Skill Grader / report card

B

chen0416ccc-cpu/codex-windows-fast-patch-skill

  • Coding workflow

Graded B on context cost and craft. 248 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #150 of 293 on the leaderboard →

Score
2.70 / 4
Resident
248 tokens
Footprint
light
Per activation
34,509 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 10, 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/chen0416ccc-cpu/codex-windows-fast-patch-skill.svg)](https://seoagent.com/skill-grader/chen0416ccc-cpu/codex-windows-fast-patch-skill)
HTML
<a href="https://seoagent.com/skill-grader/chen0416ccc-cpu/codex-windows-fast-patch-skill"><img src="https://seoagent.com/skill-grader/badge/chen0416ccc-cpu/codex-windows-fast-patch-skill.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 2.70/4
github.com/chen0416ccc-cpu/codex-windows-fast-patch-skill@HEAD · 1 skill · 248t resident (light) · 34,509t per activation · 130,003t bundle
B
Resident footprint
248t 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: 22 comma-separated trigger keywords; 113 words. Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
F
Body size
Largest body is 17,534 words (~34,509t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 11 reference file(s); 17 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 (`codex`, 19 invocations) — verification and state live in code, not prompt.
B overall (2.70/4). 1 skill(s), 248t resident on every message (light), 34,509t loaded per activation. Weakest axis: body size (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.