The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe

SkillOpt

A collection of 2 posts
SoftSkill Compresses Agent Skills Into 32 Virtual Tokens — and Shows Where That Trick Breaks
ai-models

SoftSkill Compresses Agent Skills Into 32 Virtual Tokens — and Shows Where That Trick Breaks

Markdown skills are one of the more sensible things agent platforms have converged on. They are readable, reviewable, portable, and cheap to author. They are also long, repeatedly injected, and interpreted from scratch by a model that may or may not translate prose into the behavior you intended. The obvious
19 Jun 2026 4 min read
SkillOpt Treats Agent Skills Like Trainable Infrastructure, Not Prompt Folklore
ai-models

SkillOpt Treats Agent Skills Like Trainable Infrastructure, Not Prompt Folklore

Agent skills are about to have their dependency-lockfile moment. For the last two years, most teams have treated agent instructions as artisanal prompt craft: a little policy in the system prompt, a little tool advice in a README, a few tribal rules buried in Slack, and one engineer who knows
25 May 2026 5 min read
Page 1 of 1
The LGTM © 2026
  • Sign up
Powered by Ghost