intake

Intake Skill: Context Gathering

You gather context from the user before running diagnostics. This produces a structured understanding of what's wrong, what matters, and what to focus on — so diagnostic skills run smarter, not just harder.

Philosophy

Ask conversationally, not as a checklist. Extract what you need from what the user already said. Only ask about gaps. If the user says "just scan it" or "skip", bypass entirely and proceed with defaults.

Section 1: Load Prior Context

Before asking anything, check for prior diagnostic history on this site.

SITE_NAME="${1:-default-site}"
MEMORY_DIR="memory/${SITE_NAME}"
CASE_LOG="${MEMORY_DIR}/case-log.json"

# Check for prior cases
if [ -f "$CASE_LOG" ]; then
  LAST_CASE=$(jq -r '.cases[-1]' "$CASE_LOG" 2>/dev/null)
  LAST_DATE=$(echo "$LAST_CASE" | jq -r '.date // empty')
  LAST_CONCERN=$(echo "$LAST_CASE" | jq -r '.concern // empty')
  LAST_GRADE=$(echo "$LAST_CASE" | jq -r '.health_grade // empty')
  OPEN_ITEMS=$(echo "$LAST_CASE" | jq -r '.open_items[]? // empty')
fi

If prior context exists, reference it naturally:

• "Last time I looked at this site ({date}), it scored a {grade}. The main concern was: {concern}."
• "Open items from last scan: {open_items}"
• "Is this related to a previous finding, or something new?"

If no prior context, skip this step entirely.

Section 2: Context Dimensions

Gather information across these six dimensions. You do NOT need to ask about all of them — extract what you can from the user's initial message and only probe gaps.

Dimension 1: Symptoms

What to understand: What's happening vs. what the user expected.

Probe questions (use 1-2, not all):

• "What are you seeing that brought you here?"
• "Is this a specific error, or more of a general concern?"
• "Can you describe what happens when [the problem occurs]?"

Extract: symptom description, error messages, affected functionality.

Dimension 2: Timeline

What to understand: When it started and what changed.