Don't scroll to bottm when sending message on mobile

web/agent/skills/investigate-first/SKILL.md

@@ -0,0 +1,14 @@
+---
+description: "Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses."
+---
+# Investigate first
+
+Gather evidence before changing product code.
+
+- Separate observed symptom from inferred cause.
+- Trace inputs, state transitions, ownership boundaries, and failure output.
+- Rank hypotheses by evidence and cheap falsification value.
+- Do not edit until one credible mechanism explains evidence.
+- Stop exploration when evidence is sufficient to name cause or exact blocker.
+
+Report cause and proof. Make no fix unless task authorizes implementation.

web/agent/skills/investigate-first/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Investigate First"
+  short_description: "Find credible cause before editing code"
+  default_prompt: "Use $investigate-first to diagnose this failure before proposing edits."