Skill Grader / report card

deanpeters/Product-Manager-Skills

Graded C on context cost and craft. 1,841 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #286 of 314 on the leaderboard →

Score: 1.70 / 4
Resident: 1,841 tokens
Footprint: heavy
Per activation: 7,713 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 13, 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/deanpeters/Product-Manager-Skills.svg)](https://seoagent.com/skill-grader/deanpeters/Product-Manager-Skills)

HTML

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

Report card

C overall · 1.70/4

github.com/deanpeters/Product-Manager-Skills@HEAD · 40 skills · 1,841t resident (heavy) · 7,713t per activation · 251,980t bundle

Resident footprint

1,841t 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: 100 comma-separated trigger keywords; 997 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 4,283 words (~7,713t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

74 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 (12 shell blocks + 12 shell blocks) — verification and state live in code, not prompt.

C overall (1.70/4). 40 skill(s), 1,841t resident on every message (heavy), 7,713t 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.