Skill Grader / report card

B

fuwenhao12/academic-ref-inserter

  • Documents & files
  • Writing

Graded B on context cost and craft. 221 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #40 of 48 on the leaderboard →

Score
3.00 / 4
Resident
221 tokens
Footprint
light
Per activation
2,092 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 1, 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/fuwenhao12/academic-ref-inserter.svg)](https://seoagent.com/skill-grader/fuwenhao12/academic-ref-inserter)
HTML
<a href="https://seoagent.com/skill-grader/fuwenhao12/academic-ref-inserter"><img src="https://seoagent.com/skill-grader/badge/fuwenhao12/academic-ref-inserter.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 3.00/4
github.com/fuwenhao12/academic-ref-inserter@HEAD · 4 skills · 221t resident (light) · 2,092t per activation · 11,081t bundle
B
Resident footprint
221t of description text ride in the system prompt of every message across 4 skills (paper's observed per-skill range: 50–280t).
B
Description honesty
Defensive padding detected: 18 comma-separated trigger keywords; 106 words. Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
B
Body size
Largest body is 1,322 words (~2,092t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
8 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 (`arXiv`, 1 invocations + 17 shell blocks) — verification and state live in code, not prompt.
B overall (3.00/4). 4 skill(s), 221t resident on every message (light), 2,092t loaded per activation. Weakest axis: progressive disclosure (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.