Skill Grader / report card

C

MichelKerkmeester/skilled-agent-harness_spec-driven-loops

  • Agents & automation
  • Coding workflow

Graded C on context cost and craft. 1,276 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #138 of 161 on the leaderboard →

Score
1.80 / 4
Resident
1,276 tokens
Footprint
heavy
Per activation
14,864 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Oct 22, 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/MichelKerkmeester/skilled-agent-harness_spec-driven-loops.svg)](https://seoagent.com/skill-grader/MichelKerkmeester/skilled-agent-harness_spec-driven-loops)
HTML
<a href="https://seoagent.com/skill-grader/MichelKerkmeester/skilled-agent-harness_spec-driven-loops"><img src="https://seoagent.com/skill-grader/badge/MichelKerkmeester/skilled-agent-harness_spec-driven-loops.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 1.80/4
github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops@HEAD · 40 skills · 1,276t resident (heavy) · 14,864t per activation · 287,707t bundle
F
Resident footprint
1,276t of description text ride in the system prompt of every message across 40 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 70 comma-separated trigger keywords; 570 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 7,898 words (~14,864t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 238 reference file(s); 12 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 (`cupt`, 76 invocations + 51 shell blocks) — verification and state live in code, not prompt.
C overall (1.80/4). 40 skill(s), 1,276t resident on every message (heavy), 14,864t 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.