ThomasMoreAI/legal-skills-open

Documents & files
Data & research

Graded C on context cost and craft. 5,381 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #123 of 143 on the leaderboard →

Score: 1.95 / 4
Resident: 5,381 tokens
Footprint: heavy
Per activation: 4,407 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 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.

Markdown

[![Skill Grader: C](https://seoagent.com/skill-grader/badge/ThomasMoreAI/legal-skills-open.svg)](https://seoagent.com/skill-grader/ThomasMoreAI/legal-skills-open)

HTML

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

Report card

C overall · 1.95/4

github.com/ThomasMoreAI/legal-skills-open@HEAD · 40 skills · 5,381t resident (heavy) · 4,407t per activation · 114,092t bundle

Resident footprint

5,381t 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: 399 comma-separated trigger keywords; 2768 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 2,567 words (~4,407t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Body routes to 7 reference file(s); 16 auxiliary .md files are fetched at point of use instead of riding in the body.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Some CLI usage; more verification could move from prose into commands.

C overall (1.95/4). 40 skill(s), 5,381t resident on every message (heavy), 4,407t 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.