mcpField
F
ftd-detector

ftd-detector

github.com/mphinanceData & databases3284 installsUpdated 5d ago
Repository

About ftd-detector

FTD Detector is an agent skill that assesses Follow-Through Day signals after market corrections using William O'Neil's methodology. It analyzes S&P 500 and QQQ data, then reports a signal-quality score and suggested exposure guidance.

Key features

  1. 01Analyze S&P 500 and QQQ data
  2. 02Track correction and rally states
  3. 03Assess post-FTD market health
  4. 04Score signal quality from 0 to 100
  5. 05Generate JSON and Markdown reports

Use cases

  1. 01Assess bottom signals after a correction
  2. 02Review rally attempts and FTD confirmation
  3. 03Evaluate exposure after a market decline

MCP support

This is an agent skill, not an MCP server. The README does not describe an MCP connection or interface.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mphinance/alpha-skills --skill ftd-detector

After installing, type/ftd-detectorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
references/
ftd_methodology.md
post_ftd_guide.md
scripts/
fmp_client.py
ftd_detector.py
post_ftd_monitor.py
rally_tracker.py
report_generator.py
scripts/tests/
conftest.py
helpers.py
test_fmp_client.py
test_post_ftd_monitor.py
test_rally_tracker.py

Details

From the project README

FTD Detector Skill

Purpose

Detect Follow-Through Day (FTD) signals that confirm a market bottom, using William O'Neil's proven methodology. Generates a quality score (0-100) with exposure guidance for re-entering the market after corrections.

Complementary to Market Top Detector:

  • Market Top Detector = defensive (detects distribution, rotation, deterioration)
  • FTD Detector = offensive (detects rally attempts, bottom confirmation)

When to Use This Skill

English:

  • User asks "Is the market bottoming?" or "Is it safe to buy again?"
  • User observes a market correction (3%+ decline) and wants re-entry timing
  • User asks about Follow-Through Days or rally attempts
  • User wants to assess if a recent bounce is sustainable
  • User asks about increasing equity exposure after a correction
  • Market Top Detector shows elevated risk and user wants bottom signals

Japanese:

  • 「底打ちした？」「買い戻して良い？」
  • 調整局面（3%以上の下落）からのエントリータイミング
  • フォロースルーデーやラリーアテンプトについて
  • 直近の反発が持続可能か評価したい
  • 調整後のエクスポージャー拡大の判断
  • Market Top Detectorが高リスク表示の後の底打ちシグナル確認

Difference from Market Top Detector

AspectFTD DetectorMarket Top Detector
FocusBottom confirmation (offensive)Top detection (defensive)
TriggerMarket correction (3%+ decline)Market at/near highs
SignalRally attempt → FTD → Re-entryDistribution → Deterioration → Exit
Score0-100 FTD quality0-100 top probability
ActionWhen to increase exposureWhen to reduce exposure

Execution Workflow

Phase 1: Execute Python Script

Run the FTD detector script:

python3 skills/ftd-detector/scripts/ftd_detector.py --api-key $FMP_API_KEY

The script will:

  1. Fetch S&P 500 and QQQ historical data (60+ trading days) from FMP API
  2. Fetch current quotes for both indices
  3. Run dual-index state machine (correction → rally → FTD detection)
  4. Assess post-FTD health (distribution days, invalidation, power trend)
  5. Calculate quality score (0-100)
  6. Generate JSON and Markdown reports

API Budget: 4 calls (well within free tier of 250/day)

Phase 2: Present Results

Present the generated Markdown report to the user, highlighting:

  • Current market state (correction, rally attempt, FTD confirmed, etc.)
  • Quality score and signal strength
  • Recommended exposure level
  • Key watch levels (swing low, FTD day low)
  • Post-FTD health (distribution days, power trend)
Phase 3: Contextual Guidance

Based on the market state, provide additional guidance:

If FTD Confirmed (score 60+):

  • Suggest looking at leading stocks in proper bases
  • Reference CANSLIM screener for candidate stocks
  • Remind about position sizing and stops

If Rally Attempt (Day 1-3):

  • Advise patience, do not buy ahead of FTD
  • Suggest building watchlists

If No Correction:

  • FTD analysis is not applicable in uptrend
  • Redirect to Market Top Detector for defensive signals

State Machine

NO_SIGNAL → CORRECTION → RALLY_ATTEMPT → FTD_WINDOW → FTD_CONFIRMED
                ↑              ↓               ↓              ↓
                └── RALLY_FAILED ←─────────────┘     FTD_INVALIDATED
StateDefinition
NO_SIGNALUptrend, no qualifying correction
CORRECTION3%+ decline with 3+ down days
RALLY_ATTEMPTDay 1-3 of rally from swing low
FTD_WINDOWDay 4-10, waiting for qualifying FTD
FTD_CONFIRMEDValid FTD signal detected
RALLY_FAILEDRally broke below swing low
FTD_INVALIDATEDClose below FTD day's low

Quality Score (0-100)

ScoreSignalExposure
80-100Strong FTD75-100%
60-79Moderate FTD50-75%
40-59Weak FTD25-50%
<40No FTD / Failed0-25%

Prerequisites

  • FMP API Key: Required. Set FMP_API_KEY environment variable or pass via --api-key flag.
  • Python 3.8+: With requests library installed.
  • API Budget: 4 calls per execution (well within FMP free tier of 250/day).

Output Files

  • JSON: ftd_detector_YYYY-MM-DD_HHMMSS.json
  • Markdown: ftd_detector_YYYY-MM-DD_HHMMSS.md

Reference Documents

skills/ftd-detector/references/ftd_methodology.md
  • O'Neil's FTD rules in detail
  • Rally attempt mechanics and day counting
  • Historical FTD examples (2020 March, 2022 October)
skills/ftd-detector/references/post_ftd_guide.md
  • Post-FTD distribution day failure rates
  • Power Trend definition and conditions
  • Success vs failure pattern comparison
When to Load References
  • First use: Load skills/ftd-detector/references/ftd_methodology.md for full understanding
  • Post-FTD questions: Load skills/ftd-detector/references/post_ftd_guide.md
  • Regular execution: References not needed - script handles analysis

Comments

Markdown supported