Skill Grader / report card

C

conorbronsdon/avoid-ai-writing

Graded C on context cost and craft. 676 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #206 of 332 on the leaderboard →

Score
2.30 / 4
Resident
676 tokens
Footprint
medium
Per activation
8,079 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 14, 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/conorbronsdon/avoid-ai-writing.svg)](https://seoagent.com/skill-grader/conorbronsdon/avoid-ai-writing)
HTML
<a href="https://seoagent.com/skill-grader/conorbronsdon/avoid-ai-writing"><img src="https://seoagent.com/skill-grader/badge/conorbronsdon/avoid-ai-writing.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.30/4
github.com/conorbronsdon/avoid-ai-writing@HEAD · 9 skills · 676t resident (medium) · 8,079t per activation · 225,581t bundle
D
Resident footprint
676t of description text ride in the system prompt of every message across 9 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 62 comma-separated trigger keywords; 380 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
C
Body size
Largest body is 4,827 words (~8,079t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 19 reference file(s); 111 auxiliary .md files are fetched at point of use instead of riding in the body.
A
Factoring
Scoped to a coherent procedure set.
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). 9 skill(s), 676t resident on every message (medium), 8,079t loaded per activation. Weakest axis: resident footprint (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.