Skill Grader / report card

A

assafkip/research-mode

  • Data & research
  • Agents & automation

Graded A on context cost and craft. 42 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #17 of 43 on the leaderboard →

Score
3.60 / 4
Resident
42 tokens
Footprint
light
Per activation
793 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Sep 30, 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: A
Markdown
[![Skill Grader: A](https://seoagent.com/skill-grader/badge/assafkip/research-mode.svg)](https://seoagent.com/skill-grader/assafkip/research-mode)
HTML
<a href="https://seoagent.com/skill-grader/assafkip/research-mode"><img src="https://seoagent.com/skill-grader/badge/assafkip/research-mode.svg" alt="Skill Grader: A" height="20"></a>

Report card

A
A overall · 3.60/4
github.com/assafkip/research-mode@HEAD · 1 skill · 42t resident (light) · 793t per activation · 2,419t bundle
A
Resident footprint
42t 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.
A
Body size
Largest body is 516 words (~793t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
2 auxiliary .md files ship but the body never points at them — the agent won't find them.
A
Factoring
Scoped to a coherent procedure set.
C
CLI leverage
Prompt-only. Every rule stated in prose pays attention rent; consider a companion CLI for deterministic steps.
A overall (3.60/4). 1 skill(s), 42t resident on every message (light), 793t loaded per activation. Weakest axis: progressive disclosure (C).

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.