zy-zmc/tianming-skill

Writing
Memory & context

Graded A on context cost and craft. 52 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #15 of 35 on the leaderboard →

Score: 3.60 / 4
Resident: 52 tokens
Footprint: light
Per activation: 1,814 tokens

Re-grade now →View on GitHub ↗Share the grade Grade another skillLast graded Sep 27, 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: A](https://seoagent.com/skill-grader/badge/zy-zmc/tianming-skill.svg)](https://seoagent.com/skill-grader/zy-zmc/tianming-skill)

HTML

<a href="https://seoagent.com/skill-grader/zy-zmc/tianming-skill"><img src="https://seoagent.com/skill-grader/badge/zy-zmc/tianming-skill.svg" alt="Skill Grader: A" height="20"></a>

Report card

A overall · 3.60/4

github.com/zy-zmc/tianming-skill@HEAD · 1 skill · 52t resident (light) · 1,814t per activation · 25,844t bundle

Resident footprint

52t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).

Description honesty

Reads as a statement of purpose, not defensive trigger padding.

Body size

Largest body is 741 words (~1,814t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

31 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

Prompt-only. Every rule stated in prose pays attention rent; consider a companion CLI for deterministic steps.

A overall (3.60/4). 1 skill(s), 52t resident on every message (light), 1,814t loaded per activation. Weakest axis: progressive disclosure (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.