Stats
Links
Categories
Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions that point the model at the destination on every token.
npx claudepluginhub kingbootoshi/directional-promptingWrite prompts, system instructions, agent directives, and skill descriptions using two stacked layers: outcome-first (goal, success criteria, stopping condition) plus directional language (every sentence names the path with positive verbs).
Matt Pocock's skills for real engineering, as an installable Claude Code plugin.
Plugins by Alex Newman (thedotmack)
Ultra-compressed communication mode for Claude Code. Cuts 65% of output tokens (measured) while keeping full technical accuracy.