Skill Grader / report card

gavdalf/total-recall

Graded B on context cost and craft. 104 tokens of this skill ride in the system prompt of every message, whether or not it fires (light footprint). Last graded Sep 7, 2026; re-graded weekly from HEAD.

View on GitHub ↗Share the gradeGrade another skill
B
B overall · 3.40/4
github.com/gavdalf/total-recall@HEAD · 1 skill · 104t resident (light) · 3,421t per activation · 21,489t bundle
A
Resident footprint
104t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).
A
Description honesty
Reads as a statement of purpose, not defensive trigger padding.
B
Body size
Largest body is 1,842 words (~3,421t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
13 auxiliary .md files ship but the body never points at them — the agent won't find them.
B
Factoring
38 sections in one skill.
A
CLI leverage
Drives a CLI (`which`, 1 invocations + 5 shell blocks) — verification and state live in code, not prompt.
B overall (3.40/4). 1 skill(s), 104t resident on every message (light), 3,421t loaded per activation. Weakest axis: progressive disclosure (C).

Put the grade in your README

The badge shows the current letter grade and links back to this page. It re-renders from the latest grade, so it never goes stale when you improve the skill.

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

How this was graded

Six deterministic axes from “@skills: Attention Is All You Have” (Yin et al., 2026) and the open seo-skill-bench footprint scorer: resident footprint, description honesty, body size, progressive disclosure, factoring, and CLI leverage. Tokens are approximated as chars/4. No LLM, no signup, same result every run. Read the full methodology.