/maverickgao8848/mav-slide-craft-skill.svg" alt="Skill Grader: A" height="20"></a>

Report card

A
A overall · 3.80/4
github.com/maverickgao8848/mav-slide-craft-skill@HEAD · 1 skill · 58t resident (light) · 3,539t per activation · 67,233t bundle
A
Resident footprint
58t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).
A
Description honesty
Reads as a statement of purpose, not defensive trigger padding.
B
Body size
Largest body is 1,662 words (~3,539t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 17 reference file(s); 21 auxiliary .md files are fetched at point of use instead of riding in the body.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (`hero`, 8 invocations + 1 shell blocks) — verification and state live in code, not prompt.
A overall (3.80/4). 1 skill(s), 58t resident on every message (light), 3,539t 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.