ryan4yin/nix-config

DevOps & infra
Debugging & testing

Graded B on context cost and craft. 309 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #95 of 152 on the leaderboard →

Score: 2.50 / 4
Resident: 309 tokens
Footprint: medium
Per activation: 3,252 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 21, 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.

Markdown

[![Skill Grader: B](https://seoagent.com/skill-grader/badge/ryan4yin/nix-config.svg)](https://seoagent.com/skill-grader/ryan4yin/nix-config)

HTML

<a href="https://seoagent.com/skill-grader/ryan4yin/nix-config"><img src="https://seoagent.com/skill-grader/badge/ryan4yin/nix-config.svg" alt="Skill Grader: B" height="20"></a>

Report card

B overall · 2.50/4

github.com/ryan4yin/nix-config@HEAD · 11 skills · 309t resident (medium) · 3,252t per activation · 20,842t bundle

Resident footprint

309t of description text ride in the system prompt of every message across 11 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 28 comma-separated trigger keywords; 172 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.

Body size

Largest body is 1,778 words (~3,252t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

1 auxiliary .md files ship but the body never points at them — the agent won't find them.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`just`, 74 invocations + 25 shell blocks) — verification and state live in code, not prompt.

B overall (2.50/4). 11 skill(s), 309t resident on every message (medium), 3,252t loaded per activation. Weakest axis: resident footprint (C).

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.