Last commit on October 15, 2026·Created on July 2, 2026
dzhng/skills
“A framework for authoring and auditing the operational principles of AI agents”
Combined rank
#294
across all skills
Stars
1.3k
+31.2% in last 7d
Forks
84
+37.7% in last 7d
Watchers
5
+25.0% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR
This collection provides a structured methodology for building and refining agent skills. It helps automation builders define clear trigger descriptions and distinguish between core skill logic and supporting references or scripts.
The toolkit includes specialized processes for auditing agent configurations, ensuring that operational documents maintain lasting principles rather than transient session data.
WHO IT'S FOR
AI agent / automation builders
create and refine reusable agent skills
Technical leads / architects
audit AI-driven architectural decisions
Platform / DevEx teams
evaluate agent skills against golden cases
AI coding assistant power users
maintain lasting agent principles in AGENTS.md
Claude
Codex
Cursor
OpenCodeWant to install it?
Clone to Claude · Manual Copy · NPX Skills Add · Symlink to AgentRepository instructions