Skill Grader / report card

apache/infrastructure-actions

Graded B on context cost and craft. 0 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #74 of 161 on the leaderboard →

Score: 3.15 / 4
Resident: 0 tokens
Footprint: light
Per activation: 8,365 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 22, 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/apache/infrastructure-actions.svg)](https://seoagent.com/skill-grader/apache/infrastructure-actions)

HTML

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

Report card

B overall · 3.15/4

github.com/apache/infrastructure-actions@HEAD · 2 skills · 0t resident (light) · 8,365t per activation · 10,662t bundle

Resident footprint

0t of description text ride in the system prompt of every message across 2 skills (paper's observed per-skill range: 50–280t).

Description honesty

Reads as a statement of purpose, not defensive trigger padding.

Body size

Largest body is 4,814 words (~8,365t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Everything is inlined into a 4,814-word body with no reference layer to disclose progressively.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`gh`, 12 invocations) — verification and state live in code, not prompt.

B overall (3.15/4). 2 skill(s), 0t resident on every message (light), 8,365t loaded per activation. Weakest axis: progressive disclosure (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.