Skill Grader / report card

luongnv89/claude-howto

Graded C on context cost and craft. 1,810 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #242 of 314 on the leaderboard →

Score: 2.00 / 4
Resident: 1,810 tokens
Footprint: heavy
Per activation: 5,956 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.

Markdown

[![Skill Grader: C](https://seoagent.com/skill-grader/badge/luongnv89/claude-howto.svg)](https://seoagent.com/skill-grader/luongnv89/claude-howto)

HTML

<a href="https://seoagent.com/skill-grader/luongnv89/claude-howto"><img src="https://seoagent.com/skill-grader/badge/luongnv89/claude-howto.svg" alt="Skill Grader: C" height="20"></a>

Report card

C overall · 2.00/4

github.com/luongnv89/claude-howto@HEAD · 40 skills · 1,810t resident (heavy) · 5,956t per activation · 142,618t bundle

Resident footprint

1,810t of description text ride in the system prompt of every message across 40 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 116 comma-separated trigger keywords; 1079 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 3,550 words (~5,956t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Body routes to 16 reference file(s); 50 auxiliary .md files are fetched at point of use instead of riding in the body.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`claude`, 7 invocations + 35 shell blocks) — verification and state live in code, not prompt.

C overall (2.00/4). 40 skill(s), 1,810t resident on every message (heavy), 5,956t 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.