skills: make kal intake friendlier

This commit is contained in:
Eve
2026-04-16 16:45:14 +08:00
parent 86c2d2764f
commit 1c16de7122

View File

@@ -9,15 +9,20 @@ When this skill triggers, first collect the minimum input needed for a KAL run,
## Primary behavior ## 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 ```text
好,我先幫你把 KAL 開題格式立起來。
topic: "" topic: ""
seed: "" seed: ""
goal: "" goal: ""
scope: "" scope: ""
``` ```
Keep the lead-in short and natural. Do not add analysis yet.
## Field meanings ## Field meanings
- `topic`: the subject, concept, repo, framework, or question area - `topic`: the subject, concept, repo, framework, or question area
@@ -27,8 +32,8 @@ scope: ""
## Response rules ## Response rules
- If the user only says `啟動KAL`, return the 4-line template. - 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. - 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. - 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. - Keep the intake step lightweight.
- Do not add unnecessary analysis before the intake is clear. - Do not add unnecessary analysis before the intake is clear.