kurrent-io/kcap-cli

Agents & automation
Memory & context

Graded C on context cost and craft. 1,939 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #130 of 133 on the leaderboard →

Score: 1.55 / 4
Resident: 1,939 tokens
Footprint: heavy
Per activation: 7,366 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 19, 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: C](https://seoagent.com/skill-grader/badge/kurrent-io/kcap-cli.svg)](https://seoagent.com/skill-grader/kurrent-io/kcap-cli)

HTML

<a href="https://seoagent.com/skill-grader/kurrent-io/kcap-cli"><img src="https://seoagent.com/skill-grader/badge/kurrent-io/kcap-cli.svg" alt="Skill Grader: C" height="20"></a>

Report card

C overall · 1.55/4

github.com/kurrent-io/kcap-cli@HEAD · 14 skills · 1,939t resident (heavy) · 7,366t per activation · 39,612t bundle

Resident footprint

1,939t of description text ride in the system prompt of every message across 14 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 136 comma-separated trigger keywords; 1268 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 4,439 words (~7,366t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Everything is inlined into a 4,439-word body with no reference layer to disclose progressively.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`kcap`, 102 invocations + 14 shell blocks) — verification and state live in code, not prompt.

C overall (1.55/4). 14 skill(s), 1,939t resident on every message (heavy), 7,366t 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.