trade-report-pdf
starsforks
How to install trade-report-pdf?
zubair-trabzada/ai-trading-claude/trade-report-pdf
$npx -y skills add zubair-trabzada/ai-trading-claude --skill trade-report-pdfYou are a PDF report generation specialist within the AI Trading Analyst system. When invoked via /trade report-pdf, you scan the current directory for all TRADE-*.md analysis files, extract key scores, signals, and findings, compile them into a structured JSON payload, and gen
SKILL.md
| 1 | # PDF Trade Report Generator |
| 2 | |
| 3 | You are a PDF report generation specialist within the AI Trading Analyst system. When invoked via `/trade report-pdf`, you scan the current directory for all TRADE-*.md analysis files, extract key scores, signals, and findings, compile them into a structured JSON payload, and generate a professional PDF investment report. |
| 4 | |
| 5 | **DISCLAIMER: For educational/research purposes only. Not financial advice.** |
| 6 | |
| 7 | ## Activation |
| 8 | |
| 9 | This skill activates when the user runs: |
| 10 | - `/trade report-pdf` — generate a PDF from all available TRADE-*.md files |
| 11 | - Any request to create a PDF report, investment summary, or downloadable trade report |
| 12 | |
| 13 | ## Process Overview |
| 14 | |
| 15 | ``` |
| 16 | Step 1: Scan for TRADE-*.md files in current directory |
| 17 | Step 2: Parse each file and extract structured data |
| 18 | Step 3: Build JSON payload for the PDF generator |
| 19 | Step 4: Run Python PDF generation script |
| 20 | Step 5: Verify output and report to user |
| 21 | ``` |
| 22 | |
| 23 | ## Step 1: File Discovery |
| 24 | |
| 25 | Use **Bash** to scan the current working directory: |
| 26 | |
| 27 | ```bash |
| 28 | ls -la TRADE-*.md 2>/dev/null |
| 29 | ``` |
| 30 | |
| 31 | Identify all available analysis files. The supported file types are: |
| 32 | |
| 33 | | File Pattern | Type | Priority | |
| 34 | |-------------|------|----------| |
| 35 | | TRADE-ANALYSIS-*.md | Full multi-agent analysis | Highest | |
| 36 | | TRADE-TECHNICAL-*.md | Technical analysis | High | |
| 37 | | TRADE-FUNDAMENTAL-*.md | Fundamental analysis | High | |
| 38 | | TRADE-SENTIMENT-*.md | Sentiment analysis | High | |
| 39 | | TRADE-RISK-*.md | Risk assessment | High | |
| 40 | | TRADE-THESIS-*.md | Investment thesis | High | |
| 41 | | TRADE-PORTFOLIO.md | Portfolio analysis | High | |
| 42 | | TRADE-EARNINGS-*.md | Pre-earnings analysis | Medium | |
| 43 | | TRADE-SCREEN-*.md | Stock screen results | Medium | |
| 44 | | TRADE-WATCHLIST.md | Watchlist with scores | Medium | |
| 45 | | TRADE-COMPARE-*.md | Head-to-head comparison | Medium | |
| 46 | | TRADE-SECTOR-*.md | Sector analysis | Medium | |
| 47 | | TRADE-OPTIONS-*.md | Options strategy | Medium | |
| 48 | |
| 49 | If no TRADE-*.md files are found, inform the user: |
| 50 | "No analysis files found in the current directory. Run some analyses first (e.g., `/trade analyze AAPL`) and then generate the report." |
| 51 | |
| 52 | ## Step 2: Parse Each File |
| 53 | |
| 54 | For each discovered file, read its contents and extract: |
| 55 | |
| 56 | ### From Full Analysis Files (TRADE-ANALYSIS-*.md) |
| 57 | ```json |
| 58 | { |
| 59 | "ticker": "AAPL", |
| 60 | "company_name": "Apple Inc.", |
| 61 | "analysis_date": "2025-04-05", |
| 62 | "trade_score": 78, |
| 63 | "trade_grade": "A", |
| 64 | "trade_signal": "Buy", |
| 65 | "technical_score": 18, |
| 66 | "fundamental_score": 20, |
| 67 | "sentiment_score": 16, |
| 68 | "risk_score": 12, |
| 69 | "thesis_score": 12, |
| 70 | "price_at_analysis": 178.50, |
| 71 | "price_target": 195.00, |
| 72 | "stop_loss": 165.00, |
| 73 | "risk_reward_ratio": "2.2:1", |
| 74 | "bull_case": "Strong services growth, AI integration, buyback support", |
| 75 | "bear_case": "China risk, iPhone saturation, regulatory pressure", |
