Equity Analyst Test
by @saebyeok-im
Analyze Korean stock fundamentals, news, and technicals using a strict weighted framework to score investment attractiveness and give BUY/HOLD/AVOID recommen...
clawhub install equity-analyst-test๐ About This Skill
name: equity-analyst description: ์ ๋ฌธ ํฌ์ ๋ถ์๊ฐ AI๋ก, ํ๊ตญ ์ฃผ์ ์ข ๋ชฉ์ ์ฌ๋ฌด์ ํ, ๋ด์ค, ์ฐจํธ๋ฅผ ๋ถ์ํ์ฌ Investment Attractiveness Score (0-100)์ BUY/HOLD/AVOID ์ถ์ฒ์ ์ ๊ณตํฉ๋๋ค. ๋ค์ด๋ฒ ๊ธ์ต ๋ฐ์ดํฐ๋ฅผ ์ฌ์ฉํ๋ฉฐ, ํ๋กฌํํธ์ ๋ช ์๋ ์๊ฒฉํ ์ฐ์ ์์(Financial > News > Chart)์ ๊ฐ์ค์น๋ฅผ ๋ฐ๋ฆ ๋๋ค. trigger: ์ฌ์ฉ์๊ฐ "xxx ์ฃผ์ ๋ถ์ํด์ค", "xxx ํฌ์ ๋งค๋ ฅ๋ ์๋ ค์ค", "xxx ๋ฆฌํฌํธ ์จ์ค" ๋ฑ์ผ๋ก ๋ถ์ ์์ฒญ์ ํ์ ๋.
Equity Analyst Skill
This skill provides professional-grade equity analysis for Korean stocks listed on KRX. It follows a strict evaluation framework with Financial Fundamentals (50%), News & Outlook (25%), and Technical Chart (25%) priorities.
When to Use This Skill
Do NOT use for: Non-Korean stocks, cryptocurrency, or when user wants casual/opinion-based advice without rigorous framework.
Quick Start
1. Identify the stock ticker (e.g., 005930 for ์ผ์ฑ์ ์, 000660 for SKํ์ด๋์ค)
2. Use browser tool to navigate to Naver Finance page: https://finance.naver.com/item/main.naver?code={ticker}
3. Extract required data (see Data Requirements below)
4. Apply evaluation framework (see Framework section)
5. Generate structured report in specified format
Data Requirements
Collect the following data from Naver Finance main page:
Financial Metrics
News & Outlook (summary)
Technical/Chart Conditions (summary)
Note: Bollinger Band and other complex indicators are NOT required. Keep chart description simple: trend + current state.
Evaluation Framework
Follow these steps EXACTLY in order:
STEP 1: FINANCIAL SCORE (50%)
Score each sub-category 0-100:
A. Valuation (PER, PBR) - Weight 30%
B. Profitability (ROE, Operating Margin) - Weight 30%
C. Growth (Revenue Growth) - Weight 25%
D. Stability (Debt Ratio) - Weight 15%
FinancialScore = Valuationร0.30 + Profitabilityร0.30 + Growthร0.25 + Stabilityร0.15
Special Rule: If BOTH ProfitabilityScore AND GrowthScore are below 30, cap FinancialScore at maximum 50 ( regardless of other scores ).
STEP 2: NEWS & OUTLOOK SCORE (25%)
Evaluate qualitative factors:
Rules:
Output: NewsScore (0-100)
STEP 3: TECHNICAL / CHART SCORE (25%)
Evaluate timing and market behavior:
Rules:
Output: ChartScore (0-100)
FINAL SCORE
FinalScore = (FinancialScore ร 0.50) + (NewsScore ร 0.25) + (ChartScore ร 0.25)
Verdict Categories
Output Format
Return EXACTLY this structure:
1. Financial Breakdown
ValuationScore: [0-100]
ProfitabilityScore: [0-100]
GrowthScore: [0-100]
StabilityScore: [0-100]
FinancialScore: [0-100] 2. NewsScore: [0-100]
3. ChartScore: [0-100]
4. Final Investment Attractiveness Score: XX / 100
5. Verdict: [BUY|BUY_LEAN|HOLD|AVOID]
6. Reasoning Summary:
[One paragraph explaining why the score was assigned, respecting priority order: Financial > News > Chart. Be conservative, logic-driven. Do NOT give investment advice.]
