FTD Detector runs a Python script that pulls S&P 500 and Nasdaq Composite history from the Financial Modeling Prep API and tracks a market correction through rally attempt, Follow-Through Day window and confirmation, using William O’Neil’s methodology.
It reports the current state, a 0-100 quality score for the signal, key watch levels and post-signal health such as distribution days. The score is a technical heuristic. The skill does not assess portfolio exposure and gives no investment advice.
What You Get
- A JSON and a Markdown report named with the run timestamp
- The combined market state across both indices, from no signal to confirmed
- A 0-100 quality score with a signal label, marked as a technical heuristic
- Key watch levels such as the swing low and the Follow-Through Day low
- Post-signal health: distribution day count, invalidation check and power trend
- Explicit data-gap flags when price bars are missing or invalid
Common Use Cases
- Checking whether a bounce after a correction has produced a confirmed Follow-Through Day
- Counting rally-attempt days and seeing which day the qualifying window is on
- Reviewing the health of a signal after it appears, including distribution days
- Pairing with a top-detection skill to look at both sides of a market cycle
What Makes It Unique
The skill keeps the event separate from its current health: a close below the signal-day low is a warning, while an intraday low below the recorded Day 1 low fails the rally. Missing or invalid bars are never read as zero; they produce an explicit data-gap state and a score of zero. The exposure field always says Not assessed, so the score is never turned into a portfolio percentage.
Under The Hood
Claude runs a Python script (ftd_detector.py) from the skill folder with a Financial Modeling Prep API key from the FMP_API_KEY environment variable or a command-line flag. The script makes about four calls to the FMP web API for index history and quotes, runs the state machine locally and writes the JSON and Markdown reports to disk. Reference documents on the method and post-signal health are loaded only when needed. Python 3.9 or later with the requests library is required.