Skill Grader / report card

B

kaankiziltug/logo-design-skill

Graded B on context cost and craft. 257 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #147 of 314 on the leaderboard →

Score
2.90 / 4
Resident
257 tokens
Footprint
light
Per activation
4,109 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 13, 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: B
Markdown
[![Skill Grader: B](https://seoagent.com/skill-grader/badge/kaankiziltug/logo-design-skill.svg)](https://seoagent.com/skill-grader/kaankiziltug/logo-design-skill)
HTML
<a href="https://seoagent.com/skill-grader/kaankiziltug/logo-design-skill"><img src="https://seoagent.com/skill-grader/badge/kaankiziltug/logo-design-skill.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 2.90/4
github.com/kaankiziltug/logo-design-skill@HEAD · 1 skill · 257t resident (light) · 4,109t per activation · 36,670t bundle
B
Resident footprint
257t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 38 comma-separated trigger keywords; 145 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
C
Body size
Largest body is 2,406 words (~4,109t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 14 reference file(s); 15 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 (3 shell blocks + 3 shell blocks) — verification and state live in code, not prompt.
B overall (2.90/4). 1 skill(s), 257t resident on every message (light), 4,109t loaded per activation. Weakest axis: description honesty (C).

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.