Skill Grader / report card

D

Team-Commonly/commonly

Graded D on context cost and craft. 2,785 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #450 of 457 on the leaderboard →

Score
1.40 / 4
Resident
2,785 tokens
Footprint
heavy
Per activation
16,246 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 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.

Skill Grader: D
Markdown
[![Skill Grader: D](https://seoagent.com/skill-grader/badge/Team-Commonly/commonly.svg)](https://seoagent.com/skill-grader/Team-Commonly/commonly)
HTML
<a href="https://seoagent.com/skill-grader/Team-Commonly/commonly"><img src="https://seoagent.com/skill-grader/badge/Team-Commonly/commonly.svg" alt="Skill Grader: D" height="20"></a>

Report card

D
D overall · 1.40/4
github.com/Team-Commonly/commonly@HEAD · 26 skills · 2,785t resident (heavy) · 16,246t per activation · 171,978t bundle
F
Resident footprint
2,785t of description text ride in the system prompt of every message across 26 skills (paper's observed per-skill range: 50–280t).
F
Description honesty
Defensive padding detected: 276 comma-separated trigger keywords; 5 shouted imperatives (ALWAYS/NEVER/MUST…); 1604 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
D
Body size
Largest body is 9,793 words (~16,246t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 2 reference file(s); 54 auxiliary .md files are fetched at point of use instead of riding in the body.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (`officecli`, 187 invocations + 240 shell blocks) — verification and state live in code, not prompt.
D overall (1.40/4). 26 skill(s), 2,785t resident on every message (heavy), 16,246t 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.