gsd-build/gsd-browser

Agents & automation
Debugging & testing

Graded C on context cost and craft. 340 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #19 of 20 on the leaderboard →

Score: 2.30 / 4
Resident: 340 tokens
Footprint: medium
Per activation: 7,293 tokens

Re-grade now →View on GitHub ↗Share the grade Grade another skillLast graded Sep 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/gsd-build/gsd-browser.svg)](https://seoagent.com/skill-grader/gsd-build/gsd-browser)

HTML

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

Report card

C overall · 2.30/4

github.com/gsd-build/gsd-browser@HEAD · 2 skills · 340t resident (medium) · 7,293t per activation · 50,107t bundle

Resident footprint

340t of description text ride in the system prompt of every message across 2 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 46 comma-separated trigger keywords; 201 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 3,492 words (~7,293t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

15 auxiliary .md files ship but the body never points at them — the agent won't find them.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`gsd-browser`, 10 invocations + 48 shell blocks) — verification and state live in code, not prompt.

C overall (2.30/4). 2 skill(s), 340t resident on every message (medium), 7,293t loaded per activation. Weakest axis: resident footprint (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.