Portfolio Management Skill

Parse $ARGUMENTS to determine the command, then execute the corresponding command below.

Execution Command

bash

python3 /Users/kikuchihiroyuki/stock-skills/.claude/skills/stock-portfolio/scripts/run_portfolio.py <command> [args]

Command List

snapshot -- Portfolio Snapshot

Generate a portfolio snapshot including current price, profit/loss, and currency conversion.

bash

python3 .../run_portfolio.py snapshot

buy -- Add Purchase Record

bash

python3 .../run_portfolio.py buy --symbol <sym> --shares <n> --price <p> [--currency JPY] [--date YYYY-MM-DD] [--memo text] [--yes]

Omitting

--yes

(

-y

) will display a confirmation preview of the purchase details and exit. Specifying

--yes

skips confirmation and directly records the purchase (KIK-444).

sell -- Add Sale Record

bash

python3 .../run_portfolio.py sell --symbol <sym> --shares <n> [--price <sale-price>] [--date YYYY-MM-DD] [--yes]

Omitting

--yes

(

-y

) will display a confirmation preview of the sale details (acquisition price, estimated realized profit/loss) and exit. Specifying

--yes

skips confirmation and directly records the sale (KIK-444).

When

--price

is specified, it calculates and displays realized profit/loss, profit/loss ratio, and after-tax estimate, then saves to

data/history/trade/*.json

(KIK-441).

review -- Trade Performance Review (KIK-441)

Aggregate and display profit/loss statistics from past sale records (those recorded with

--price

bash

python3 .../run_portfolio.py review [--year 2026] [--symbol NVDA]

Output Content:

Transaction History Table (Symbol, Sale Date, Shares Held, Acquisition Price, Sale Price, Holding Period, Realized Profit/Loss, Profit/Loss Ratio)
Statistics (Number of Transactions, Win Rate, Average Return, Average Holding Period, Total Realized Profit/Loss)

analyze -- Structural Analysis

Calculate HHI (Herfindahl-Hirschman Index) for region/sector/currency/size to analyze portfolio bias. 4-axis analysis including size-based composition table (Large/Mid/Small/ETF/Unknown) (KIK-438, KIK-469 P2: ETF Classification). ETFs are independently categorized as sector "ETF" and size "ETF".

bash

python3 .../run_portfolio.py analyze

health -- Health Check

Check if the investment hypothesis for held securities is still valid. Output 3-level alerts based on multiple axes of technical analysis (SMA50/200, RSI, Golden Cross/Dead Cross detection) and fundamental analysis (Change Score, Shareholder Return Stability). Sensitivity is automatically increased for small-cap stocks (KIK-438).

bash

python3 .../run_portfolio.py health

Technical Analysis (KIK-356/374/438):

Trend determination for SMA50/200 (Uptrend/Sideways/Downtrend)
Golden Cross/Dead Cross Detection: Detect cross events with a 60-day lookback, display occurrence date and elapsed days
Small-Cap Cross Lookback Shortening (KIK-438): For small-cap stocks, use lookback=30 days to detect recent fluctuations early

Shareholder Return Stability (KIK-403):

Evaluate stability based on total return ratio of dividends + share buybacks (✅Stable High Return/📈Increasing Trend/⚠️Temporary High Return/📉Decreasing Trend)
Temporary High Return → Promoted to early warning
Decreasing Trend → Add reason to alert details
Use total return ratio (dividends + share buybacks) for long-term suitability assessment

Small-Cap Allocation (KIK-438):

Classify each security by market capitalization (Large/Mid/Small/Unknown) and display
```
[Small-Cap]
```
badge
Small-cap stocks automatically escalate from EARLY_WARNING to CAUTION
Calculate the small-cap ratio of the entire portfolio, display warning if >25%, danger if >35%

ETF Health Check (KIK-469 Phase 2):

Display separate tables for individual stocks and ETFs
ETF Table: Symbol, Profit/Loss, Trend, Expense Ratio, AUM, ETF Score, Alert
Individual Stock Table: As before (Quality of Change, Long-Term Suitability, Return Stability)

Alert Levels:

Early Warning: Break below SMA50 / Sharp RSI decline / Deterioration of 1 change score indicator / Temporary High Return
Caution: SMA50 approaching SMA200 + indicator deterioration / Deterioration of multiple change score indicators / Escalation of small-cap EARLY_WARNING
Exit: Dead Cross detected / Trend collapse + change score deterioration

adjust -- Portfolio Adjustment Advisor (KIK-496)

