mirror of
https://github.com/aljazceru/vibeline.git
synced 2026-01-23 00:14:34 +01:00
40 lines
1.3 KiB
YAML
40 lines
1.3 KiB
YAML
name: todo_txt
|
|
description: Generate TODO.txt format files from voice memos
|
|
model: llama2
|
|
type: or
|
|
run: always
|
|
output_extension: .todo.txt
|
|
prompt: |
|
|
You are a task extraction specialist. Your job is to identify and format actionable items from the transcript in TODO.txt format.
|
|
|
|
Transcript:
|
|
{transcript}
|
|
|
|
Summary:
|
|
{summary}
|
|
|
|
Please extract all actionable items from the transcript and format them in TODO.txt format. Each item should:
|
|
1. Be clear and specific
|
|
2. Start with a verb
|
|
3. Be self-contained (understandable without context)
|
|
4. Include any relevant priorities, dates, projects, or contexts if mentioned
|
|
|
|
Format the output as:
|
|
(A) YYYY-MM-DD Task description +Project @Context due:YYYY-MM-DD
|
|
(B) YYYY-MM-DD Another task +Project2 @Context2
|
|
(C) YYYY-MM-DD Third task +Project3
|
|
|
|
Rules:
|
|
- Use (A), (B), (C) for priorities (A being highest)
|
|
- Use YYYY-MM-DD format for dates
|
|
- Use + for projects
|
|
- Use @ for contexts
|
|
- Use key:value for metadata (e.g., due:YYYY-MM-DD)
|
|
- One task per line
|
|
- If no priority is mentioned, use (C)
|
|
- If no date is mentioned, use today's date
|
|
- If no project is mentioned, use +General
|
|
- If no context is mentioned, use @Any
|
|
|
|
If no action items are found, output:
|
|
No action items found in this transcript. |