Skill Grader / report card

C

danoszz/penthera

Graded C on context cost and craft. 836 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #271 of 457 on the leaderboard →

Score
2.30 / 4
Resident
836 tokens
Footprint
medium
Per activation
7,979 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/danoszz/penthera.svg)](https://seoagent.com/skill-grader/danoszz/penthera)
HTML
<a href="https://seoagent.com/skill-grader/danoszz/penthera"><img src="https://seoagent.com/skill-grader/badge/danoszz/penthera.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.30/4
github.com/danoszz/penthera@HEAD · 7 skills · 836t resident (medium) · 7,979t per activation · 306,208t bundle
D
Resident footprint
836t of description text ride in the system prompt of every message across 7 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 74 comma-separated trigger keywords; 549 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 4,731 words (~7,979t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 28 reference file(s); 94 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 (`penthera`, 66 invocations + 60 shell blocks) — verification and state live in code, not prompt.
C overall (2.30/4). 7 skill(s), 836t resident on every message (medium), 7,979t 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.