Skill Grader / report card

B

zj-unicom-ai/UniEmployee

Graded B on context cost and craft. 654 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #231 of 446 on the leaderboard →

Score
2.60 / 4
Resident
654 tokens
Footprint
medium
Per activation
3,344 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 20, 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/zj-unicom-ai/UniEmployee.svg)](https://seoagent.com/skill-grader/zj-unicom-ai/UniEmployee)
HTML
<a href="https://seoagent.com/skill-grader/zj-unicom-ai/UniEmployee"><img src="https://seoagent.com/skill-grader/badge/zj-unicom-ai/UniEmployee.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 2.60/4
github.com/zj-unicom-ai/UniEmployee@HEAD · 26 skills · 654t resident (medium) · 3,344t per activation · 20,481t bundle
D
Resident footprint
654t of description text ride in the system prompt of every message across 26 skills (paper's observed per-skill range: 50–280t).
B
Description honesty
Defensive padding detected: 122 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
B
Body size
Largest body is 1,618 words (~3,344t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 1 reference file(s); 4 auxiliary .md files are fetched at point of use instead of riding in the body.
A
Factoring
Scoped to a coherent procedure set.
C
CLI leverage
Prompt-only. Every rule stated in prose pays attention rent; consider a companion CLI for deterministic steps.
B overall (2.60/4). 26 skill(s), 654t resident on every message (medium), 3,344t loaded per activation. Weakest axis: resident footprint (D).

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.