From 1c16de71223750c412c0184895f7f98078e059e9 Mon Sep 17 00:00:00 2001
From: Eve <eve@ai.cowbay.org>
Date: Thu, 16 Apr 2026 16:45:14 +0800
Subject: [PATCH] skills: make kal intake friendlier

---
 skills/kal/SKILL.md | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/skills/kal/SKILL.md b/skills/kal/SKILL.md
index d854792..5b42619 100644
--- a/skills/kal/SKILL.md
+++ b/skills/kal/SKILL.md
@@ -9,15 +9,20 @@ When this skill triggers, first collect the minimum input needed for a KAL run,
 
 ## Primary behavior
 
-If the user says only `啟動KAL` or gives an incomplete kickoff, reply with exactly this template and nothing extra except a short intro line if needed:
+If the user says only `啟動KAL` or gives an incomplete kickoff, use a friendly intake reply: one short lead-in sentence plus the same 4-line template.
+
+Default wording:
 
 ```text
+好，我先幫你把 KAL 開題格式立起來。
 topic: ""
 seed: ""
 goal: ""
 scope: ""
 ```
 
+Keep the lead-in short and natural. Do not add analysis yet.
+
 ## Field meanings
 
 - `topic`: the subject, concept, repo, framework, or question area
@@ -27,8 +32,8 @@ scope: ""
 
 ## Response rules
 
-- If the user only says `啟動KAL`, return the 4-line template.
-- If the user gives some fields but not all, return the same template with known values filled in and missing ones left empty.
+- If the user only says `啟動KAL`, return one short friendly lead-in sentence plus the 4-line template.
+- If the user gives some fields but not all, return the same template with known values filled in and missing ones left empty; a short natural lead-in is allowed.
 - If the user provides enough information, normalize it into the 4-line template and then proceed with the KAL workflow.
 - Keep the intake step lightweight.
 - Do not add unnecessary analysis before the intake is clear.