Skill Grader / report card

C

GarethManning/education-agent-skills

  • Agents & automation
  • Writing

Graded C on context cost and craft. 2,256 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #156 of 171 on the leaderboard →

Score
1.70 / 4
Resident
2,256 tokens
Footprint
heavy
Per activation
8,774 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 23, 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: C
Markdown
[![Skill Grader: C](https://seoagent.com/skill-grader/badge/GarethManning/education-agent-skills.svg)](https://seoagent.com/skill-grader/GarethManning/education-agent-skills)
HTML
<a href="https://seoagent.com/skill-grader/GarethManning/education-agent-skills"><img src="https://seoagent.com/skill-grader/badge/GarethManning/education-agent-skills.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 1.70/4
github.com/GarethManning/education-agent-skills@HEAD · 40 skills · 2,256t resident (heavy) · 8,774t per activation · 225,825t bundle
F
Resident footprint
2,256t of description text ride in the system prompt of every message across 40 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 53 comma-separated trigger keywords; 1022 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 5,187 words (~8,774t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 3 reference file(s); 3 auxiliary .md files are fetched at point of use instead of riding in the body.
A
Factoring
Scoped to a coherent procedure set.
C
CLI leverage
Prompt-only. Every rule stated in prose pays attention rent; consider a companion CLI for deterministic steps.
C overall (1.70/4). 40 skill(s), 2,256t resident on every message (heavy), 8,774t 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.