Skill Grader / report card

C

SNL-UCSB/paper-writing-skill

Graded C on context cost and craft. 177 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #265 of 457 on the leaderboard →

Score
2.30 / 4
Resident
177 tokens
Footprint
light
Per activation
8,727 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 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.

Skill Grader: C
Markdown
[![Skill Grader: C](https://seoagent.com/skill-grader/badge/SNL-UCSB/paper-writing-skill.svg)](https://seoagent.com/skill-grader/SNL-UCSB/paper-writing-skill)
HTML
<a href="https://seoagent.com/skill-grader/SNL-UCSB/paper-writing-skill"><img src="https://seoagent.com/skill-grader/badge/SNL-UCSB/paper-writing-skill.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.30/4
github.com/SNL-UCSB/paper-writing-skill@HEAD · 1 skill · 177t resident (light) · 8,727t per activation · 70,187t bundle
B
Resident footprint
177t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).
B
Description honesty
Defensive padding detected: 18 comma-separated trigger keywords; 99 words. Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
D
Body size
Largest body is 5,008 words (~8,727t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
32 auxiliary .md files ship but the body never points at them — the agent won't find them.
D
Factoring
one skill carrying 31 sections — a monolith wearing a trigger.
A
CLI leverage
Drives a CLI (7 shell blocks + 7 shell blocks) — verification and state live in code, not prompt.
C overall (2.30/4). 1 skill(s), 177t resident on every message (light), 8,727t loaded per activation. Weakest axis: body size (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.