Skip to content

hktitan/kheskills

unversioned · 5168196f9e01MIT

Harshit Khemani's 19 agent skills: UI craft, design tokens, SVG, stickers, diagrams, sound, launch films, demos, packaging, the poteto pyramid, a content engine, and brains that answer from one source's public work with the source named. Start with khe-auto.

khe-poteto-pyramid

Puts every correction you give a coding agent at the highest layer of Lauren Tan's poteto pyramid that can hold it (the codebase, then lints, types and CI, then verification, then a line of prose, with human review last), builds the fix there, proves the check fails on a real past mistake, and deletes the instruction it replaces. Also sweeps a repo's history for repeated mistakes, triages an AGENTS.md or CLAUDE.md into checks and judgment calls, and audits how far agents can be trusted to merge. Use when someone says "the agent keeps doing X", "where should this fix live", "turn this into a lint", "stop it writing this again", "our AGENTS.md is too long", "can we let agents merge", "all code is slop", or names the poteto pyramid. For UI review use khe-ui, for a recording of the app khe-demo, for design corrections turned into taste rules learn-taste (Emil Kowalski). When unsure, khe-auto.

Version
1.1.0
License
MIT
Read SKILL.md at the source

Pinned to revision 5168196f9e01, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.