Skill Grader / report card

InternScience/DrClaw

Graded C on context cost and craft. 2,816 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #116 of 181 on the leaderboard →

Score: 2.25 / 4
Resident: 2,816 tokens
Footprint: heavy
Per activation: 1,951 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 24, 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/InternScience/DrClaw.svg)](https://seoagent.com/skill-grader/InternScience/DrClaw)

HTML

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

Report card

C overall · 2.25/4

github.com/InternScience/DrClaw@HEAD · 40 skills · 2,816t resident (heavy) · 1,951t per activation · 41,335t bundle

Resident footprint

2,816t of description text ride in the system prompt of every message across 40 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 86 comma-separated trigger keywords; 1385 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 836 words (~1,951t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Single-file skill small enough to need no reference layer.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (4 shell blocks + 4 shell blocks) — verification and state live in code, not prompt.

C overall (2.25/4). 40 skill(s), 2,816t resident on every message (heavy), 1,951t 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.