You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: profile/README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -31,7 +31,7 @@ graph LR
31
31
32
32
### The Effector Type System
33
33
34
-
Our [analysis of 13,729 ClawHub skills](https://github.com/effectorHQ/clawhub-analysis) found a **67% agent failure rate** — driven by untyped interfaces, missing prerequisites, and permission mismatches.
34
+
Our [analysis of 13,729 ClawHub skills](https://github.com/effectorHQ/clawhub-analysis) found a **67% agent failure rate**: driven by untyped interfaces, missing prerequisites, and permission mismatches.
35
35
36
36
The core thesis: AI agent capabilities need types. Today you chain two skills and pray they work. Tomorrow you type-check the composition before a single token is spent. This is the paradigm we're building.
0 commit comments