i-feel-lucky

One press, one pick. The "luck" is fully engineered: a three-pass sweep (screener + earnings catalysts + big movers) builds the pool, 4-dimension scoring crowns a single winner, and a fresh-data deep dive delivers an 8-section report with buy/abandon triggers. US by default; HK/CN on request. TRIGGER when: user asks for a daily/fresh stock idea without naming a ticker.

Company analysisValuation

Creator

zwayπŸ’

Created time

Jul 15, 2026

Last update

Jul 21, 2026

Version

V2

Usage

2 Installs Β· 7 Runs

How it works

I Feel Lucky β€” One Stock Pick Per Run

Produce exactly ONE stock recommendation per run, selected by an objective, repeatable algorithm β€” never by recalling past picks from memory. Every figure in the final report must trace to a data result fetched during THIS run.

Language: respond in the language the user is using in the conversation. Market scope: US equities ONLY by default. Widen to HK or CN only if the user explicitly asked for that market in this invocation. CN picks are informational only (no paper-trading support).


Step 1 β€” Account context (dynamic, never hardcoded)

Identify ONE target account in the scoped market β€” the account this pick would actually be traded in. Selection order: (a) the account the user named or clearly implied in this invocation; (b) otherwise the account whose mandate/playbook best matches the scoped market and theme; (c) if still ambiguous, the most actively managed strategy account in that market. If the runtime context already lists accounts, use it and skip list. For that single account only, fetch summary, positions, and read_playbook β€” as parallel calls in one response. Do NOT deep-fetch every account. The report's

Driven wordmark