From ee9d05a4ad65c73e4888a0be5370c09afbd654df Mon Sep 17 00:00:00 2001
From: Eve <eve@ai.cowbay.org>
Date: Thu, 16 Apr 2026 16:51:00 +0800
Subject: [PATCH] skills: use kal field placeholders

---
 skills/kal/SKILL.md | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/skills/kal/SKILL.md b/skills/kal/SKILL.md
index 33034e0..1741e1d 100644
--- a/skills/kal/SKILL.md
+++ b/skills/kal/SKILL.md
@@ -9,22 +9,16 @@ 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, use a friendly intake reply: one short lead-in sentence plus the same 4-line template, followed by short field guidance.
+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, with the field guidance written inside the quotes as placeholder text.
 
 Default wording:
 
 ```text
 好，我先幫你把 KAL 開題格式立起來。
-topic: ""
-seed: ""
-goal: ""
-scope: ""
-
-說明：
-- topic：你想研究的主題是什麼
-- seed：先給我起始材料，例如網址 / repo / 關鍵字 / 文件
-- goal：你最後想得到什麼，例如摘要 / 比較 / 評估 / 決策建議
-- scope：要納入或排除什麼範圍
+topic: "你想研究的主題是什麼"
+seed: "先給我起始材料，例如網址 / repo / 關鍵字 / 文件"
+goal: "你最後想得到什麼，例如摘要 / 比較 / 評估 / 決策建議"
+scope: "要納入或排除什麼範圍"
 ```
 
 Keep the lead-in short and natural. Do not add analysis yet.
@@ -38,13 +32,12 @@ Keep the lead-in short and natural. Do not add analysis yet.
 
 ## Response rules
 
-- If the user only says `啟動KAL`, return one short friendly lead-in sentence plus the 4-line template and short field explanations.
-- 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, and keep the short explanations.
+- If the user only says `啟動KAL`, return one short friendly lead-in sentence plus the 4-line template with placeholder guidance inside the quotes.
+- If the user gives some fields but not all, return the same template with known values filled in and missing ones left as friendly placeholder guidance.
 - 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.
-- If the user explicitly asks how to fill the fields, always include the explanation block.
-- If the user explicitly asks for raw copy-paste format only, you may omit the explanation block.
+- If the user explicitly asks for raw copy-paste format only, you may omit the placeholder guidance and leave empty strings.
 
 ## Filled-template behavior
 
@@ -65,8 +58,8 @@ If the user appears to be drafting or unsure, stop after the normalized template
 Only use light defaults when necessary:
 
 - If `seed` is a URL and `topic` is missing, infer a short topic from the URL target if obvious.
-- If `goal` is missing, leave it empty instead of guessing.
-- If `scope` is missing, leave it empty instead of guessing.
+- If `goal` is missing, leave it as placeholder guidance instead of guessing.
+- If `scope` is missing, leave it as placeholder guidance instead of guessing.
 
 ## KAL run behavior
 
@@ -95,7 +88,8 @@ goal: "..."
 scope: "..."
 ```
 
-- The explanation block belongs below the 4 fields by default.
-- For chat surfaces, short bullets are preferred over tables.
+- When information is missing, prefer placeholder text inside the quotes rather than a separate explanation block.
+- For chat surfaces, this placeholder style is preferred because it feels like a pre-filled form.
 - Do not turn intake into a long questionnaire.
-- Keep it to one short lead-in, the 4 fields, and brief field hints.
+- Keep it to one short lead-in and the 4 fields.
+- Do not pre-fill missing fields with invented research content; only use short writing guidance as placeholders.