Skill Grader / report card

B

yinnho/aginxbrowser

  • Agents & automation
  • Data & research

Graded B on context cost and craft. 286 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #94 of 152 on the leaderboard →

Score
2.50 / 4
Resident
286 tokens
Footprint
medium
Per activation
2,336 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 21, 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/yinnho/aginxbrowser.svg)](https://seoagent.com/skill-grader/yinnho/aginxbrowser)
HTML
<a href="https://seoagent.com/skill-grader/yinnho/aginxbrowser"><img src="https://seoagent.com/skill-grader/badge/yinnho/aginxbrowser.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 2.50/4
github.com/yinnho/aginxbrowser@HEAD · 1 skill · 286t resident (medium) · 2,336t per activation · 177,036t bundle
C
Resident footprint
286t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 43 comma-separated trigger keywords; 171 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
B
Body size
Largest body is 1,237 words (~2,336t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
92 auxiliary .md files ship but the body never points at them — the agent won't find them.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (3 shell blocks + 3 shell blocks) — verification and state live in code, not prompt.
B overall (2.50/4). 1 skill(s), 286t resident on every message (medium), 2,336t loaded per activation. Weakest axis: resident footprint (C).

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.