Skill Grader / report card

C

sepehr071/awesome-iran-mcp

  • Agents & automation
  • Data & research

Graded C on context cost and craft. 1,246 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #97 of 124 on the leaderboard →

Score
2.25 / 4
Resident
1,246 tokens
Footprint
heavy
Per activation
1,206 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 18, 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: C
Markdown
[![Skill Grader: C](https://seoagent.com/skill-grader/badge/sepehr071/awesome-iran-mcp.svg)](https://seoagent.com/skill-grader/sepehr071/awesome-iran-mcp)
HTML
<a href="https://seoagent.com/skill-grader/sepehr071/awesome-iran-mcp"><img src="https://seoagent.com/skill-grader/badge/sepehr071/awesome-iran-mcp.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.25/4
github.com/sepehr071/awesome-iran-mcp@HEAD · 23 skills · 1,246t resident (heavy) · 1,206t per activation · 18,066t bundle
F
Resident footprint
1,246t of description text ride in the system prompt of every message across 23 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 96 comma-separated trigger keywords; 700 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
A
Body size
Largest body is 693 words (~1,206t), loaded on every trigger. Corpus median 921, p90 2207.
B
Progressive disclosure
Single-file skill small enough to need no reference layer.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (`claude`, 23 invocations) — verification and state live in code, not prompt.
C overall (2.25/4). 23 skill(s), 1,246t resident on every message (heavy), 1,206t 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.