General skillAI and agent development
skill-master
Find, create, run, and improve agent skills from real execution feedback.
- Stars
- 4
- Forks
- 0
- Updated
- Updated Jul 5, 2026
MIT
Find, create, run, and improve agent skills from real execution feedback.
Skill Master searches local, GitHub, and web sources for a skill that matches a task, and can research and create one when no suitable option exists. It executes the selected skill, reviews what actually happened against the instructions, and updates the skill only when divergences appear. Later feedback can repair the current output and refine the originating skill together.
Resource types
Use cases
Platforms
Runtime
Turn detailed business processes into reusable, tested AI skills.
Define portable task-specific sub-agents in Markdown for several coding assistants.
Public GitHub facts last synced Jul 10, 2026.
Reduce LLM token use by pruning context, caching prompts, and routing models.
Surface unknowns and assumptions before an AI agent starts building.