petar-nauka/fact-check-skill

Data & research

Graded B on context cost and craft. 184 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #30 of 43 on the leaderboard →

Score: 3.20 / 4
Resident: 184 tokens
Footprint: light
Per activation: 1,692 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Sep 30, 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/petar-nauka/fact-check-skill.svg)](https://seoagent.com/skill-grader/petar-nauka/fact-check-skill)

HTML

<a href="https://seoagent.com/skill-grader/petar-nauka/fact-check-skill"><img src="https://seoagent.com/skill-grader/badge/petar-nauka/fact-check-skill.svg" alt="Skill Grader: B" height="20"></a>

Report card

B overall · 3.20/4

github.com/petar-nauka/fact-check-skill@HEAD · 1 skill · 184t resident (light) · 1,692t per activation · 11,993t bundle

Resident footprint

184t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 32 comma-separated trigger keywords; 90 words. Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.

Body size

Largest body is 927 words (~1,692t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Body routes to 10 reference file(s); 12 auxiliary .md files are fetched at point of use instead of riding in the body.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Prompt-only. Every rule stated in prose pays attention rent; consider a companion CLI for deterministic steps.

B overall (3.20/4). 1 skill(s), 184t resident on every message (light), 1,692t loaded per activation. Weakest axis: cli leverage (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.