Skill Grader / report card

C

UiPath/skills

Graded C on context cost and craft. 4,530 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #383 of 394 on the leaderboard →

Score
1.50 / 4
Resident
4,530 tokens
Footprint
heavy
Per activation
17,040 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/UiPath/skills.svg)](https://seoagent.com/skill-grader/UiPath/skills)
HTML
<a href="https://seoagent.com/skill-grader/UiPath/skills"><img src="https://seoagent.com/skill-grader/badge/UiPath/skills.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 1.50/4
github.com/UiPath/skills@HEAD · 40 skills · 4,530t resident (heavy) · 17,040t per activation · 431,265t bundle
F
Resident footprint
4,530t of description text ride in the system prompt of every message across 40 skills (paper's observed per-skill range: 50–280t).
D
Description honesty
Defensive padding detected: 374 comma-separated trigger keywords; 2 shouted imperatives (ALWAYS/NEVER/MUST…); 2233 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
D
Body size
Largest body is 9,211 words (~17,040t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 203 reference file(s); 80 auxiliary .md files are fetched at point of use instead of riding in the body.
B
Factoring
description claims to replace multiple skills.
A
CLI leverage
Drives a CLI (`uip`, 504 invocations + 73 shell blocks) — verification and state live in code, not prompt.
C overall (1.50/4). 40 skill(s), 4,530t resident on every message (heavy), 17,040t 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.