serenity-radar

Serenity Radar

A data-driven companion to serenity-method. Where serenity-method teaches how she analyzes, this skill uses her actual 11-month archive (2025-07-02 → present, ~6,120 posts / 750 tickers) to estimate where her attention is going and to generate candidates the way she would.

What this is NOT. Not a predictor, not a buy/sell signal, not "she will pump X next." It is a candidate generator + checklist. A single account is fragile; virality ≠ correctness; her archive has survivorship bias (winners get re-cited, losers fade). Read the Caveats section before using output. Always end with: 仅作信息跟踪，不构成投资建议。

Prerequisites

• The mention archive must exist (the follow-aleabito skill produces it). Default path: $FOLLOW_ALEABITO_REPORTS_DIR/aleabito-mentions-events.csv (else the workspace reports/).
• Keep it current with follow-aleabito's incremental fetch (analyze-mentions.js --incremental --resume) before running radar, so signals reflect the latest days.
• For the analytical gate, use the local serenity-method skill.

Mode 1 — RADAR (data-driven, run this first)

Run the signal extractor:

FOLLOW_ALEABITO_REPORTS_DIR="<reports dir>" node skills/serenity-radar/scripts/radar.js --window 14 --top 20
# add --json for machine-readable output; --asof YYYY-MM-DD to evaluate a past date; --window 7 for a tighter read

It prints four signal blocks (see references/signals.md for the exact math):

• 🔥 Heating — tickers whose mention count is accelerating (recent window vs prior window). This is the core "she's ramping attention here" signal.
• 🆕 New entrants — tickers that first appeared within the window. Candidate next focus — she often seeds a name quietly, then ramps.
• 🎯 Conviction watch — high recent volume + sustained + still active. Her core book right now (defended, repeated).
• 🔄 Theme rotation — theme mention-share recent vs prior. Tells you which narrative she is rotating into / out of.