MADEVAL/RankWise

SEO & marketing

Graded B on context cost and craft. 134 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #159 of 276 on the leaderboard →

Score: 2.55 / 4
Resident: 134 tokens
Footprint: light
Per activation: 13,932 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 7, 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: B](https://seoagent.com/skill-grader/badge/MADEVAL/RankWise.svg)](https://seoagent.com/skill-grader/MADEVAL/RankWise)

HTML

<a href="https://seoagent.com/skill-grader/MADEVAL/RankWise"><img src="https://seoagent.com/skill-grader/badge/MADEVAL/RankWise.svg" alt="Skill Grader: B" height="20"></a>

Report card

B overall · 2.55/4

github.com/MADEVAL/RankWise@HEAD · 1 skill · 134t resident (light) · 13,932t per activation · 55,714t bundle

Resident footprint

134t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 17 comma-separated trigger keywords; 75 words. Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.

Body size

Largest body is 8,363 words (~13,932t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

22 auxiliary .md files ship but the body never points at them — the agent won't find them.

Factoring

one skill carrying 95 sections — a monolith wearing a trigger.

CLI leverage

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

B overall (2.55/4). 1 skill(s), 134t resident on every message (light), 13,932t loaded per activation. Weakest axis: body size (D).

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.