Generate specific adjustment actions (SELL/SWAP/ADD/TRIM_CLASS/FLAG) using 17 rules (P1-P10: Position-specific, F1-F7: Portfolio-wide) based on health check results + market regime determination.

bash

python3 .../run_portfolio.py adjust [--full]

CLI Options:

```
--full
```
: Full analysis mode (includes concentration and correlation analysis. High API load)

Output:

Market Regime (bull/bear/crash/neutral) — Determined from SMA50/200, RSI, drawdown
Action Table by HIGH/MEDIUM/LOW Priority (Action Type/Target/Reason/Rule ID)
Summary (Number of Actions)

Regime Correction: In crash regime, increase urgency by 1 level. In bear regime, prioritize rules for small-cap stocks and downtrend sectors.

rebalance -- Rebalancing Proposal

Analyze current portfolio structure and present proposals to reduce concentration risk and adjust to target allocation.

bash

python3 .../run_portfolio.py rebalance [options]

CLI Options:

--strategy defensive|balanced|aggressive

(Default: balanced)

```
--reduce-sector SECTOR
```
(Example: Technology)
```
--reduce-currency CURRENCY
```
(Example: USD)
```
--max-single-ratio RATIO
```
(Example: 0.15)
```
--max-sector-hhi HHI
```
(Example: 0.25)
```
--max-region-hhi HHI
```
(Example: 0.30)
```
--additional-cash AMOUNT
```
(JPY, Example: 1000000)
```
--min-dividend-yield YIELD
```
(Example: 0.03)

forecast -- Estimated Return

Estimate 12-month expected returns for each held security in 3 scenarios (Optimistic/Base/Pessimistic) based on analyst target prices or historical return distribution. Includes value trap warnings and TOP/BOTTOM rankings.

bash

python3 .../run_portfolio.py forecast

Estimation Methods:

Analyst Method: Analyst target price + dividend yield + share buyback yield (including shareholder returns)
Historical Return Method: For securities without analyst coverage such as ETFs, estimate using historical CAGR + standard deviation (KIK-469 P2: ETFs display annual volatility +
```
[ETF]
```
badge)
Industry Catalyst Adjustment (KIK-433, when connected to Neo4j): Add number of recent
```
growth_driver
```
catalysts in the same sector × 1.7% to optimistic scenario, subtract number of
```
risk
```
catalysts × 1.7% from pessimistic scenario (capped at 10% each)

Output Structure (KIK-390):

Portfolio-wide 3-scenario return and profit/loss table
Watchlist Section (Aggregate securities with value trap warnings)
Expected Return TOP 3 / BOTTOM 3 Rankings
Security-specific details (Analyst Target/Forward PER/Number of News/X Sentiment/3 Scenarios)

what-if -- What-If Simulation (KIK-376 / KIK-451)

Simulate adding/selling/swapping securities and display the impact on the portfolio with Before/After comparison.

bash

# Add only (Traditional)
python3 .../run_portfolio.py what-if --add "SYMBOL:SHARES:PRICE[,...]"

# Swap (Sell then Buy) (KIK-451)
python3 .../run_portfolio.py what-if --remove "SYMBOL:SHARES[,...]" --add "SYMBOL:SHARES:PRICE[,...]"

# Sell only simulation (KIK-451)
python3 .../run_portfolio.py what-if --remove "SYMBOL:SHARES[,...]"

CLI Options:

```
--add
```
: List of securities to add (optional). Format: Comma-separated
```
SYMBOL:SHARES:PRICE
```
```
--remove
```
: List of securities to sell (optional). Format: Comma-separated
```
SYMBOL:SHARES
```
(price not required, calculated at market price)
Either
```
--add
```
or
```
--remove
```
is required

Output:

[When Selling] Context of Sale Candidates (KIK-470): When
```
--remove
```
is specified, automatically display screening appearance count, investment notes, and research history before simulation (when connected to Neo4j)
Before/After comparison of sector HHI, region HHI, currency HHI
Basic information of added securities (PER/PBR/Dividend Yield/ROE)
[When Swapping] Sale Security Table (Symbol, Shares, Estimated Sale Proceeds)
[When Swapping] Cash Flow (Required Purchase Funds / Estimated Sale Proceeds / Difference)
[When Swapping] Sale Security Health Check (Alert status of sale targets)
Judgment label: Recommended / Consider with Caution / Not Recommended (e.g., "This swap is recommended" for swaps)
ETF Quality Evaluation (KIK-469 P2): When adding ETFs, reflect ETF score in judgment (Warning if quality is low <40, Good if ≥75)

backtest -- Backtesting

Verify returns from accumulated screening results and compare with benchmarks (Nikkei 225/S&P500).

