Your agent skills should improve themselves
What if coding agents (Claude Code, Codex, Warp, etc) could improve Skills by reviewing past conversations?
Here's the three step loop:
- Score conversations from criteria you define
- Isolate failures
- Generate skill improvements
0:00 Why agents need self-improvement loops
0:25 Three-step scoring system
1:12 Configuring a code quality scorer
2:14 Self-improvement agents
3:13 Closing the loop
Here's the three step loop:
- Score conversations from criteria you define
- Isolate failures
- Generate skill improvements
0:00 Why agents need self-improvement loops
0:25 Three-step scoring system
1:12 Configuring a code quality scorer
2:14 Self-improvement agents
3:13 Closing the loop
Warp
Warp is the terminal with AI and your dev team's knowledge built-in.
...