sag skill: add chat voice response guidance

When Peter asks for voice replies, generate audio with sag and send via MEDIA:

pnpm-lock.yaml

@@ -3755,11 +3755,11 @@ snapshots:
       - utf-8-validate
       - vite
 
-  '@vitest/browser-preview@4.0.16(vite@8.0.0-beta.3(@types/node@25.0.3)(jiti@2.6.1)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)':
+  '@vitest/browser-preview@4.0.16(vite@7.3.0(@types/node@25.0.3)(jiti@2.6.1)(lightningcss@1.30.2)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)':
     dependencies:
       '@testing-library/dom': 10.4.1
       '@testing-library/user-event': 14.6.1(@testing-library/dom@10.4.1)
-      '@vitest/browser': 4.0.16(vite@8.0.0-beta.3(@types/node@25.0.3)(jiti@2.6.1)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)
+      '@vitest/browser': 4.0.16(vite@7.3.0(@types/node@25.0.3)(jiti@2.6.1)(lightningcss@1.30.2)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)
       vitest: 4.0.16(@types/node@25.0.3)(@vitest/browser-playwright@4.0.16)(@vitest/browser-preview@4.0.16)(jiti@2.6.1)(lightningcss@1.30.2)(tsx@4.21.0)(yaml@2.8.2)
     transitivePeerDependencies:
       - bufferutil
@@ -5522,8 +5522,8 @@ snapshots:
       why-is-node-running: 2.3.0
     optionalDependencies:
       '@types/node': 25.0.3
-      '@vitest/browser-playwright': 4.0.16(playwright@1.57.0)(vite@8.0.0-beta.3(@types/node@25.0.3)(jiti@2.6.1)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)
-      '@vitest/browser-preview': 4.0.16(vite@8.0.0-beta.3(@types/node@25.0.3)(jiti@2.6.1)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)
+      '@vitest/browser-playwright': 4.0.16(playwright@1.57.0)(vite@7.3.0(@types/node@25.0.3)(jiti@2.6.1)(lightningcss@1.30.2)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)
+      '@vitest/browser-preview': 4.0.16(vite@7.3.0(@types/node@25.0.3)(jiti@2.6.1)(lightningcss@1.30.2)(tsx@4.21.0)(yaml@2.8.2))(vitest@4.0.16)
     transitivePeerDependencies:
       - jiti
       - less

skills/sag/SKILL.md

@@ -41,3 +41,22 @@ Voice defaults
 - `ELEVENLABS_VOICE_ID` or `SAG_VOICE_ID`
 
 Confirm voice + speaker before long output.
+
+## Chat voice responses
+
+When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:
+
+```bash
+# Generate audio file
+sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"
+
+# Then include in reply:
+# MEDIA:/tmp/voice-reply.mp3
+```
+
+Voice character tips:
+- Crazy scientist: Use `[excited]` tags, dramatic pauses `[short pause]`, vary intensity
+- Calm: Use `[whispers]` or slower pacing
+- Dramatic: Use `[sings]` or `[shouts]` sparingly
+
+Default voice for Clawd: `lj2rcrvANS3gaWWnczSX` (or just `-v Clawd`)

src/canvas-host/a2ui/.bundle.hash

@@ -1 +1 @@
-ac7d607313f8977b3fd7b5807201e0bf79d2c7366dbeff48747352d55cd3b253
+debc115fd2b264d3b3090e28b733551ca5f7532287d827c13fc579e5a7a95b9d