$npx -y skills add mphinance/alpha-skills --skill earnings-trade-analyzerAnalyze recent post-earnings stocks using a 5-factor scoring system (Gap Size, Pre-Earnings Trend, Volume Trend, MA200 Position, MA50 Position). Scores each stock 0-100 and assigns A/B/C/D grades. Use when user asks about earnings trade analysis, post-earnings momentum screening,
| 1 | # Earnings Trade Analyzer - Post-Earnings 5-Factor Scoring |
| 2 | |
| 3 | Analyze recent post-earnings stocks using a 5-factor weighted scoring system to identify the strongest earnings reactions for potential momentum trades. |
| 4 | |
| 5 | ## When to Use |
| 6 | |
| 7 | - User asks for post-earnings trade analysis or earnings gap screening |
| 8 | - User wants to find the best recent earnings reactions |
| 9 | - User requests earnings momentum scoring or grading |
| 10 | - User asks about post-earnings accumulation day (PEAD) candidates |
| 11 | |
| 12 | ## Prerequisites |
| 13 | |
| 14 | - FMP API key (set `FMP_API_KEY` environment variable or pass `--api-key`) |
| 15 | - Free tier (250 calls/day) is sufficient for default screening (lookback 2 days, top 20) |
| 16 | - Paid tier recommended for larger lookback windows or full screening |
| 17 | |
| 18 | ## Workflow |
| 19 | |
| 20 | ### Step 1: Run the Earnings Trade Analyzer |
| 21 | |
| 22 | Execute the analyzer script: |
| 23 | |
| 24 | ```bash |
| 25 | # Default: last 2 days of earnings, top 20 results |
| 26 | python3 skills/earnings-trade-analyzer/scripts/analyze_earnings_trades.py --output-dir reports/ |
| 27 | |
| 28 | # Custom lookback and market cap filter |
| 29 | python3 skills/earnings-trade-analyzer/scripts/analyze_earnings_trades.py \ |
| 30 | --lookback-days 5 \ |
| 31 | --min-market-cap 1000000000 \ |
| 32 | --top 30 \ |
| 33 | --output-dir reports/ |
| 34 | |
| 35 | # With entry quality filter |
| 36 | python3 skills/earnings-trade-analyzer/scripts/analyze_earnings_trades.py \ |
| 37 | --apply-entry-filter \ |
| 38 | --output-dir reports/ |
| 39 | ``` |
| 40 | |
| 41 | ### Step 2: Review Results |
| 42 | |
| 43 | 1. Read the generated JSON and Markdown reports |
| 44 | 2. Load `references/scoring_methodology.md` for scoring interpretation context |
| 45 | 3. Focus on Grade A and B stocks for actionable setups |
| 46 | |
| 47 | ### Step 3: Present Analysis |
| 48 | |
| 49 | For each top candidate, present: |
| 50 | - Composite score and letter grade (A/B/C/D) |
| 51 | - Earnings gap size and direction |
| 52 | - Pre-earnings 20-day trend |
| 53 | - Volume ratio (20-day vs 60-day average) |
| 54 | - Position relative to 200-day and 50-day moving averages |
| 55 | - Weakest and strongest scoring components |
| 56 | |
| 57 | ### Step 4: Provide Actionable Guidance |
| 58 | |
| 59 | Based on grades: |
| 60 | - **Grade A (85+):** Strong earnings reaction with institutional accumulation - consider entry |
| 61 | - **Grade B (70-84):** Good earnings reaction worth monitoring - wait for pullback or confirmation |
| 62 | - **Grade C (55-69):** Mixed signals - use caution, additional analysis needed |
| 63 | - **Grade D (<55):** Weak setup - avoid or wait for better conditions |
| 64 | |
| 65 | ## Output |
| 66 | |
| 67 | - `earnings_trade_analyzer_YYYY-MM-DD_HHMMSS.json` - Structured results with schema_version "1.0" |
| 68 | - `earnings_trade_analyzer_YYYY-MM-DD_HHMMSS.md` - Human-readable report with tables |
| 69 | |
| 70 | ## Resources |
| 71 | |
| 72 | - `references/scoring_methodology.md` - 5-factor scoring system, grade thresholds, and entry quality filter rules |