Skill Grader / report card

D

emilkowalski/skills

Graded D on context cost and craft. 2,179 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #424 of 434 on the leaderboard →

Score
1.45 / 4
Resident
2,179 tokens
Footprint
heavy
Per activation
10,506 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 19, 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: D
Markdown
[![Skill Grader: D](https://seoagent.com/skill-grader/badge/emilkowalski/skills.svg)](https://seoagent.com/skill-grader/emilkowalski/skills)
HTML
<a href="https://seoagent.com/skill-grader/emilkowalski/skills"><img src="https://seoagent.com/skill-grader/badge/emilkowalski/skills.svg" alt="Skill Grader: D" height="20"></a>

Report card

D
D overall · 1.45/4
github.com/emilkowalski/skills@HEAD · 20 skills · 2,179t resident (heavy) · 10,506t per activation · 88,577t bundle
F
Resident footprint
2,179t of description text ride in the system prompt of every message across 20 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 196 comma-separated trigger keywords; 1307 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
D
Body size
Largest body is 6,011 words (~10,506t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
9 auxiliary .md files ship but the body never points at them — the agent won't find them.
A
Factoring
Scoped to a coherent procedure set.
B
CLI leverage
Some CLI usage; more verification could move from prose into commands.
D overall (1.45/4). 20 skill(s), 2,179t resident on every message (heavy), 10,506t loaded per activation. Weakest axis: resident footprint (F).

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.