prime-skills/runcomfy-agent-skills

Images & media

Graded D on context cost and craft. 5,893 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #169 of 171 on the leaderboard →

Score: 1.45 / 4
Resident: 5,893 tokens
Footprint: heavy
Per activation: 7,088 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 23, 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: D](https://seoagent.com/skill-grader/badge/prime-skills/runcomfy-agent-skills.svg)](https://seoagent.com/skill-grader/prime-skills/runcomfy-agent-skills)

HTML

<a href="https://seoagent.com/skill-grader/prime-skills/runcomfy-agent-skills"><img src="https://seoagent.com/skill-grader/badge/prime-skills/runcomfy-agent-skills.svg" alt="Skill Grader: D" height="20"></a>

Report card

D overall · 1.45/4

github.com/prime-skills/runcomfy-agent-skills@HEAD · 30 skills · 5,893t resident (heavy) · 7,088t per activation · 95,598t bundle

Resident footprint

5,893t of description text ride in the system prompt of every message across 30 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 469 comma-separated trigger keywords; 3413 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 2,963 words (~7,088t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Everything is inlined into a 2,963-word body with no reference layer to disclose progressively.

Factoring

description claims to replace multiple skills.

CLI leverage

Drives a CLI (`runcomfy`, 92 invocations + 165 shell blocks) — verification and state live in code, not prompt.

D overall (1.45/4). 30 skill(s), 5,893t resident on every message (heavy), 7,088t 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.