Skill Grader / report card

C

mhattingpete/claude-skills-marketplace

Graded C on context cost and craft. 1,157 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #262 of 394 on the leaderboard →

Score
2.10 / 4
Resident
1,157 tokens
Footprint
heavy
Per activation
1,186 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 17, 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/mhattingpete/claude-skills-marketplace.svg)](https://seoagent.com/skill-grader/mhattingpete/claude-skills-marketplace)
HTML
<a href="https://seoagent.com/skill-grader/mhattingpete/claude-skills-marketplace"><img src="https://seoagent.com/skill-grader/badge/mhattingpete/claude-skills-marketplace.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.10/4
github.com/mhattingpete/claude-skills-marketplace@HEAD · 18 skills · 1,157t resident (heavy) · 1,186t per activation · 47,996t bundle
F
Resident footprint
1,157t of description text ride in the system prompt of every message across 18 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 97 comma-separated trigger keywords; 573 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
A
Body size
Largest body is 668 words (~1,186t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
11 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 (`make`, 3 invocations + 9 shell blocks) — verification and state live in code, not prompt.
C overall (2.10/4). 18 skill(s), 1,157t resident on every message (heavy), 1,186t loaded per activation. Weakest axis: resident footprint (F).

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.