Skill Grader / report card

marmelab/react-admin

Graded C on context cost and craft. 237 tokens of this skill ride in the system prompt of every message, whether or not it fires (light footprint). Last graded Sep 9, 2026; re-graded weekly from HEAD.

View on GitHub ↗Share the grade Grade another skill

C overall · 2.35/4

github.com/marmelab/react-admin@HEAD · 2 skills · 237t resident (light) · 4,769t per activation · 7,498t bundle

Resident footprint

237t of description text ride in the system prompt of every message across 2 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 22 comma-separated trigger keywords; 121 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 2,471 words (~4,769t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Everything is inlined into a 2,471-word body with no reference layer to disclose progressively.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Prompt-only. Every rule stated in prose pays attention rent; consider a companion CLI for deterministic steps.

C overall (2.35/4). 2 skill(s), 237t resident on every message (light), 4,769t loaded per activation. Weakest axis: progressive disclosure (D).

Put the grade in your README

The badge shows the current letter grade and links back to this page. It re-renders from the latest grade, so it never goes stale when you improve the skill.

Markdown

[![Skill Grader: C](https://seoagent.com/skill-grader/badge/marmelab/react-admin.svg)](https://seoagent.com/skill-grader/marmelab/react-admin)

HTML

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

How this was graded

Six deterministic axes from “@skills: Attention Is All You Have” (Yin et al., 2026) and the open seo-skill-bench footprint scorer: resident footprint, description honesty, body size, progressive disclosure, factoring, and CLI leverage. Tokens are approximated as chars/4. No LLM, no signup, same result every run. Read the full methodology.