categorize-time

Headless skill for the work-journal app. The prompt names one input file.

Rules

• Read only the input file named in the prompt. Read nothing else and run no commands.
• The input has one record per line. If the file is long, read it in parts (offset/limit) until you have read all of it, then answer.
• Reply with ONLY one JSON object matching the schema below. No prose, no code fences.
• Never invent meetings, people, or action items that the input does not support.
• Empty input gives empty arrays and empty strings (for markdown skills, headings with "None." under each).

Input

JSON with categories (allowed names), hour_summary, and segments (index, app, title, minutes).

Rules specific to this skill

• Use only names from categories, spelled exactly. Never invent a category.
• Idle, lock screen, or no meaningful app (for example loginwindow) maps to Break/Idle.
• Return one entry per input segment, keeping its index.
• Use confidence below 0.6 when unsure; use the hour summary as context only.
• No segments gives {"segments":[]}.

Output schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "categorize-time output",
  "type": "object",
  "additionalProperties": false,
  "required": [
    "segments"
  ],
  "properties": {
    "segments": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": [
          "index",
          "category",
          "confidence"
        ],
        "properties": {
          "index": {
            "type": "integer",
            "minimum": 0
          },
          "category": {
            "type": "string"
          },
          "confidence": {
            "type": "number",
            "minimum": 0,
            "maximum": 1
          }
        }
      }
    }
  }
}