Skill Grader / report card

B

alchaincyf/darwin-skill

Graded B on context cost and craft. 188 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #126 of 314 on the leaderboard →

Score
3.20 / 4
Resident
188 tokens
Footprint
light
Per activation
4,470 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/alchaincyf/darwin-skill.svg)](https://seoagent.com/skill-grader/alchaincyf/darwin-skill)
HTML
<a href="https://seoagent.com/skill-grader/alchaincyf/darwin-skill"><img src="https://seoagent.com/skill-grader/badge/alchaincyf/darwin-skill.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 3.20/4
github.com/alchaincyf/darwin-skill@HEAD · 1 skill · 188t resident (light) · 4,470t per activation · 11,675t bundle
B
Resident footprint
188t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).
B
Description honesty
Defensive padding detected: 17 comma-separated trigger keywords; 85 words. Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
B
Body size
Largest body is 2,168 words (~4,470t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 2 reference file(s); 4 auxiliary .md files are fetched at point of use instead of riding in the body.
B
Factoring
48 sections in one skill.
A
CLI leverage
Drives a CLI (`git`, 7 invocations + 1 shell blocks) — verification and state live in code, not prompt.
B overall (3.20/4). 1 skill(s), 188t resident on every message (light), 4,470t loaded per activation. Weakest axis: resident footprint (B).

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.