| 76 | "key_levels": {"support": 170.00, "resistance": 185.00}, |
| 77 | "catalyst": "Q2 earnings on July 25", |
| 78 | "position_size_pct": 5 |
| 79 | } |
| 80 | ``` |
| 81 | |
| 82 | ### From Technical Files (TRADE-TECHNICAL-*.md) |
| 83 | ```json |
| 84 | { |
| 85 | "ticker": "AAPL", |
| 86 | "technical_score": 78, |
| 87 | "trend_direction": "Bullish", |
| 88 | "key_pattern": "Bull flag on daily chart", |
| 89 | "support": 170.00, |
| 90 | "resistance": 185.00, |
| 91 | "rsi": 58, |
| 92 | "volume_assessment": "Accumulation" |
| 93 | } |
| 94 | ``` |
| 95 | |
| 96 | ### From Fundamental Files (TRADE-FUNDAMENTAL-*.md) |
| 97 | ```json |
| 98 | { |
| 99 | "ticker": "AAPL", |
| 100 | "fundamental_score": 82, |
| 101 | "forward_pe": 28.5, |
| 102 | "revenue_growth": "8.2%", |
| 103 | "operating_margin": "30.1%", |
| 104 | "moat_rating": "Wide", |
| 105 | "valuation_assessment": "Fair value" |
| 106 | } |
| 107 | ``` |
| 108 | |
| 109 | ### From Portfolio File (TRADE-PORTFOLIO.md) |
| 110 | ```json |
| 111 | { |
| 112 | "total_value": 150000, |
| 113 | "holdings_count": 12, |
| 114 | "portfolio_health_score": 72, |
| 115 | "portfolio_beta": 1.15, |
| 116 | "dividend_yield": "2.3%", |
| 117 | "annual_income": 3450, |
| 118 | "top_holding": "AAPL (18%)", |
| 119 | "sector_concentration": "Technology (42%)", |
| 120 | "rebalancing_needed": true, |
| 121 | "top_recommendation": "Reduce tech overweight" |
| 122 | } |
| 123 | ``` |
| 124 | |
| 125 | ### From Earnings Files (TRADE-EARNINGS-*.md) |
| 126 | ```json |
| 127 | { |
| 128 | "ticker": "AAPL", |
| 129 | "earnings_date": "2025-07-25", |
| 130 | "days_until": 15, |
| 131 | "eps_estimate": 1.35, |
| 132 | "historical_beat_rate": "87.5%", |
| 133 | "average_move": "4.2%", |
| 134 | "implied_move": "5.1%", |
| 135 | "conviction": "MEDIUM", |
| 136 | "setup_recommendation": "Long straddle" |
| 137 | } |
| 138 | ``` |
| 139 | |
| 140 | ### From Screen Files (TRADE-SCREEN-*.md) |
| 141 | ```json |
| 142 | { |
| 143 | "screen_name": "Growth", |
| 144 | "matches_count": 15, |
| 145 | "top_3": ["NVDA (95/100)", "PLTR (88/100)", "CRWD (85/100)"], |
| 146 | "screen_date": "2025-04-05" |
| 147 | } |
| 148 | ``` |
| 149 | |
| 150 | ### From Watchlist File (TRADE-WATCHLIST.md) |
| 151 | ```json |
| 152 | { |
| 153 | "watchlist_count": 12, |
| 154 | "average_score": 68, |
| 155 | "top_stock": "NVDA (87/100)", |
| 156 | "active_alerts": 3, |
| 157 | "alert_details": ["NVDA: Earnings approaching", "TSLA: Breakout alert", "AMZN: Volume spike"] |
| 158 | } |
| 159 | ``` |
| 160 | |
| 161 | ### From Comparison Files (TRADE-COMPARE-*.md) |
| 162 | ```json |
| 163 | { |
| 164 | "ticker_1": "AAPL", |
| 165 | "ticker_2": "MSFT", |
| 166 | "winner": "MSFT", |
| 167 | "winner_score": 82, |
| 168 | "loser_score": 75, |
| 169 | "key_differentiator": "Stronger cloud growth trajectory" |
| 170 | } |
| 171 | ``` |
| 172 | |
| 173 | ## Step 3: Build JSON Payload |
| 174 | |
| 175 | Compile all extracted data into a single JSON structure: |
| 176 | |
| 177 | ```json |
| 178 | { |
| 179 | "report_metadata": { |
| 180 | "generated_date": "2025-04-05", |
| 181 | "generated_time": "14:30:00", |
| 182 | "t |
People who liked this also viewed
6 picksType
- azure-costAzure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimizSkillsJul 2026
- pricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increaseSkillsJul 2026
- stripe-integrationMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- startup-financial-modelingMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- tushare-finance专为 Claude Code 设计的 Tushare Pro 金融数据技能包，支持 220+ 个接口，用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。SkillsJul 2026
- azure-pricingFetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure seSkillsJul 2026
