News for hackers. Stuff that matters.
Re:Agent Skill to Force Docs in ASD-STE100 Simplified Techni... by jpease on Thursday July 30, 2026 @06:16PM (#49116577)
I like the idea, but not sold on the skill.

But did lead to me finding https://vale.sh and its various available linters. Might give that a try.

Re:Agent Skill to Force Docs in ASD-STE100 Simplified Techni... by aurareturn on Friday July 31, 2026 @01:42AM (#49119403)
How would one use Vale in LLM documentation?
Re:Agent Skill to Force Docs in ASD-STE100 Simplified Techni... by dymk on Friday July 31, 2026 @02:14AM (#49119594)
Precommit hook
Re:Agent Skill to Force Docs in ASD-STE100 Simplified Techni... by tbhb on Friday July 31, 2026 @10:41AM (#49123801)
I use it with a rule package that has a variety of Vale styles for AI writing tells (github.com/tbhb/vale-ai-tells). Typically I have it set up in a project and then gate the agent with post tool use hooks and pre-commit hooks. It's far from perfect but it does help eliminate a lot of the common tells.
Re:Agent Skill to Force Docs in ASD-STE100 Simplified Techni... by lab14 on Friday July 31, 2026 @11:53AM (#49124656)
STE is part of the training set, so the skill is redundant and only pollutes your context window.