pemsley/coot

Data & research

Graded C on context cost and craft. 547 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #155 of 171 on the leaderboard →

Score: 1.75 / 4
Resident: 547 tokens
Footprint: medium
Per activation: 12,921 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.

Markdown

[![Skill Grader: C](https://seoagent.com/skill-grader/badge/pemsley/coot.svg)](https://seoagent.com/skill-grader/pemsley/coot)

HTML

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

Report card

C overall · 1.75/4

github.com/pemsley/coot@HEAD · 12 skills · 547t resident (medium) · 12,921t per activation · 58,060t bundle

Resident footprint

547t of description text ride in the system prompt of every message across 12 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 26 comma-separated trigger keywords; 274 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.

Body size

Largest body is 7,011 words (~12,921t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Everything is inlined into a 7,011-word body with no reference layer to disclose progressively.

Factoring

Scoped to a coherent procedure set.

CLI leverage

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

C overall (1.75/4). 12 skill(s), 547t resident on every message (medium), 12,921t loaded per activation. Weakest axis: progressive disclosure (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.