Skill Grader / report card

C

KyaniteLabs/kinocut

  • Images & media
  • Agents & automation

Graded C on context cost and craft. 226 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #99 of 152 on the leaderboard →

Score
2.45 / 4
Resident
226 tokens
Footprint
light
Per activation
5,621 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.

Skill Grader: C
Markdown
[![Skill Grader: C](https://seoagent.com/skill-grader/badge/KyaniteLabs/kinocut.svg)](https://seoagent.com/skill-grader/KyaniteLabs/kinocut)
HTML
<a href="https://seoagent.com/skill-grader/KyaniteLabs/kinocut"><img src="https://seoagent.com/skill-grader/badge/KyaniteLabs/kinocut.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.45/4
github.com/KyaniteLabs/kinocut@HEAD · 5 skills · 226t resident (light) · 5,621t per activation · 13,489t bundle
B
Resident footprint
226t of description text ride in the system prompt of every message across 5 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 29 comma-separated trigger keywords; 123 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
C
Body size
Largest body is 2,887 words (~5,621t), loaded on every trigger. Corpus median 921, p90 2207.
D
Progressive disclosure
Everything is inlined into a 2,887-word body with no reference layer to disclose progressively.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (`kino`, 10 invocations + 14 shell blocks) — verification and state live in code, not prompt.
C overall (2.45/4). 5 skill(s), 226t resident on every message (light), 5,621t loaded per activation. Weakest axis: progressive disclosure (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.