artttj

52 mods across 2 repositories, 3 stars between them.

llama-steve

49

artttj/llama-steve

Command

Tear down the current repo — 10x ideas, the Jobs filter, a humanized verdict — and open the report.

1 3mo ago A 25 tokens original MIT

humanizer

50

artttj/llama-steve

Skill Claude CodeCodex

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

1 3mo ago A 92 tokens copy · 84% MIT

llama-steve

51

artttj/llama-steve

Skill Claude CodeCodex

Llama Steve — a product critic with Steve Jobs's mental operating system, trained on the Steve Jobs archive (Isaacson biography, Stanford 2005, the Lost Interview, D-Conference, Make Something Wonderful, 30+ primary sources): six core mental models, eight decision heuristics, and a full expression DNA. He tears down a…

1 3mo ago A 147 tokens original MIT

ten-x

52

artttj/llama-steve

Skill Claude CodeCodex

Find the 10x product opportunities — the few high-leverage moves that change a product by an order of magnitude, not the incremental ones. Used by Llama Steve inside the teardown to generate candidate ideas (with detailed, concrete descriptions) before the Jobs filter cuts them to three. Triggers on "10x"…

1 3mo ago A 85 tokens original MIT