bash

python3 .../run_portfolio.py backtest [options]

CLI Options:

```
--preset PRESET
```
: Screening preset to verify (Example: alpha, value)
```
--region REGION
```
: Region to verify (Example: jp, us)
```
--days N
```
: Verify returns for N days after acquisition (Default: 90)

Output:

Daily returns by screening date
Benchmark comparison (Excess Return)
Win Rate, Average Return, Maximum Return/Maximum Loss

simulate -- Compound Interest Simulation

Simulate future asset growth using compound interest based on the current portfolio. Calculate compound interest using forecast expected returns + dividend reinvestment + monthly contributions, display in 3 scenarios (Optimistic/Base/Pessimistic).

bash

python3 .../run_portfolio.py simulate [options]

CLI Options:

```
--years N
```
(Simulation period in years, Default: 10)
```
--monthly-add AMOUNT
```
(Monthly contribution amount, JPY, Default: 0)
```
--target AMOUNT
```
(Target amount, JPY, Example: 15000000)
```
--reinvest-dividends
```
(Reinvest dividends, Default: ON)
```
--no-reinvest-dividends
```
(Do not reinvest dividends)

list -- List of Held Securities

Display the contents of portfolio.csv as-is.

bash

python3 .../run_portfolio.py list

Natural Language Routing

Refer to .claude/rules/intent-routing.md for natural language → skill determination.

Constraints

Japanese Stocks: 100-share units (board lot)
ASEAN Stocks: 100-share units (minimum commission 3,300 JPY)
Rakuten Securities compatible (commission structure)

portfolio.csv path:

.claude/skills/stock-portfolio/data/portfolio.csv

Output

Display results in Markdown format.

snapshot Output Items

Symbol / Name / Quantity Held / Acquisition Price / Current Price / Valuation Amount / Profit/Loss / Profit/Loss Ratio / Currency

analyze Output Items

Sector HHI / Region HHI / Currency HHI / Size HHI (KIK-438)
Composition ratio for each axis (Size-based composition table: Large/Mid/Small/ETF/Unknown)
ETF Notes (Note on unimplemented look-through)
Risk level determination

health Output Items

Individual Stock Table: Symbol (Small-cap stocks have
[Small-Cap]
badge) / Profit/Loss Ratio / Trend / Cross Event / Quality of Change / Alert / Long-Term Suitability / Shareholder Return Stability
ETF Table (KIK-469 P2): Symbol / Profit/Loss / Trend / Expense Ratio / AUM / ETF Score / Alert
Details of securities with alerts (Reason, SMA/RSI values, Cross occurrence date/elapsed days, Change Score, Shareholder Return Stability, Recommended Action)
Small-Cap Allocation: Summary of small-cap ratio for entire portfolio (✅Normal/⚠️Warning/🔴Danger)

forecast Output Items

Portfolio-wide: 3-scenario returns (Optimistic/Base/Pessimistic) + Profit/Loss Amount + Total Valuation
Watchlist Section: List of securities with value trap warnings
TOP 3 / BOTTOM 3: Expected Return Rankings (with number of analysts)
Security-specific: Analyst Target Price / Forward PER / Number of News / X Sentiment / 3 Scenarios / ETFs display annual volatility +
[ETF]
badge

what-if Output Items

[When Selling] Context of Sale Candidates (KIK-470): Screening appearance count, investment notes, research history
Before/After HHI comparison (Sector/Region/Currency)
Fundamentals of added securities
Concentration change determination
[When Swapping] Sale Security Table (Estimated Sale Proceeds)
[When Swapping] Cash Flow (Required Purchase Funds / Sale Proceeds / Difference)
[When Swapping] Sale Security Health Check
[When Swapping] "This swap is recommended / Consider with Caution / Not Recommended"

backtest Output Items

Daily returns by screening date
Benchmark comparison (Excess Return)
Win Rate, Statistical Values

adjust Output Items

Market Regime (Regime Name/SMA50 vs SMA200/RSI/Drawdown)
HIGH Priority Table: SELL/SWAP/TRIM_CLASS Actions
MEDIUM Priority Table: FLAG/SELL Actions
LOW Priority Table: FLAG Actions
Summary (Number of HIGH/MEDIUM/LOW Actions, Regime)

