Data and caching behavior: - Raw daily K-line data, watchlist data, and portfolio data are stored in ~/.stockbuddy/stockbuddy.db (SQLite) - Positions are linked through watchlist_id - Analysis results are cached separately in SQLite with a default TTL of 10 minutes - Cache cleanup runs automatically and total cached analysis rows are capped - If the user explicitly asks to "refresh data" or "reanalyze", add --no-cache - To clear analysis cache: --clear-cache

• Interpret and present the result

Scenario 2: Batch Portfolio Analysis

Trigger examples: "analyze my portfolio", "look at my holdings", "how are my positions doing"

Default output should still be decision-first: for each position, give the action label, score/confidence, important events, event-adjusted second suggestion, and a compact practical order version. Do not expand every holding into a full long report unless the user explicitly wants a detailed version.

Steps:

• Check portfolio data

   python3 {{SKILL_DIR}}/scripts/portfolio_manager.py list
   

• If the portfolio is empty → guide the user to add positions first (see Scenario 3)

• Run batch analysis

   python3 {{SKILL_DIR}}/scripts/portfolio_manager.py analyze
   

• Interpret and present the result

Scenario 3: Position Management

Trigger examples: "add a Tencent position", "I bought 100 shares of BYD", "remove Alibaba from my holdings"

After the first successful position record, proactively guide the user to fill the missing durable facts needed for execution-aware advice. Do not stop at only code / shares / cost if important constraints are still unknown.

Ask for or help the user confirm these fields, in this priority order:

• Account context — which account this belongs to, and its market / currency
• Cash — total cash or available cash in that account
• Lot rule — lot size for the stock
• Odd-lot support — whether the broker supports odd-lot selling / buying
• Trade date — if omitted and relevant for later review
• Notes — optional thesis, time horizon, or special constraints

If some fields are already known, only ask for the missing ones. Keep the follow-up compact: confirm what was captured, state what is still missing, and ask for the missing durable facts in one short message.

If the user gives only partial follow-up info, update what is available and continue asking only for the remaining missing fields. Once enough execution constraints are known, stop prompting and proceed normally.

Scenario 4: Account and Allocation Management

Trigger examples: "my HK account has 3000 HKD cash", "track available cash", "record this under my US account", "how concentrated is my portfolio"

Rules:

• Keep cash, account, market, and currency as durable facts
• Keep position weights, market value, and unrealized P&L as computed fields
• If the user has multiple markets or currencies, treat them as separate account contexts unless the user explicitly wants cross-account aggregation
• Use account information to improve practical trading advice: whether the user can afford a new lot, whether a rebalance is even possible, and whether the trade would increase concentration too much

Scenario 5: Watchlist Management

Trigger examples: "watch Tencent", "add Apple to my watchlist", "remove Moutai from watchlist"

Analysis Methodology

The scoring system combines technicals (roughly 60% weight) and basic valuation (roughly 40% weight). Final score range is approximately -10 to +10:

When deciding the final output format, choosing between default query vs full report, or generating practical order suggestions, prefer references/output_templates.md. It defines the default query template, atomic templates, full-report composition rules, and the conservative / balanced / aggressive order-price generation rules (balanced is the default).

Important Notes

• All analysis is for reference only and is not investment advice
• The primary data source is Tencent Finance, which may have delays, gaps, or field limitations
• Hong Kong stocks do not have the same daily price-limit structure as A-shares and therefore carry higher intraday volatility risk
• Every final analysis output must include a risk disclaimer
• Technical analysis can fail during extreme market conditions
• Encourage the user to combine macro conditions, sector trends, and company fundamentals in final decision-making
• Only store user-confirmed durable facts in the database; latest price, market value, unrealized P&L, and position weight should be fetched or calculated at analysis time

Resource Files