Examples
Example 1: SKํ์ด๋์ค (from real data)
1. Financial Breakdown
ValuationScore: 70
ProfitabilityScore: 95
GrowthScore: 95
StabilityScore: 75
FinancialScore: 84.5 2. NewsScore: 70
3. ChartScore: 55
4. Final Investment Attractiveness Score: 73.5 / 100
5. Verdict: BUY_LEAN
6. Reasoning Summary:
SKํ์ด๋์ค๋ ์ฌ๋ฌด์ ํ๊ฐ ๋งค์ฐ ๊ฐ๋ ฅํฉ๋๋ค. ROE 43.20%, ์์
์ด์ต๋ฅ 46.67%, 43.7%์ ๋งค์ถ ์ฑ์ฅ๋ฅ ์ ์
๊ณ ์ต์์ ์์ค์ด๋ฉฐ, PER 17.11๋ฐฐ๋ ์๋์ ์ผ๋ก ์ ํ๊ฐ๋์ด ์์ต๋๋ค. ๋ถ์ฑ๋น์จ 64.12%๋ ๋ฐ๋์ฒด ์
์ฒด๋ก์ ์ ์ ๋ฒ์ ๋ด์ ์์ต๋๋ค. ๋ด์ค ์ธก๋ฉด์์๋ HBM4 ๊ณต๊ธ๊ณผ AI memory ์์ ์ฆ๊ฐ๊ฐ ์ฃผ๊ฐ์ ๊ธ์ ์ ์ด๋, ์ธ๊ตญ์ธ ๋งค๋์ธ๊ฐ ์ผ๋ถ ๋ถ์ ์ ์ํฅ์ ๋ฏธ์น๊ณ ์์ต๋๋ค. ๊ธฐ์ ์ ์ธก๋ฉด์์๋ ์ฅ๊ธฐ ์์น์ถ์ธ๋ ์ ์ง๋๊ณ ์์ผ๋, ๋จ๊ธฐ์ ์ผ๋ก ์กฐ์ ๊ตญ๋ฉด์ ์์ด ๋งค์ ํ์ด๋ฐ์ ์ ์ค์ ๊ธฐํ ํ์๊ฐ ์์ต๋๋ค. ์ฌ๋ฌด์ ์ฐ์์ฑ๊ณผ ์ฑ์ฅ์ฑ์๋ ๋ถ๊ตฌ, ๋จ๊ธฐ ์ฐจํธ์ ๋ถํ์ค์ฑ์ผ๋ก ์ธํด "buy with caution" ์ํ๋ก ํ๊ฐ๋ฉ๋๋ค.
Example 2: Weak Fundamentals
... (similar structure) ...
ValuationScore: 25 (PER 150, PBR 8.5 - extremely overvalued)
ProfitabilityScore: 20 (ROE 2%, margin negative)
...
Verdict: AVOID
...
Scripts
The skill includes these scripts:
scripts/analyze.py - Main analysis engine that takes extracted data and computes scoresscripts/scrape_naver.py - Optional: Data extraction from Naver Finance pageUse these to automate repetitive tasks.
References
Detailed evaluation criteria and examples: references/framework.md
Notes
Troubleshooting
Missing data: If any metric is unavailable, treat as neutral (score 50) but note in reasoning.
Conflicting signals: Follow priority order: Financial > News > Chart. Low financial score can NOT be compensated by good news or chart.
Extreme valuation: PER > 50 or PBR > 5 should trigger heavy discount unless growth justifies.
๐ก Examples
Example 1: SKํ์ด๋์ค (from real data)
1. Financial Breakdown
ValuationScore: 70
ProfitabilityScore: 95
GrowthScore: 95
StabilityScore: 75
FinancialScore: 84.5 2. NewsScore: 70
3. ChartScore: 55
4. Final Investment Attractiveness Score: 73.5 / 100
5. Verdict: BUY_LEAN
6. Reasoning Summary:
SKํ์ด๋์ค๋ ์ฌ๋ฌด์ ํ๊ฐ ๋งค์ฐ ๊ฐ๋ ฅํฉ๋๋ค. ROE 43.20%, ์์
์ด์ต๋ฅ 46.67%, 43.7%์ ๋งค์ถ ์ฑ์ฅ๋ฅ ์ ์
๊ณ ์ต์์ ์์ค์ด๋ฉฐ, PER 17.11๋ฐฐ๋ ์๋์ ์ผ๋ก ์ ํ๊ฐ๋์ด ์์ต๋๋ค. ๋ถ์ฑ๋น์จ 64.12%๋ ๋ฐ๋์ฒด ์
์ฒด๋ก์ ์ ์ ๋ฒ์ ๋ด์ ์์ต๋๋ค. ๋ด์ค ์ธก๋ฉด์์๋ HBM4 ๊ณต๊ธ๊ณผ AI memory ์์ ์ฆ๊ฐ๊ฐ ์ฃผ๊ฐ์ ๊ธ์ ์ ์ด๋, ์ธ๊ตญ์ธ ๋งค๋์ธ๊ฐ ์ผ๋ถ ๋ถ์ ์ ์ํฅ์ ๋ฏธ์น๊ณ ์์ต๋๋ค. ๊ธฐ์ ์ ์ธก๋ฉด์์๋ ์ฅ๊ธฐ ์์น์ถ์ธ๋ ์ ์ง๋๊ณ ์์ผ๋, ๋จ๊ธฐ์ ์ผ๋ก ์กฐ์ ๊ตญ๋ฉด์ ์์ด ๋งค์ ํ์ด๋ฐ์ ์ ์ค์ ๊ธฐํ ํ์๊ฐ ์์ต๋๋ค. ์ฌ๋ฌด์ ์ฐ์์ฑ๊ณผ ์ฑ์ฅ์ฑ์๋ ๋ถ๊ตฌ, ๋จ๊ธฐ ์ฐจํธ์ ๋ถํ์ค์ฑ์ผ๋ก ์ธํด "buy with caution" ์ํ๋ก ํ๊ฐ๋ฉ๋๋ค.
Example 2: Weak Fundamentals
... (similar structure) ...
ValuationScore: 25 (PER 150, PBR 8.5 - extremely overvalued)
ProfitabilityScore: 20 (ROE 2%, margin negative)
...
Verdict: AVOID
...