rebalance Output Items

Current HHI (Sector/Region/Currency) and Target HHI
Sale Candidates (Symbol, Shares, Reason)
Purchase Candidates (Symbol, Shares, Reason, Dividend Yield)
Predicted HHI after rebalancing

simulate Output Items

Annual transition table (Year/Valuation Amount/Total Contributions/Investment Gains/Total Dividends)
3-scenario comparison (Final year of Optimistic/Base/Pessimistic)
Target Achievement Analysis (Year of Achievement / Required Monthly Contribution)
Compound interest effect of dividend reinvestment

Execution Examples

bash

# Snapshot
python3 .../run_portfolio.py snapshot

# Purchase Record
python3 .../run_portfolio.py buy --symbol 7203.T --shares 100 --price 2850 --currency JPY --date 2025-06-15 --memo Toyota

# Sale Record
python3 .../run_portfolio.py sell --symbol AAPL --shares 5

# Structural Analysis
python3 .../run_portfolio.py analyze

# List Display
python3 .../run_portfolio.py list

# Health Check
python3 .../run_portfolio.py health

# Estimated Return
python3 .../run_portfolio.py forecast

# Rebalancing Proposal
python3 .../run_portfolio.py rebalance
python3 .../run_portfolio.py rebalance --strategy defensive
python3 .../run_portfolio.py rebalance --reduce-sector Technology --additional-cash 1000000

# What-If Simulation (Add only)
python3 .../run_portfolio.py what-if --add "7203.T:100:2850,AAPL:10:250"

# What-If Simulation (Swap: Sell 7203.T → Buy 9984.T) (KIK-451)
python3 .../run_portfolio.py what-if --remove "7203.T:100" --add "9984.T:50:7500"

# What-If Simulation (Sell only) (KIK-451)
python3 .../run_portfolio.py what-if --remove "7203.T:50"

# Adjustment Advisor (KIK-496)
python3 .../run_portfolio.py adjust
python3 .../run_portfolio.py adjust --full

# Backtesting
python3 .../run_portfolio.py backtest --preset alpha --region jp --days 90

Prior Knowledge Integration Rules (KIK-466)

health Command

If the output of get_context.py includes the following, integrate with health check results in the response:

Trade History (BOUGHT/SOLD): Reference purchase price and date to add context of unrealized profit/loss. If a sold security appears in warnings, clearly state "No problem as it has been sold"
Investment Notes (Note): If there are thesis/concern notes, cross-reference with health check results. e.g., "Value trap concern note exists → BT score is also high this time → Requires close attention"
Previous Health Check (HealthCheck): Show differences from previous check. e.g., "Previous HOLD → Current EXIT: Situation deteriorated" "Previous EXIT → Current HOLD: Improved"
Screening History (SURFACED): If a warning security was in the top rankings in past screenings, e.g., "High attention (3 times in top rankings) but requires caution now"
Thesis Progress: If thesis note is over 90 days old, prompt "Time to review thesis"

snapshot / forecast

If there is a previous snapshot/forecast, add difference comments
e.g., "Compared to previous: Valuation amount +5.2%, return improved"

Prompt to Record Analysis Conclusions

When providing a response that includes a specific judgment for EXIT/warnings (e.g., "Recommended to sell" "Continue holding"):

💡 Would you like to record this judgment as an investment note?

stock-portfolio

NPX Install

Tags

SKILL.md Content (Chinese)

Portfolio Management Skill

Execution Command

Command List

snapshot -- Portfolio Snapshot

buy -- Add Purchase Record

sell -- Add Sale Record

review -- Trade Performance Review (KIK-441)

analyze -- Structural Analysis

health -- Health Check

adjust -- Portfolio Adjustment Advisor (KIK-496)

rebalance -- Rebalancing Proposal

forecast -- Estimated Return

what-if -- What-If Simulation (KIK-376 / KIK-451)

backtest -- Backtesting

simulate -- Compound Interest Simulation

list -- List of Held Securities

Natural Language Routing

Constraints

Output

snapshot Output Items

analyze Output Items

health Output Items

forecast Output Items

what-if Output Items

backtest Output Items

adjust Output Items

rebalance Output Items

simulate Output Items

Execution Examples

Prior Knowledge Integration Rules (KIK-466)

health Command

snapshot / forecast

Prompt to Record Analysis Conclusions